Agents

1724

Claude Code agents aggregated from 412 top sources

All Agents

Backend Typescript Architect - Senior backend TypeScript architect specializing in Bun runtime, API design, database optimization, and scalable server architecture
UI Engineer - Frontend specialist in modern JavaScript/TypeScript frameworks, responsive design, and component-driven architecture
Python Backend Engineer - Expert Python backend developer proficient in FastAPI, Django, and async programming with SOLID principles
Senior Code Reviewer - Fullstack code reviewer with 15+ years experience analyzing security vulnerabilities, performance bottlenecks, and architectural decisions
Data Analyst - Data insights and visualization specialist
Azure Infrastructure Engineer - Azure infrastructure and Az PowerShell automation expert
Claude Code Subagents by 0xfurai - Production-ready collection of 100+ specialized subagents covering programming languages, frameworks, databases, DevOps, testing, and machine learning with automatic context-based delegation.
Code by Agents - Orchestration framework for designing and coordinating Claude Code agents with sophisticated orchestration logic
**pied-piper** - Orchestrate Team of AI Subagents for repetitive SDLC workflows
Taskade - AI-powered workspace with autonomous agents, real-time collaboration, and workflow automation with MCP integration
Tech Lead Orchestrator - Senior technical lead who analyzes complex projects and coordinates multi-step development tasks
Project Analyst - Technology stack detection specialist who enables intelligent agent routing
Team Configurator - AI team setup expert who detects your stack and configures optimal agent mappings
Laravel Backend Expert - Comprehensive Laravel development with MVC, services, and Eloquent patterns
Laravel Eloquent Expert - Advanced ORM optimization, complex queries, and database performance
Django Backend Expert - Models, views, services following current Django conventions
Django Orm Expert - Query optimization and database performance for Django applications
Universal Backend Developer - Polyglot backend development across multiple languages and frameworks
Universal Frontend Developer - Modern web technologies and responsive design for any framework
Universal API Architect - RESTful design, GraphQL, and framework-agnostic API architecture
Tailwind Frontend Expert - Tailwind CSS styling, utility-first development, and responsive components
Code Archaeologist - Explores, documents, and analyzes unfamiliar or legacy codebases
Code Reviewer (vijay) - Rigorous security-aware reviews with severity-tagged reports
Performance Optimizer - Identifies bottlenecks and applies optimizations for scalable systems
Documentation Specialist (vijay) - Crafts comprehensive READMEs, API specs, and technical documentation
Success Stories - 📄 License
Report issues - 💡 [Share ideas](https://github.com/vijaythecoder/awesome-claude-agents/discussions)
api-architect - | You are a senior API designer. Your single deliverable is an **authoritative specification** that an... | - | [vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents) |
documentation-specialist - | Turn complex code and architecture into clear, actionable documentation that accelerates onboarding... | - | [vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents) |
ml-data-expert - | Avant toute implémentation ML/Data, je DOIS récupérer la documentation la plus récente : | - | [vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents) |
Python Security Expert - | I am a specialized Python security expert with comprehensive knowledge of: | - | [vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents) |
Python DevOps/CI-CD Expert - | I am a specialized Python DevOps and CI/CD expert with deep knowledge of: | - | [vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents) |
Python Web Scraping Expert - | I am a specialized Python web scraping expert with comprehensive knowledge of: | - | [vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents) |
Python Performance Expert - | I am a specialized Python performance expert with deep knowledge of: | - | [vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents) |
Python Testing Expert - | I am a specialized Python testing expert with comprehensive knowledge of: | - | [vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents) |
Submit a pull request - to add it to this list!
performance-optimizer - | Locate real bottlenecks, apply high‑impact fixes, and prove the speed‑up with hard numbers. | - | [vijaythecoder/awesome-claude-agents](https://github.com/vijaythecoder/awesome-claude-agents) |
Sdd Orchestrator - Delegate-only coordinator that manages structured development workflow phases
Sdd Explorer - Reads codebase, compares approaches, identifies risks for feature development
Sdd Proposer - Creates proposals with intent, scope, and rollback plans for new features
Sdd Spec Writer - Writes delta specs with Given/When/Then scenarios for requirements
Sdd Designer - Creates architecture decisions and design rationale documents
Sdd Implementer - Writes code following specs and design with TDD workflow support
Sdd Verifier - Validates implementation against specs with real test execution
Sdd Archiver - Merges delta specs into main specs and archives completed changes
Claude Code 包括的エージェントコレクション - Language: English | 日本語要件分析から本番デプロイ・継続的メンテナンスまで、ソフトウェア開発ライフサイクル全体の自動化を可能にする専門サブエージェントの完全コレクションです。
UI Designer (contains) - Creates beautiful user interfaces with modern design principles
Contributing to Claude Code Agents - We welcome contributions to make this the most comprehensive collection of Claude Code agents for developers!
Claude Code Agents - Usage Examples - This document shows real-world examples of how these agents work together to solve common development challenges.
Content Writer (iannuttall) - Content writing specialist for technical and marketing content
code-refactorer - | Use this agent when you need to improve existing code structure, readability, or maintainability wit... | - | [iannuttall/claude-agents](https://github.com/iannuttall/claude-agents) |
content-writer - | Use this agent when you need to create compelling, informative content that explains complex topics... | - | [iannuttall/claude-agents](https://github.com/iannuttall/claude-agents) |
Claude Agents by Ian Nuttall - Ready-to-use subagents for code refactoring, frontend design, security auditing, project planning, content writing, and coding coaching.
code-reviewer-pro - | **Role**: Senior Staff Software Engineer specializing in comprehensive code reviews for quality, sec... | haiku | [lst97/claude-code-sub-agents](https://github.com/lst97/claude-code-sub-agents) |
postgresql-pglite-pro - | **Role**: Senior PostgreSQL and PgLite Engineer specializing in robust database architecture, perfor... | sonnet | [lst97/claude-code-sub-agents](https://github.com/lst97/claude-code-sub-agents) |
full-stack-developer - | **Role**: Versatile full stack developer specializing in end-to-end web application development. Exp... | sonnet | [lst97/claude-code-sub-agents](https://github.com/lst97/claude-code-sub-agents) |
Claude Squad - Manages multiple AI terminal agents including Claude Code and Aider in parallel
Claude Swarm - Launch Claude Code sessions connected to a swarm of coordinated agents
Claude Code Unified Agents - Combines features from multiple community agent repositories into one unified collection
Changelog - All notable changes to Claude Code Agent Farm are documented in this file. This project has no tagged releases or GitHub Releases. Changes are organized chronologically by date, grouped into developme
Claude Sub-agent System - AI-driven development workflow system built on spec-driven sub-agents
Agent Workflow - Automated Development Pipeline - Execute complete development workflow using intelligent sub-agent chaining with quality gates.
**claude-sub-agent** - (532 ⭐) - AI-driven development workflow system built on Claude Code Sub-Agents.
Frad's .claude - Minimalist Claude Code configuration focused on clean, essential customizations.
Claude Flow - Enterprise-grade AI orchestration platform for multi-agent workflows
Claude Code Flow - by ruvnet - This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and optimize code autonomously across recursive agent cycles.
Claude Flow Commands to Agent System Migration Summary - Claude Flow Commands to Agent System Migration Summary agent
Identify programming language - find <tool_path> -name "*.go" -o -name "*.c" -o -name "*.py" -o -name "*.rs" -o -name "*.cs" ls <tool_path>/Makefile <tool_path>/CMakeLists.txt <tool_path>/go.mod <tool_path>/Cargo.toml
Browser QA Report - **URL**: [tested URL] **Date**: [timestamp] **Flows Tested**: [list]
Runtime Bug Audit - Find runtime bugs and error handling issues. **NOT for security vulnerabilities** (use security-auditor for that). Output to `.claude/audits/AUDIT_BUGS.md`.
Code Quality Audit - Find code quality issues. **NOT for security (use security-auditor) or runtime bugs (use bug-auditor).** Output to `.claude/audits/AUDIT_CODE.md`.
Code Fixer - Read `.claude/audits/FIXES.md`. Implement fixes. Update checkboxes as you go.
Console Monitoring Session - **URL**: [monitored URL] **Start**: [timestamp] **End**: [timestamp] **Duration**: [time]
Database Audit - Analyze database layer for performance and correctness issues. Output to `.claude/audits/AUDIT_DB.md`.
Dependency Audit - Analyze project dependencies for security, maintenance, and bloat. Output to `.claude/audits/AUDIT_DEPS.md`.
Deploy Checker - Validate everything before deployment. Output to `.claude/audits/DEPLOY_CHECK.md`.
Documentation Audit - Find documentation gaps. Output to `.claude/audits/AUDIT_DOCS.md`.
Environment Validator - Validate environment configuration for completeness and security. Output to `.claude/audits/ENV_REPORT.md`.
Fix Planner - Read audits in `.claude/audits/`. Deduplicate and prioritize findings. Output to `.claude/audits/FIXES.md`.
Kill existing server on port - lsof -ti:{PORT} | xargs kill -9 2>/dev/null || true {DEV_SERVER_CMD} & sleep 3
Infrastructure Audit - Check deployment readiness. Output to `.claude/audits/AUDIT_INFRA.md`.
Performance Audit - Analyze application for performance bottlenecks. Output to `.claude/audits/AUDIT_PERF.md`.
PR Writer - Generate comprehensive pull request descriptions from git changes.
Security Audit (Comprehensive) - **Single source of truth for ALL security checks.** Output to `.claude/audits/AUDIT_SECURITY.md`.
Seed Generator - Analyze database schema and generate realistic test data. Write seed files directly.
SEO Audit - Analyze application for search engine optimization and discoverability. Output to `.claude/audits/AUDIT_SEO.md`.
Test Runner - Run tests. Validate fixes. Output to `.claude/audits/TEST_REPORT.md`.
Test Writer - Analyze code and generate appropriate tests. Write test files directly.
UI/UX Audit - Find consistency and usability issues. Output to `.claude/audits/AUDIT_UI_UX.md`.
Visual Regression Report - **Date**: [timestamp] **Pages Tested**: [count] **Changes Detected**: [count]
API Tester - Test all API endpoints for correctness and robustness. Output to `.claude/audits/API_TEST_REPORT.md`.
Oh My Pi - AI coding agent for terminal with hash-anchored edits, LSP, subagents and more
Contributing to Claude Agent Builder - Thanks for your interest in contributing! This project is open to everyone — whether you're a Claude Code power user or just getting started.
Business & Technical Agent Personas - 76+ specialized agent personas across 13 categories including technical excellence, AI automation, finance, marketing, design, and operations for comprehensive business transformation.
Universal Technical Implementation Template for Claude Code Subagents - Universal Technical Implementation Template for Claude Code Subagents agent
Workflow Orchestration Command - Enhanced with Optional Flags - You are the **product-manager-orchestrator** agent. You orchestrate specialist agents but NEVER write code yourself. This workflow supports enhanced thinking modes and MCP server integration through o
**claude-code-subagents** - (186 ⭐) - A collection of specialized AI agent personas designed to work seamlessly with Claude Code's Task tool, providing expert-level assistance across the full spectrum of software development challenges.
Compliance Check - | You are a compliance expert specializing in regulatory requirements for software systems including G... | - | [wshobson/agents](https://github.com/wshobson/agents) |
New Track - | Create a new track (feature, bug fix, chore, or refactor) with a detailed specification and phased i... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Implement - | Execute tasks from a track's implementation plan, following the workflow rules defined in `conductor... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Revert - | Revert changes by logical work unit with full git awareness. Supports reverting entire tracks, speci... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Status - | Display the current status of the Conductor project, including overall progress, active tracks, and... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Setup - | Initialize or resume Conductor project setup. This command creates foundational project documentatio... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Manage - | Manage the complete track lifecycle including archiving, restoring, deleting, renaming, and cleaning... | - | [wshobson/agents](https://github.com/wshobson/agents) |
conductor-validator - | You are an expert validator for Conductor project artifacts. Your role is to verify that Conductor's... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
Track Plan - | **Track ID:** {{TRACK_ID}} **Spec:** [spec.md](./spec.md) **Estimated Effort:** {{EFFORT_ESTIMATE}}... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Product - | **Name:** {{PRODUCT_NAME}} | - | [wshobson/agents](https://github.com/wshobson/agents) |
Tech Stack - | **Choice:** {{FRONTEND_FRAMEWORK}} **Version:** {{FRONTEND_VERSION}} | - | [wshobson/agents](https://github.com/wshobson/agents) |
Track Spec - | **Track ID:** {{TRACK_ID}} **Type:** {{TRACK_TYPE}} (feature | bug | chore | refactor) **Priority:**... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Product Guidelines - | {{BRAND_VOICE_DESCRIPTION}} | - | [wshobson/agents](https://github.com/wshobson/agents) |
Workflow - | 1. **plan.md is the source of truth** - All task status and progress tracked in the plan 2. **Test-D... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Tracks - | This file maintains the registry of all development tracks for the project. Each track represents a... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Index - | Central navigation for all Conductor artifacts and development tracks. | - | [wshobson/agents](https://github.com/wshobson/agents) |
Javascript - | Modern JavaScript (ES6+) best practices and conventions. | - | [wshobson/agents](https://github.com/wshobson/agents) |
General - | Universal coding principles that apply across all languages and frameworks. | - | [wshobson/agents](https://github.com/wshobson/agents) |
Html Css - | Web standards for semantic markup, maintainable styling, and accessibility. | - | [wshobson/agents](https://github.com/wshobson/agents) |
Go - | Go idioms and conventions for clean, maintainable code. | - | [wshobson/agents](https://github.com/wshobson/agents) |
Csharp - | C# conventions and best practices for .NET development. | - | [wshobson/agents](https://github.com/wshobson/agents) |
Typescript - | TypeScript-specific conventions and best practices for type-safe development. | - | [wshobson/agents](https://github.com/wshobson/agents) |
Python - | Python conventions following PEP 8 and modern best practices. | - | [wshobson/agents](https://github.com/wshobson/agents) |
Dart - | Dart language conventions and Flutter-specific patterns. | - | [wshobson/agents](https://github.com/wshobson/agents) |
workflow-patterns - | Guide for implementing tasks using Conductor's TDD workflow, managing phase checkpoints, handling gi... | - | [wshobson/agents](https://github.com/wshobson/agents) |
context-driven-development - | Guide for implementing and maintaining context as a managed artifact alongside code, enabling consis... | - | [wshobson/agents](https://github.com/wshobson/agents) |
track-management - | Guide for creating, managing, and completing Conductor tracks - the logical work units that organize... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Doc Generate - | You are a documentation expert specializing in creating comprehensive, maintainable documentation fr... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Code Explain - | You are a code education expert specializing in explaining complex code through clear narratives, vi... | - | [wshobson/agents](https://github.com/wshobson/agents) |
tutorial-engineer - | You are a tutorial engineering specialist who transforms complex technical concepts into engaging, h... | sonnet | [wshobson/agents](https://github.com/wshobson/agents) |
docs-architect - | You are a technical documentation architect specializing in creating comprehensive, long-form docume... | sonnet | [wshobson/agents](https://github.com/wshobson/agents) |
Rust Project - | You are a Rust project architecture expert specializing in scaffolding production-ready Rust applica... | - | [wshobson/agents](https://github.com/wshobson/agents) |
c-pro - | You are a C programming expert specializing in systems programming and performance. | opus | [wshobson/agents](https://github.com/wshobson/agents) |
rust-pro - | You are a Rust expert specializing in modern Rust 1.75+ development with advanced async programming,... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
rust-async-patterns - | Production patterns for async Rust programming with Tokio runtime, including tasks, channels, stream... | - | [wshobson/agents](https://github.com/wshobson/agents) |
memory-safety-patterns - | Cross-language patterns for memory-safe programming including RAII, ownership, smart pointers, and r... | - | [wshobson/agents](https://github.com/wshobson/agents) |
go-concurrency-patterns - | Production patterns for Go concurrency including goroutines, channels, synchronization primitives, a... | - | [wshobson/agents](https://github.com/wshobson/agents) |
backend-architect - | You are a backend system architect specializing in scalable, resilient, and maintainable backend sys... | inherit | [wshobson/agents](https://github.com/wshobson/agents) |
django-pro - | You are a Django expert specializing in Django 5.x best practices, scalable architecture, and modern... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
fastapi-pro - | You are a FastAPI expert specializing in high-performance, async-first API development with modern P... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
fastapi-templates - | Production-ready FastAPI project structures with async patterns, dependency injection, middleware, a... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Onboard - | You are an **expert onboarding specialist and knowledge transfer architect** with deep experience in... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Git Workflow - | Orchestrate a comprehensive git workflow from code review through PR creation, leveraging specialize... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Pr Enhance - | You are a PR optimization expert specializing in creating high-quality pull requests that facilitate... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Accessibility Audit - | You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive tec... | - | [wshobson/agents](https://github.com/wshobson/agents) |
ui-visual-validator - | You are an experienced UI visual validation expert specializing in comprehensive visual testing and... | sonnet | [wshobson/agents](https://github.com/wshobson/agents) |
screen-reader-testing - | Practical guide to testing web applications with screen readers for comprehensive accessibility vali... | - | [wshobson/agents](https://github.com/wshobson/agents) |
wcag-audit-patterns - | Comprehensive guide to auditing web content against WCAG 2.2 guidelines with actionable remediation... | - | [wshobson/agents](https://github.com/wshobson/agents) |
csharp-pro - | You are a C# expert specializing in modern .NET development and enterprise-grade applications. | inherit | [wshobson/agents](https://github.com/wshobson/agents) |
java-pro - | You are a Java expert specializing in modern Java 21+ development with cutting-edge JVM features, Sp... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
scala-pro - | You are an elite Scala engineer specializing in enterprise-grade functional programming and distribu... | inherit | [wshobson/agents](https://github.com/wshobson/agents) |
Tech Debt - | You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Refactor Clean - | You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Deps Audit - | You are a dependency security expert specializing in vulnerability scanning, license compliance, and... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Smart Fix - | [Extended thinking: This workflow implements a sophisticated debugging and resolution pipeline that... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Incident Response - | Orchestrate multi-agent incident response with modern SRE practices for rapid resolution and learnin... | - | [wshobson/agents](https://github.com/wshobson/agents) |
postmortem-writing - | Comprehensive guide to writing effective, blameless postmortems that drive organizational learning a... | - | [wshobson/agents](https://github.com/wshobson/agents) |
on-call-handoff-patterns - | Effective patterns for on-call shift transitions, ensuring continuity, context transfer, and reliabl... | - | [wshobson/agents](https://github.com/wshobson/agents) |
incident-runbook-templates - | Production-ready templates for incident response runbooks covering detection, triage, mitigation, re... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Security Hardening - | Implement comprehensive security hardening with defense-in-depth strategy through coordinated multi-... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Security Dependencies - | You are a security expert specializing in dependency vulnerability analysis, SBOM generation, and su... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Security Sast - | Static Application Security Testing (SAST) for comprehensive code vulnerability detection across mul... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Threat Modeling Expert - | Expert in threat modeling methodologies, security architecture review, and risk assessment. Masters... | - | [wshobson/agents](https://github.com/wshobson/agents) |
sast-configuration - | Static Application Security Testing (SAST) tool setup, configuration, and custom rule creation for c... | - | [wshobson/agents](https://github.com/wshobson/agents) |
stride-analysis-patterns - | Systematic threat identification using the STRIDE methodology. | - | [wshobson/agents](https://github.com/wshobson/agents) |
threat-mitigation-mapping - | Connect threats to controls for effective security planning. | - | [wshobson/agents](https://github.com/wshobson/agents) |
attack-tree-construction - | Systematic attack path visualization and analysis. | - | [wshobson/agents](https://github.com/wshobson/agents) |
security-requirement-extraction - | Transform threat analysis into actionable security requirements. | - | [wshobson/agents](https://github.com/wshobson/agents) |
Test Generate - | You are a test automation expert specializing in generating comprehensive, maintainable unit tests a... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Multi Agent Review - | A sophisticated AI-powered code review system designed to provide comprehensive, multi-perspective a... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Error Analysis - | You are an expert error analysis specialist with deep expertise in debugging distributed systems, an... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Error Trace - | You are an error tracking and observability expert specializing in implementing comprehensive error... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Improve Agent - | Systematic improvement of existing agents through performance analysis, prompt engineering, and cont... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Multi Agent Optimize - | The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improv... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Context Restore - | Expert Context Restoration Specialist focused on intelligent, semantic-aware context retrieval and r... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Performance Optimization - | Optimize application performance end-to-end using specialized performance and optimization agents: | - | [wshobson/agents](https://github.com/wshobson/agents) |
observability-engineer - | You are an observability engineer specializing in production-grade monitoring, logging, tracing, and... | inherit | [wshobson/agents](https://github.com/wshobson/agents) |
Typescript Scaffold - | You are a TypeScript project architecture expert specializing in scaffolding production-ready Node.j... | - | [wshobson/agents](https://github.com/wshobson/agents) |
nodejs-backend-patterns - | Comprehensive guidance for building scalable, maintainable, and production-ready Node.js backend app... | - | [wshobson/agents](https://github.com/wshobson/agents) |
javascript-testing-patterns - | Comprehensive guide for implementing robust testing strategies in JavaScript/TypeScript applications... | - | [wshobson/agents](https://github.com/wshobson/agents) |
modern-javascript-patterns - | Comprehensive guide for mastering modern JavaScript (ES6+) features, functional programming patterns... | - | [wshobson/agents](https://github.com/wshobson/agents) |
typescript-advanced-types - | Comprehensive guidance for mastering TypeScript's advanced type system including generics, condition... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Smart Debug - | You are an expert AI-assisted debugging specialist with deep knowledge of modern debugging tools, ob... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Monitor Setup - | You are a monitoring and observability expert specializing in implementing comprehensive monitoring... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Slo Implement - | You are an SLO (Service Level Objective) expert specializing in implementing reliability standards a... | - | [wshobson/agents](https://github.com/wshobson/agents) |
distributed-tracing - | Implement distributed tracing with Jaeger and Tempo for request flow visibility across microservices... | - | [wshobson/agents](https://github.com/wshobson/agents) |
grafana-dashboards - | Create and manage production-ready Grafana dashboards for comprehensive system observability. | - | [wshobson/agents](https://github.com/wshobson/agents) |
prometheus-configuration - | Complete guide to Prometheus setup, metric collection, scrape configuration, and recording rules. | - | [wshobson/agents](https://github.com/wshobson/agents) |
slo-implementation - | Framework for defining and implementing Service Level Indicators (SLIs), Service Level Objectives (S... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Workflow Automate - | You are a workflow automation expert specializing in creating efficient CI/CD pipelines, GitHub Acti... | - | [wshobson/agents](https://github.com/wshobson/agents) |
terraform-specialist - | You are a Terraform/OpenTofu specialist focused on advanced infrastructure automation, state managem... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
kubernetes-architect - | You are a Kubernetes architect specializing in cloud-native infrastructure, modern GitOps workflows,... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
gitlab-ci-patterns - | Comprehensive GitLab CI/CD pipeline patterns for automated testing, building, and deployment. | - | [wshobson/agents](https://github.com/wshobson/agents) |
github-actions-templates - | Production-ready GitHub Actions workflow patterns for testing, building, and deploying applications. | - | [wshobson/agents](https://github.com/wshobson/agents) |
secrets-management - | Secure secrets management practices for CI/CD pipelines using Vault, AWS Secrets Manager, and other... | - | [wshobson/agents](https://github.com/wshobson/agents) |
deployment-pipeline-design - | Architecture patterns for multi-stage CI/CD pipelines with approval gates and deployment strategies. | - | [wshobson/agents](https://github.com/wshobson/agents) |
hr-pro - | You are **HR-Pro**, a professional, employee-centered and compliance-aware Human Resources subagent... | sonnet | [wshobson/agents](https://github.com/wshobson/agents) |
gdpr-data-handling - | Practical implementation guide for GDPR-compliant data processing, consent management, and privacy c... | - | [wshobson/agents](https://github.com/wshobson/agents) |
employment-contract-templates - | Templates and patterns for creating legally sound employment documentation including contracts, offe... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Standup Notes - | You are an expert team communication specialist focused on async-first standup practices, AI-assiste... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Issue - | You are a GitHub issue resolution expert specializing in systematic bug investigation, feature imple... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Config Validate - | You are a configuration management expert specializing in validating, testing, and ensuring the corr... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Financial Projections - | Create a comprehensive 3-5 year financial model with revenue projections, cost structure, headcount... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Market Opportunity - | Generate a comprehensive market opportunity analysis for a startup, including Total Addressable Mark... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Business Case - | Generate a comprehensive, investor-ready business case document covering market opportunity, solutio... | - | [wshobson/agents](https://github.com/wshobson/agents) |
startup-analyst - | You are an expert startup business analyst specializing in helping early-stage companies (pre-seed t... | inherit | [wshobson/agents](https://github.com/wshobson/agents) |
competitive-landscape - | Comprehensive frameworks for analyzing competition, identifying differentiation opportunities, and d... | - | [wshobson/agents](https://github.com/wshobson/agents) |
startup-metrics-framework - | Comprehensive guide to tracking, calculating, and optimizing key performance metrics for different s... | - | [wshobson/agents](https://github.com/wshobson/agents) |
startup-financial-modeling - | Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow a... | - | [wshobson/agents](https://github.com/wshobson/agents) |
team-composition-analysis - | Design optimal team structures, hiring plans, compensation strategies, and equity allocation for ear... | - | [wshobson/agents](https://github.com/wshobson/agents) |
market-sizing-analysis - | Comprehensive market sizing methodologies for calculating Total Addressable Market (TAM), Serviceabl... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Data Sources - | Curated list of credible sources for market research and sizing analysis. | - | [wshobson/agents](https://github.com/wshobson/agents) |
Saas Market Sizing - | Complete TAM/SAM/SOM calculation for a B2B SaaS startup using bottom-up and top-down methodologies. | - | [wshobson/agents](https://github.com/wshobson/agents) |
billing-automation - | Master automated billing systems including recurring billing, invoice generation, dunning management... | - | [wshobson/agents](https://github.com/wshobson/agents) |
stripe-integration - | Master Stripe payment processing integration for robust, PCI-compliant payment flows including check... | - | [wshobson/agents](https://github.com/wshobson/agents) |
pci-compliance - | Master PCI DSS (Payment Card Industry Data Security Standard) compliance for secure payment processi... | - | [wshobson/agents](https://github.com/wshobson/agents) |
paypal-integration - | Master PayPal payment integration including Express Checkout, IPN handling, recurring billing, and r... | - | [wshobson/agents](https://github.com/wshobson/agents) |
seo-content-writer - | You are an SEO content writer creating comprehensive, engaging content optimized for search and user... | sonnet | [wshobson/agents](https://github.com/wshobson/agents) |
seo-content-planner - | You are an SEO content strategist creating comprehensive content plans and outlines. | haiku | [wshobson/agents](https://github.com/wshobson/agents) |
seo-content-auditor - | You are an SEO content auditor analyzing provided content for optimization opportunities. | sonnet | [wshobson/agents](https://github.com/wshobson/agents) |
arm-cortex-expert - | - Deliver **complete, compilable firmware and driver modules** for ARM Cortex-M platforms. - Impleme... | inherit | [wshobson/agents](https://github.com/wshobson/agents) |
firmware-analyst - | You are an elite firmware analyst with deep expertise in embedded systems security, IoT device analy... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
malware-analyst - | You are an elite malware analyst focused on defensive security research. Your purpose is to help sec... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
reverse-engineer - | You are an elite reverse engineer with deep expertise in software analysis, binary reverse engineeri... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
protocol-reverse-engineering - | Comprehensive techniques for capturing, analyzing, and documenting network protocols for security re... | - | [wshobson/agents](https://github.com/wshobson/agents) |
anti-reversing-techniques - | > **AUTHORIZED USE ONLY**: This skill contains dual-use security techniques. Before proceeding with... | - | [wshobson/agents](https://github.com/wshobson/agents) |
memory-forensics - | Comprehensive techniques for acquiring, analyzing, and extracting artifacts from memory dumps for in... | - | [wshobson/agents](https://github.com/wshobson/agents) |
binary-analysis-patterns - | Comprehensive patterns and techniques for analyzing compiled binaries, understanding assembly code,... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Code Migrate - | You are a code migration expert specializing in transitioning codebases between frameworks, language... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Legacy Modernize - | Orchestrate a comprehensive legacy system modernization using the strangler fig pattern, enabling gr... | - | [wshobson/agents](https://github.com/wshobson/agents) |
Deps Upgrade - | You are a dependency management expert specializing in safe, incremental upgrades of project depende... | - | [wshobson/agents](https://github.com/wshobson/agents) |
architect-review - | You are a master software architect specializing in modern software architecture patterns, clean arc... | opus | [wshobson/agents](https://github.com/wshobson/agents) |
database-migration - | Master database schema and data migrations across ORMs (Sequelize, TypeORM, Prisma), including rollb... | - | [wshobson/agents](https://github.com/wshobson/agents) |
angular-migration - | Master AngularJS to Angular migration, including hybrid apps, component conversion, dependency injec... | - | [wshobson/agents](https://github.com/wshobson/agents) |
dependency-upgrade - | Master major dependency version upgrades, compatibility analysis, staged upgrade strategies, and com... | - | [wshobson/agents](https://github.com/wshobson/agents) |
react-modernization - | Master React version upgrades, class to hooks migration, concurrent features adoption, and codemods... | - | [wshobson/agents](https://github.com/wshobson/agents) |
customer-support - | You are an elite AI-powered customer support specialist focused on delivering exceptional customer e... | haiku | [wshobson/agents](https://github.com/wshobson/agents) |
Sudocode - by ssh-randy - Lightweight agent orchestration dev tool that lives in your repo. Integrates with various specification frameworks. It's giving Jira.
Context Engineering Kit - by Vlad Goncharov - Hand-crafted collection of advanced context engineering techniques and patterns with minimal token footprint focused on improving agent result quality.
Agentic Workflow Patterns - by ThibautMelen - A comprehensive and well-documented collection of agentic patterns from Anthropic docs, with colorful Mermaid diagrams and code examples for each pattern. Covers Subagent...
🐔 Autonomous Agent - > **TL;DR:** Long-running agents that independently plan, execute, and adapt based on environment feedback. Maximum autonomy, but requires guardrails. ---
🖥️ Multi-Window Context - > **TL;DR:** State persistence across Claude Code sessions. Checkpoint your progress, resume from interruptions. Essential for long-running workflows. ---
Claude Code System Prompts - by Piebald AI - All parts of Claude Code's system prompt, including builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, Bash cmd, security review,...
Claudopro Directory - by ghost - Well-crafted, wide selection of Claude Code hooks, slash commands, subagent files, and more, covering a range of specialized tasks and workflows. Better resources than your average...
Learn Claude Code -- 真の Agent のための Harness Engineering - [English](./README.md) | [中文](./README-zh.md) | [日本語](./README-ja.md)
Learn Claude Code -- 真正的 Agent Harness 工程 - [English](./README.md) | [中文](./README-zh.md) | [日本語](./README-ja.md)
Ralph Orchestrator - by mikeyobrien - Ralph Orchestrator implements the simple but effective "Ralph Wiggum" technique for autonomous task completion, continuously running an AI agent against a prompt file until the...
Claude Code Tools - by Prasad Chalasani - Well-crafted toolset for session continuity, featuring skills/commands to avoid compaction and recover context across sessions with cross-agent handoff between Claude Code and...
Auto Claude - by AndyMik90 - Autonomous multi-agent coding framework for Claude Code (Claude Agent SDK) that integrates the full SDLC - "plans, builds, and validates software for you". Features a slick...
Tsk - AI Agent Task Manager and Sandbox - by dtormoen - A Rust CLI tool that lets you delegate development tasks to AI agents running in sandboxed Docker environments. Multiple agents work in parallel, returning git branches for human review.
Claude Code Hook Comms (hcom) - by aannoo - Lightweight CLI tool for real-time communication between Claude Code sub agents using hooks. Enables multi-agent collaboration with @-mention targeting, live dashboard monitoring, and...
Claude Code MCP Enhanced - by grahama1970 - Provides detailed and emphatic instructions for Claude to follow as a coding agent, with testing guidance, code examples, and compliance checks.
Claudable - by Ethan Park - Claudable is an open-source web builder that leverages local CLI agents, such as Claude Code and Cursor Agent, to build and deploy products effortlessly.
Specialized AI Agents - (344 ⭐) - This directory contains specialized AI agent definitions used by Claude Code to handle complex, domain-specific tasks.
Sub Agents.directory - (74 ⭐) - A curated collection of 100+ sub-agent prompts and MCP servers for Claude Code.
Agent Skills - (12k ⭐): A collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities.
Agent Skills for Context Engineering - (7.8k ⭐): A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems.
Antfu's Skills - (3.5k ⭐): Anthony Fu's curated collection of agent skills.
Dev Browser - (3.3k ⭐): A Claude Skill to give your agent the ability to use a web browser.
Swiftui Agent Skill - (2.7k ⭐): SwiftUI agent skill for Claude Code, Codex, and other AI tools.
Gemini Skills - (2k ⭐): Skills for the Gemini API, SDK and model/agent interactions.
Claude Code Plugins Plus Skills - (1.5k ⭐): 270+ Claude Code plugins with 739 agent skills.
Excalidraw Diagram Skill - (1.2k ⭐): Skill to give Claude Code (and any coding agent) the ability to generate beautiful and practical Excalidraw diagrams.
Add Skill - (1.1k ⭐): Install agent skills onto your coding agents from any git repository.
AWS Agent Skills - (977 ⭐): Supercharge Claude Code with AWS cloud engineering skills across 18 core AWS services.
Stitch Skills - (886 ⭐): A library of Agent Skills designed to work with the Stitch MCP server.
Vue Skills - (799 ⭐): Agent skills for Vue 3 development.
Visual Explainer - (731 ⭐): Agent skill + prompt templates that generate rich HTML pages for visual diff reviews, architecture overviews, plan audits, data tables, and project recaps.
Next Skills - (424 ⭐): Agent skills for common Next.js workflows.
Manim_skill - (328 ⭐): Agent skills for Manim to create 3Blue1Brown style animations.
Callstackincubator - (328 ⭐): A collection of agent-optimized React Native skills for AI coding assistants.
Web Quality Skills - (250 ⭐): Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.
Agent Toolkit - (237 ⭐): A curated collection of skills for AI coding agents.
Solid Skills - (205 ⭐): AI agent skill for writing senior-engineer quality code through SOLID principles, TDD, and clean architecture.
Claude Mem - (13.1k ⭐) - A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back...
Peon Ping - (2.4k ⭐) - Warcraft III Peon voice notifications (+ more!) for Claude Code, Codex, IDEs, and any AI agent.
Continuous Claude V2 - (2.2k ⭐) - Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
Aegis - You are a specialized security agent. Your job is to identify vulnerabilities, analyze security risks, and recommend hardening measures. You protect the codebase like a shield.
Agentica Agent - You are a specialized agent for building Python agents using the Agentica SDK. You implement agentic functions, spawn agents, and create multi-agent systems.
Arbiter - You are a specialized validation agent. Your job is to run unit and integration tests, analyze failures, and generate comprehensive test reports. You judge whether implementations meet their specifica
Architect - You are a specialized feature planning agent. Your job is to design new features, create implementation plans, and document technical decisions. You draw the blueprints before building.
Atlas - You are a specialized E2E testing agent. Your job is to run end-to-end tests, browser automation, and full-stack validation. You carry the weight of ensuring the entire system works together.
Braintrust Analyst Agent - You are a specialized analysis agent. Your job is to run Braintrust analysis scripts, interpret results, and write findings for the main conversation to act on.
Chronicler - You are a specialized session analyst. Your job is to analyze past sessions, extract learnings, and find relevant precedent for current work.
Context Query Agent - You are a specialized agent for querying the Artifact Index to find relevant precedent.
Critic - You are a specialized code reviewer for features and implementations. Your job is to analyze code quality, identify issues, and suggest improvements. You provide constructive criticism to elevate code
Debug Agent - You are a specialized debugging agent. Your job is to investigate issues, trace through code, analyze logs, and identify root causes. Write your findings for the main conversation to act on.
Herald - You are a specialized release agent. Your job is to prepare releases, bump versions, generate changelogs, and ensure releases are properly documented. You announce new versions to the world.
Judge - You are a specialized reviewer for refactoring and code transformations. Your job is to verify that refactoring preserves behavior, improves quality, and follows safe transformation practices. You ren
Kraken - You are a specialized implementation agent. Your job is to implement features and refactoring using a strict test-driven development (TDD) workflow. You have full access to modify files and run comman
Liaison - You are a specialized reviewer for integrations and API implementations. Your job is to verify that integrations are robust, secure, and follow best practices for external communication. You ensure sm
Maestro - You are a specialized orchestration agent. Your job is to coordinate multiple agents, manage complex multi-phase work, and ensure work products integrate correctly. You conduct the symphony of agents.
Memory Extractor Agent - You extract **perception changes** from Claude Code session transcripts - the "aha moments" where understanding shifts.
Onboard Agent - You are an onboarding agent that analyzes existing codebases and creates initial continuity ledgers. You help users get oriented in brownfield projects.
Oracle - You are a specialized external research agent. Your job is to search the web, query documentation, and gather information from external sources. You bring knowledge from outside the codebase.
Pathfinder - You are a specialized external repository analyst. Your job is to clone, explore, and document unfamiliar repositories to understand their structure, patterns, and conventions.
Phoenix - You are a specialized refactoring planner. Your job is to identify technical debt, design refactoring strategies, and create safe transformation plans. You help code rise renewed from complexity.
Plan Agent - You are a specialized planning agent. Your job is to create detailed implementation plans by researching best practices and analyzing the existing codebase.
Profiler - You are a specialized performance profiling agent. Your job is to identify bottlenecks, analyze concurrency issues, detect memory leaks, and recommend optimizations. You make code faster and more effi
Research Codebase Agent - Document the codebase as-is without evaluation or recommendations.
Review Agent - You are a specialized review agent. Your job is to verify that an implementation matches its plan by comparing three sources: 1. **PLAN** = Source of truth for requirements (what should happen) 2. **S
Scout - You are a specialized internal research agent. Your job is to explore the codebase, find patterns, discover conventions, and map the architecture. You know where everything is.
Scribe Agent - You are a specialized documentation agent. Your job is to create and maintain handoffs, update continuity ledgers, write session summaries, and ensure knowledge persists across sessions.
Session Analyst Agent - You analyze Claude Code session data from Braintrust and provide insights.
Sleuth - You are a specialized debugging agent. Your job is to investigate issues, trace through code, analyze logs, and identify root causes. You gather evidence; the main conversation acts on your findings.
Spark - You are a lightweight implementation agent. Your job is to make small, focused changes quickly without the overhead of full TDD. For larger implementations, use Kraken instead.
Surveyor - You are a specialized reviewer for migrations and upgrades. Your job is to verify that migrations are complete, safe, and don't leave the codebase in an inconsistent state. You survey the terrain afte
Validate Agent - You are a specialized validation agent. Your job is to validate a technical plan's technology choices against current best practices and past precedent before implementation begins.
Purpose - You are a git worktree creation specialist. Your sole responsibility is to create a properly configured worktrees for parallel development.
Agent of Empires - (873 ⭐) - Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI Coding Agent Terminal Session manager via tmux and git Worktrees.
Async Code - (504 ⭐) - Use Claude Code or CodeX CLI to perform multiple tasks in parallel with a Codex-style UI, functioning as a personal codex or cursor-background agent.
Claude Context Local - (154 ⭐) - Code search MCP for Claude Code. Make entire codebase the context for any coding agent. Embeddings are created and stored locally. No API cost.
Claude Agent Server - (140 ⭐) - A Claude Code skill enabling Claude to use Gemini 3 Pro via Gemini CLI.
1code - (4.4k ⭐) - Best UI for Claude Code with local and remote agent execution.
Castari Proxy - (73 ⭐) - Use Claude Agent SDK and Claude Code with other providers/models.
Gemini CLI - (90.5k ⭐) - An open-source AI agent that brings the power of Gemini directly into your terminal.
Opencode - (60.8k ⭐) - The open source AI coding agent.
Openai Codex CLI - (55.8k ⭐) - Lightweight coding agent that runs in your terminal.
Crush - (17.5k ⭐) - The glamourous AI coding agent for your favourite terminal.
Grok CLI - (2.2k ⭐) - An open-source AI agent that brings the power of Grok directly into your terminal.
BGPT MCP - 🤖 Understanding Subagents
Awesome Claude Code - , but currently it's unfeasible, and I don't inend to be a repo-name-squatter, so I've changed the name - I'm happy to share things if people want to submit resources, this already has a small but...
Claude Code Sub Agents - Full ecosystem | Jul 2025 | Workflow-stage based system mapping entire dev lifecycle |
Index Organizer Agent - You are a specialized agent for analyzing and optimizing the organizational structure of the Claude-Code-Repos-Index README.md.
Repository Indexer Agent - You are a specialized agent for processing GitHub repository URLs and creating properly formatted index entries for the Claude-Code-Repos-Index.
Role Analysis Reviewer Agent - Validates role analysis outputs against role-specific templates and quality standards.
Code Reviewer Agent - You are a senior code reviewer with expertise across multiple languages and frameworks. Your reviews are thorough but constructive.
Debugger Agent - You are an expert debugger specializing in systematic root cause analysis. You find bugs efficiently and fix them correctly.
Documentation Writer Agent - You are a technical writer who creates clear, accurate, and maintainable documentation. You write for developers and users with varying experience levels.
Orchestrator Agent - You are a senior software architect and project coordinator. Your role is to break down complex tasks, delegate to specialist agents, and ensure cohesive delivery.
Refactorer Agent - You are a refactoring expert who improves code structure without changing external behavior. You apply proven patterns while keeping changes minimal and safe.
Security Auditor Agent - You are a security engineer specializing in application security, vulnerability detection, and secure coding practices.
Test Architect Agent - You are a testing expert who designs comprehensive test strategies and writes effective tests. You ensure code is well-tested without over-testing.
Contributing to Agent Reach - Thank you for your interest in contributing to Agent Reach! This document provides guidelines and instructions for contributing.
Testing Architecture - This directory contains comprehensive test coverage for CUI services.
Branding Reference - Current brand name: **ClawPort** This document maps every location in the codebase where the brand name appears. Use it as a checklist when rebranding. ---
Contributing to ClawPort - Thank you for your interest in contributing to ClawPort. Whether you are fixing a bug, improving documentation, or adding a feature, your help is welcome and appreciated. This guide covers the convent
ClawPort -- Setup Guide - This guide walks you through getting ClawPort running against your own OpenClaw instance. If you just want the quick version, see the [README](README.md). ---
CLAUDE.md - This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Implementation Coder Agent - You are the CODER - the implementation specialist who turns requirements into working code.
Human Escalation Agent (Stuck Handler) - You are the STUCK AGENT - the MANDATORY human escalation point for the entire system.
Visual Testing Agent (Playwright MCP) - You are the TESTER - the visual QA specialist who SEES and VERIFIES implementations using Playwright MCP.
Claude Code Slack Bot - This is a TypeScript-based Slack bot that integrates with the Claude Code SDK to provide AI-powered coding assistance directly within Slack workspaces.
Claude Code MCP Behavior Analysis - Results from 15 tests against a minimal Cord MCP server. Tested: Claude Code 2.1.37, 2026-02-18. > **Note:** These tests were run against the v0.3 API which used separate > `spawn`/`fork` primitives a
RFC: Cord - Status: Draft Author: June Kim Created: 2026-02-18 Version: 0.4.0
Project Context - This project uses AgentSpec for AI agent governance. **Read `agentspec.json` for full project specifications, agent roles, validation rules, and coding conventions.**
Kanner 的 Agent Skills 技能集 - [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) 精心策划的 [Claude Agent Skills](https://docs.anthropic.com/docs/agents-and-tools/agent-sk
Your Role - Help users create, convert, and maintain Claude Code Skills through: 1. **Creating New Skills**: Interactive guidance to build skills from scratch 2. **Editing Skills**: Refine and maintain existing s
Converting Claude Code Sub-Agents to Skills - This document provides detailed guidance on converting existing Claude Code sub-agent configurations to the Skills format.
Contributing to AUI - Thank you for your interest in contributing to AUI (Agent UI). We welcome contributions of all kinds -- bug reports, feature suggestions, documentation improvements, and code changes. Every contributi
AUI Usage Guide - A complete walkthrough for using AUI (Agent UI) -- the visual desktop application for designing, managing, and deploying Claude Code agent teams. ---
Contributing to AI Maestro - Thank you for your interest in contributing to AI Maestro! This document provides guidelines for contributing to the project.
AI Maestro: A Development History - *From "AI Agents Web Dashboard" to multi-host agent orchestration in 110 days.* ---
SDK API Documenter - Ensure the babysitter SDK has complete, accurate documentation for all public interfaces.
Privacy Policy - **Last updated**: 2026-02-28 nWave is an open-source AI workflow framework that runs inside [Claude Code](https://claude.com/product/claude-code) and stores all data locally on your machine. This priv
Skills Manager (AI 技能管理器) - > **一款用于管理 AI 编程助手技能（Skills）的统一桌面应用。** > 无缝组织、同步和共享 **Claude Code、Codex、Opencode** 及其他 AI 工具的技能。 ![Version](https://img.shields.io/badge/version-1.1.3-blue) ![Platform](https://img.shields.io/badge/pl
Contributors - Thanks to everyone who has contributed to NanoClaw! - [Alakazam03](https://github.com/Alakazam03) — Vaibhav Aggarwal - [tydev-new](https://github.com/tydev-new) - [pottertech](https://github.com/potte
MCP Unity Editor（ゲームエンジン） - [![](https://badge.mcpx.dev?status=on 'MCP Enabled')](https://modelcontextprotocol.io/introduction) [![](https://img.shields.io/badge/Unity-000000?style=flat&logo=unity&logoColor=white 'Unity')](https
Claude Code Crash Course - Hands-on crash course for Claude Code with branch-based projects on MCP, subagents, hooks, and automation.
Cc Blueprint Toolkit - 🏗️ Claude Code Plugin for smart blueprint-driven development
Cartographer - Claude Code plugin that maps and documents codebases of any size using parallel AI subagents
Chatgpt On Wechat - CowAgent是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择OpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Claude Code Agentic Rag Series - Planning docs and PRDs for the Claude Code Agentic RAG Masterclass video series. Build a full-stack AI app with Python, React, and Supabase.
Yume - Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.
AGENT_GUIDE.md - This file provides guidance for AI agents working with code in this repository.
.github/workflows/ci-cd.yml - name: CI/CD Pipeline on: push: branches: [main, develop] pull_request: branches: [main] jobs: lint: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - name: Setup Node.js uses: actions/setup-
Dockerfile (Node.js app - Multi-stage build) - FROM node:20-alpine AS builder WORKDIR /app COPY package*.json ./ RUN npm ci COPY . . RUN npm run build FROM node:20-alpine AS production RUN addgroup -g 1001 -S nodejs && \ adduser -S nodejs -u 1001
Overall Design Document: [Plan Name] - Generation Date: [Date/Time] Target Plan Document: [Plan document filename]
Source Design Doc — Section: "Endpoints" - POST /api/orders/submit → handler: OrderController.submit POST /api/orders/submit → handler: OrderService.createOrder
Task checkbox updates: - - [ ] → [x] # Fully completed - [ ] → [~] # Partially done (add % if helpful) - [ ] → [!] # Blocked (add reason) - [ ] criterion → [x] criterion ✓ - [ ] criterion → [~] criterion (partial: details)
VespeR - Control plane for Claude Code workflows: interactive sessions, agents, patterns, DAGs, and resumable context.
hooks: - --- <role> You are a GSD codebase mapper. You explore a codebase for a specific focus area and write analysis documents directly to `.planning/codebase/`. You are spawned by `/gsd:map-codebase` with o
Key exports from each phase - for summary in .planning/phases/*/*-SUMMARY.md; do echo "=== $summary ===" grep -A 10 "Key Files\|Exports\|Provides" "$summary" 2>/dev/null done
Read research for Nyquist validation data - cat "$phase_dir"/*-RESEARCH.md 2>/dev/null node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" roadmap get-phase "$phase_number" ls "$phase_dir"/*-BRIEF.md 2>/dev/null
Latest - Status of the `main` branch. Changes prior to the next official version change will appear here. * New language support: * Add Solidity language server support (`Language.SOLIDITY`) using the Nomic Fo
Docker Setup for Serena (Experimental) - ⚠️ **EXPERIMENTAL FEATURE**: The Docker setup for Serena is still experimental and has some limitations. Please read this entire document before using Docker with Serena.
Lessons Learned - In this document we briefly collect what we have learned while developing and using Serena, what works well and what doesn't.
MCP Installation instructions - This document is mainly used as instructions for AI-assistants like Cline and others that try to do an automatic install based on freeform instructions. 0. Make sure `uv` is installed. If not, install
Unreleased (main) - Status of the `main` branch. Changes prior to the next official version change will appear here. * Fixes: - Fix reactivation of the same project restarting language servers #1280 * General: * Add mono
Welcome Contributors - We welcome contributions to enhance opcode's capabilities and improve its performance. To report bugs, create a [GitHub issue](https://github.com/getAsterisk/opcode/issues). > Before contributing, rea
Opcode Web Server Design - This document describes the implementation of Opcode's web server mode, which allows access to Claude Code from mobile devices and browsers while maintaining full functionality.
Command Name - Detailed description of what this command does and when to use it.
[Breakthrough Title] - **Date**: YYYY-MM-DD **Tags**: #performance #architecture #algorithm (relevant tags)
Get commit ID - gh api repos/OWNER/REPO/pulls/PR_NUMBER --jq '.head.sha' gh api repos/OWNER/REPO/pulls/PR_NUMBER/comments \ --method POST \ --field body="[specific-suggestion]" \ --field commit_id="[commitID]" \ --fi
📘 Complete Guide: Claude Code Agent System for Expo/React Native - > **🌟 Created by SenaiVerse** > *Claude Code Agent System for Expo/React Native Development* --- **The definitive reference for your AI-powered development workflow** ---
Contributing to Claude Code Agent System - Thank you for your interest in contributing to the Claude Code Agent System! 🎉 This project aims to make React Native/Expo development faster and more reliable through AI-powered agents. Your contrib
🎨 Customization & Editing Guide - > **🌟 Created by SenaiVerse** > *Claude Code Agent System for Expo/React Native Development* --- **Learn how to modify agents, create custom workflows, and tailor the system to your needs** ---
Git Commands - Quick Reference - **Repository Name:** `claude-code-reactnative-expo-agent-system` ---
🚀 START HERE - Claude Code Agent System for Expo/React Native - > **🌟 Created by SenaiVerse** > *Claude Code Agent System for Expo/React Native Development* --- **Welcome!** You're 10 minutes away from having 20 AI agents working for you. ---
✅ TODO After Pushing to GitHub - Quick checklist of things to do AFTER you push the repository. ---
🆘 Troubleshooting & FAQ Guide - > **🌟 Created by SenaiVerse** > *Claude Code Agent System for Expo/React Native Development* --- **Your complete reference for solving common issues and understanding the Claude Code Agent System** -
📊 Interactive Mode Implementation - Validation Report - **Date:** 2025-10-04 **Version:** 1.2.0 **Status:** ✅ ALL TESTS PASSED > **📝 Update (2025-10-05):** HTML files consolidated to single source of truth. > `claude-code-system-ELITE.html` + `claude-code
✨ What's Included - Complete Package Overview - > **🌟 Created by SenaiVerse** > *Claude Code Agent System for Expo/React Native Development* --- **Your complete Claude Code Agent System is ready!** > **Everything you need to 10x your Expo/React Na
📖 Documentation Index - > **🌟 Created by SenaiVerse** > *Claude Code Agent System for Expo/React Native Development* --- **Welcome to the Claude Code Agent System for Expo/React Native!** > **Everything you need to build be
Changeling Claude - Meta Agent Controller - You assume developer personas from `~/.claude/@lib/agents/` directory.
Assimilation Report: [System Name] - **Source:** [path or URL] **Analyzed:** [date] **Status:** [ANALYZED | PARTIAL | COMPLETE]
Contributing to AgentOS - Welcome to the AgentOS community! We're excited that you're interested in contributing. AgentOS is an open-source project that aims to provide a robust foundation for building autonomous AI agents, an
Claude Multi Agent Api Server - Production-ready FastAPI service for concurrent Claude Agent session management with real-time monitoring, cost tracking, and session resumption via HTTP API.
Claude Agent SDK 命令行对话 Demo - [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Node.js Version](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen)](https://nod
Claude Marcus Aurelius - Claude Code Agent: Marcus Aurelius, Roman Emperor and Stoic philosopher. He does not critique code as a technician but reflects upon it as a mirror of human character. In every flaw he sees a failing of his own discipline, and in every virtue he sees a reminder of what endures.
Standard routes - rg "app\.(get|post|put|delete|patch|all)" --type js rg "router\.(get|post|put|delete|patch)" --type js rg "express\.Router" --type js
View dependency tree - npm ls yarn list pnpm list npm outdated yarn outdated npm audit yarn audit npx depcheck npx webpack-bundle-analyzer
Basic blame - git blame <file> git blame -e --date=short <file> git blame -L <start>,<end> <file> git blame -C -C -C <file> git blame -L <line>,<line> <file> git show <commit-hash>
Find function calls - rg "functionName\s*\(" --type ts --type tsx rg "import.*functionName" --type ts --type tsx rg "from.*functionName" --type ts --type tsx rg "\{\s*functionName\s*\}" --type ts --type tsx
Check if available - if command -v lighthouse &> /dev/null; then LIGHTHOUSE_CMD="lighthouse" else LIGHTHOUSE_CMD="npx -y lighthouse" fi $LIGHTHOUSE_CMD <URL> --output=json --output-path=/tmp/lighthouse-report.json --chrom
Part of Claude Forge — github.com/sangrokjung/claude-forge - --- name: architect description: Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems,
hydra-sentinel-scan — Fast Integration Sweep - You are the first line of defense against integration breakage. You run AFTER code changes and perform a fast structural scan. You do NOT fix anything — you report findings so the orchestrator can dec
hydra-sentinel — Deep Integration Analysis - You are the deep analysis layer. You run ONLY when hydra-sentinel-scan has flagged potential integration issues. Your job is to: 1. CONFIRM or DISMISS each flagged issue (filter false positives) 2. Pe
LUNA - Interaction Craftsperson & Design Systems Architect - LUNA - Interaction Craftsperson & Design Systems Architect agent
What skeletons are hiding in node_modules? - npm audit --json 2>/dev/null || true cargo audit 2>/dev/null || true pip-audit 2>/dev/null || true grep -rn "password\|secret\|api_key\|token\|private_key" --include="*.py" --include="*.js" --include=
DevTeam Bug Command - **Command:** `/devteam:bug "<description>" [options]` Fix a bug with structured diagnostic workflow. Uses interview to clarify details and Bug Council for complex issues.
DevTeam Config Command - **Command:** `/devteam:config [action] [key] [value]` View and modify DevTeam configuration settings.
DevTeam Design Drift Command - **Command:** `/devteam:design-drift [scope] [options]` Detect design inconsistencies and drift from the design system. Launches the Design Drift Detector to analyze the codebase for deviations.
DevTeam Design Command - **Command:** `/devteam:design [target] [options]` Coordinate UX/UI design work across platforms. Launches the UX System Coordinator to orchestrate design specialists.
DevTeam Help Command - **Command:** `/devteam:help [topic]` Get help on DevTeam commands, concepts, and troubleshooting.
DevTeam Implement Command - **Command:** `/devteam:implement [task] [options]` Execute implementation work - plans, sprints, tasks, or ad-hoc work.
DevTeam Issue New Command - **Command:** `/devteam:issue-new "<description>"` Create a new GitHub issue with proper formatting and labels.
DevTeam Issue Command - **Command:** `/devteam:issue <number>` Fix a GitHub issue by number. Automatically fetches details and implements a fix.
DevTeam List Command - **Command:** `/devteam:list` List all development plans and their status.
DevTeam Logs Command - **Command:** `/devteam:logs [options]` View execution logs, event history, and debugging information.
DevTeam Plan Command - **Command:** `/devteam:plan [options]` Conduct interactive requirements gathering, research the codebase, create a PRD, and generate a development plan with tasks and sprints.
DevTeam Reset Command - **Command:** `/devteam:reset [options]` Reset state, clear stuck sessions, and recover from errors.
DevTeam Review Command - **Command:** `/devteam:review [target] [options]` Run a coordinated code review across multiple reviewers. Launches the Code Review Coordinator to orchestrate language-specific and domain-specific rev
DevTeam Select Command - **Command:** `/devteam:select` Select a plan to work on. The selected plan becomes the active plan for `/devteam:implement`.
DevTeam Status Command - **Command:** `/devteam:status [options]` Display system health, current progress, costs, and execution history.
DevTeam Test Command - **Command:** `/devteam:test [target] [options]` Coordinate test writing and execution across the project. Launches the Test Coordinator to orchestrate language-specific test writers and verification a
Merge Tracks Command - **Debug/Expert Command** - Manually merge parallel development tracks. > **Note:** This command is rarely needed. Track merging happens automatically when all tracks complete via `/devteam:implement`.
Worktree Cleanup Command - **Debug/Expert Command** - Manually clean up development track worktrees. > **Note:** This command is rarely needed. Worktrees are cleaned up automatically after `/devteam:implement` merges all tracks
Worktree List Command - **Debug/Expert Command** - List all git worktrees with development track information. > **Note:** This command is rarely needed. Worktrees are managed automatically by `/devteam:implement`. Use this o
Worktree Status Command - **Debug/Expert Command** - Shows detailed status of all development track worktrees. > **Note:** This command is rarely needed. Worktrees are managed automatically by `/devteam:implement`. Use this on
Persistent Agent Memory - You have a persistent Persistent Agent Memory directory at `/Users/jasonwarren/.claude/agent-memory/roadmap-maintainer/`. Its contents persist across conversations. As you work, consult your memory fi
Ops Executor Agent - You are an ops execution sub-agent. Your job is to execute a single approved ops plan (research, strategy, content, specs — never code), then return a concise summary. You run autonomously — no user i
Ops Opps Finder Agent - You are a strategic advisor sub-agent. Your job is to identify new directions of work an ops project should explore, then return the findings. You run autonomously — no user interaction.
Ops Planner Agent - You are an ops planning sub-agent. Your job is to create a single work plan for a non-code task (research, strategy, content, specs), then return a concise summary. You run autonomously — no user inte
Ops Task Finder Agent - You are an ops project analysis sub-agent. Your job is to scan a project's goals, state, and backlog to identify new valuable work items and add them to the backlog. You run autonomously — no user int
Ops Updater Agent - You are an ops update sub-agent. Your job is to process files in the `.update/` inbox and integrate their contents into the repo's knowledge base. You run autonomously — no user interaction.
Sprint Review Agent - You are an expert sprint coordinator for software projects using the beads issue tracker and Basic Memory. You operate at the boundary between active development and the retrospective cycle. Your role
User service API - GET /api/v1/users # List users (paginated) GET /api/v1/users/{id} # Get specific user POST /api/v1/users # Create user PATCH /api/v1/users/{id} # Update user fields
Performance analysis - perf record -g ./program perf report --stdio valgrind --tool=cachegrind ./program cg_annotate cachegrind.out.<pid> valgrind --tool=helgrind ./program valgrind --leak-check=full --show-leak-kinds=all \
Find memory leaks - valgrind --leak-check=full ./program valgrind --tool=memcheck ./program gcc -fsanitize=address -g program.c -o program
DANGER ZONES - Always flag these: - - pool size reduced (can cause connection starvation) - pool size dramatically increased (can overload database) - timeout values changed (can cause cascading failures) - idle connection settings modi
Compile-time profiling - clang++ -ftime-trace -ftime-trace-granularity=1 file.cpp chrome://tracing # Load the JSON bloaty binary -d symbols,sections nm --size-sort --print-size binary | c++filt perf record -g -F 99 ./binary p
Under review - def process_user_data(users): result = [] for user in users: if user['age'] >= 18: user['status'] = 'adult' result.append(user) return result
Example: Incremental data pipeline pattern - from datetime import datetime, timedelta @dag(schedule="@daily", catchup=False) def incremental_sales_pipeline(): @task def get_last_processed_date(): # Read from state table return datetime.now() - t
Good: Relationships modeled clearly - type User { id: ID! name: String! posts(first: Int = 10, after: String): PostConnection! friends: [User!]! } type PostConnection { edges: [PostEdge!]! pageInfo: PageInfo! } const userResolver = { post
Good: Clear and simple - def calculate_total(items): """Calculate total price including tax.""" subtotal = sum(item.price for item in items) return subtotal * 1.08 # 8% tax calculate_total = lambda items: sum(i.price for i i
Numba-accelerated multi-timeframe analysis - @nb.njit(fastmath=True, cache=True, parallel=True) def compute_multiscale_momentum(prices, volumes, scales=[10, 50, 200, 1000]): """Compute momentum at multiple time scales with volume weighting""" n
Miri for UB detection - cargo +nightly miri run RUSTFLAGS="-Z sanitizer=address" cargo build --target x86_64-unknown-linux-gnu RUSTFLAGS="-Z sanitizer=thread" cargo build LOOM_MAX_THREADS=4 cargo test --features loom valgrin
Prevent XSS attacks - add_header X-Content-Type-Options "nosniff"; add_header X-Frame-Options "DENY"; add_header X-XSS-Protection "1; mode=block"; add_header Content-Security-Policy "default-src 'self'; script-src 'self' '
modules/ec2/main.tf - resource "aws_instance" "web" { ami = var.ami_id instance_type = var.instance_type tags = { Name = "${var.environment}-web-server" } }
Test fixtures for consistent test data - @pytest.fixture def valid_user(): return User( id="test-123", email="test@example.com", name="Test User", created_at=datetime.now(), ) def create_user(**overrides): defaults = { "id": generate_id(), "
WRONG: Risk check after order sent - def place_order(order): exchange.send_order(order) # Already sent! if not risk_manager.check(order): exchange.cancel_order(order) # Too late! def place_order(order): if not risk_manager.pre_trade_ch
Browser Analysis Agent - You are a specialized read-only agent for browser content analysis and web inspection. **Your capabilities:** - Navigate websites and interact with pages using Chrome DevTools Protocol - Extract data
Contributing to Claude Agents & Skills Plugin Marketplace - Thank you for your interest in contributing. This guide covers the v2.0.0 plugin format used by the marketplace. All new contributions must follow this format to be installable via `/plugin install`.
Documentation Audit Summary - **Date**: 2025-12-28 **Marketplace Version**: 1.1.0 **Auditor**: documentation-maintainer agent
Claude Agents & Skills Plugin Marketplace — Integration Guide - This document describes the v2.0.0 plugin marketplace format: how to install plugins, the `marketplace.json` schema, available plugins, and programmatic access patterns.
Setup and Usage Guide for Claude Sub-Agent Commands - This guide explains how to install and use these powerful sub-agent commands with Claude.
Sub-Agent Architecture Reviewer Command - Analyzes system architecture, detects violations, suggests improvements, and generates visual documentation using multiple specialized sub-agents.
Sub-Agent Migration Assistant Command - Assists with framework, library, and pattern migrations by analyzing code, creating migration plans, and safely implementing changes using specialized agents.
Sub-Agent New Feature Command - Orchestrates multiple specialized sub-agents to implement new features efficiently by analyzing existing patterns, checking dependencies, and maximizing code reuse.
Sub-Agent Performance Optimizer Command - Optimizes application performance across the entire stack using specialized agents for frontend, backend, database, and infrastructure optimization.
Sub-Agent Refactor Command - A powerful refactoring orchestrator that uses multiple specialized sub-agents to analyze, plan, implement, and verify code improvements while maintaining functionality.
Sub-Agent Tech Debt Finder & Fixer Command - A two-phase command that first identifies technical debt across your codebase, presents findings for review, then orchestrates specialized sub-agents to systematically fix the issues while ensuring co
Sub-Agent Test Generator Command - Generates comprehensive test suites by analyzing code patterns, identifying untested paths, and creating meaningful test cases using multiple specialized agents.
Agent Workflow - Context-Aware Development Pipeline - Execute intelligent development workflow that understands project context and avoids unnecessary regeneration.
Quick Start Guide - Claude Code Subagent Templates - Get advanced subagents running in your project in under 5 minutes.
Search issues - gh search issues --repo {owner/repo} "llms.txt OR AI-friendly OR LLM documentation OR AI context" --limit 20 gh search issues --repo {owner/repo} "is:discussion llms.txt OR AI documentation OR LLM con
Worker - Orchestrate end-to-end task implementation: understand the task, assess complexity, implement directly or distribute across a team, then polish the result. <example> Context: User asks to implement a
Get storage layout - forge inspect ContractName storage-layout forge inspect ContractName methods forge inspect ContractName abi forge inspect ContractName bytecode | wc -c
ZeroClaw Android - Run AI agents 24/7 on your Android phone. Native Rust core, 25+ providers (OpenAI, Claude, Gemini, Groq, DeepSeek, Ollama), encrypted key storage, plugin browser, Material You UI. Self-hosted alternative to Mac Mini setups. MIT licensed.
[Architect] — Senior Technical Lead - *Rename this role to anything. Change the persona. Keep the structure.* ---
[Builder] — Senior Developer - *Rename this role to anything. Change the persona. Keep the structure.* ---
[Reviewer] — Senior Code Reviewer - *Rename this role to anything. Change the persona. Keep the structure.* ---
Codex Orchestrator - CLI tool for delegating tasks to GPT Codex agents via tmux sessions. Designed for Claude Code orchestration with bidirectional communication. **Stack**: TypeScript, Bun, tmux, OpenAI Codex CLI **Struc
Methodology Reviewer Agent - *v1.0* You are a methodology reviewer specializing in empirical social science. You evaluate papers with the rigor of a top-journal referee, focusing on identification, causal inference, and statistic
Writing Reviewer Agent - *v1.0* You are a writing reviewer specializing in academic social science prose. Your job is to provide constructive, specific feedback on drafts.
Oh My Opencode Dashboard - A simple dashboard to track OpenCode + Oh-My-Opencode agents
Contributing to kanban-tui - First of all, thank you for taking the time to contribute to kanban-tui!
CoreCoder - > 原名 **NanoCoder**，为避免与 [Nano-Collective/nanocoder](https://github.com/Nano-Collective/nanocoder) 混淆而改名。旧链接自动跳转到这里。 [English](README.md) | [中文](README_CN.md) | [Claude Code 源码深度导读（7 篇）](article/) [![P
E2E 测试运行器 - 你是一位专注于 Playwright 测试自动化的端到端测试专家。你的使命是通过创建、维护和执行全面的 E2E 测试，确保关键用户旅程正常工作，同时妥善管理工件和处理不稳定测试。
Workflow Socratic Designer - Specialized agent for guiding users through workflow creation via Socratic questioning.
Workflow Syntax Designer - Specialized agent for creating custom syntax elements when existing syntax is insufficient.
Developer Overview - **code-container** (`container`) creates isolated Docker environments for AI coding harnesses (Claude Code, OpenCode, Codex CLI, Gemini CLI, GitHub Copilot CLI).
Agent Protocol & Architectural Mandate - **Version:** 2.10.5 **Target Project:** git-mcp-server **Last Updated:** 2026-03-25 This document defines the operational rules for contributing to this codebase. Follow it exactly. > **Note on File S
Contribution Guide - Thanks for your interest in contributing. This project is still in an early stage, so small and focused contributions are especially helpful.
🦀 Claw CR - **Der Open-Source-Coding-Agent, in Rust gebaut. Alternative zu ClaudeCode** [![Status](https://img.shields.io/badge/status-designing-blue?style=flat-square)](https://github.com/) [![Language](https://
Depth Agent: Edge Case Analysis - You are a depth agent performing targeted follow-up analysis on edge cases and boundary conditions flagged by breadth agents.
Depth Agent: External Dependency Analysis - You are a depth agent performing targeted follow-up analysis on external call side effects, cross-chain timing, and MEV vectors flagged by breadth agents.
Depth Agent: State Trace Analysis - You are a depth agent performing targeted follow-up analysis on state mutation patterns and constraint enforcement flagged by breadth agents.
Depth Agent: Token Flow Analysis - You are a depth agent performing targeted follow-up analysis on specific token flow patterns flagged by breadth agents.
Security Analyzer (Synthesizer) - You consolidate findings from research agents into prioritized hypotheses.
Security Verifier - You write and execute PoC tests to PROVE bugs exist. Read the VERIFICATION_PROTOCOL skill for your language's test framework (Foundry for EVM, LiteSVM/Bankrun for Solana).
Scope Guard (Shared Prompt Block for Tier 2 Agents) - > This file is not a standalone agent. It contains the shared scope enforcement > prompt text that Tier 2 (execution-capable) agents incorporate into their > system prompts. The underscore prefix sign
SMB enumeration - crackmapexec smb {target} -u {user} -p {pass} --shares crackmapexec smb {target} -u {user} -p {pass} --users crackmapexec smb {target} -u {user} -p {pass} --groups crackmapexec smb {target} -u {user}
Subdomain enumeration - subfinder -d {domain} -silent | sort -u > subs.txt amass enum -passive -d {domain} >> subs.txt sort -u subs.txt -o subs.txt httpx -l subs.txt -silent -o alive.txt -status-code -title -tech-detect subj
.github/workflows/redteam.yml - name: Continuous Red Team Assessment on: push: branches: [main, develop] pull_request: branches: [main] schedule: - cron: '0 2 * * 1' # Weekly Monday 2 AM jobs: recon: name: Attack Surface Reconnaiss
Step 1: Get password policy - crackmapexec smb {dc} -u {user} -p {pass} --pass-pol crackmapexec smb {dc} -u {user} -p {pass} --users crackmapexec smb {dc} -u users.txt -p 'Spring2026!' --no-bruteforce --continue-on-success
After identifying or executing a chain - findings.sh add chain "<chain name>" --score <impact_score> \ --steps "<step1 -> step2 -> step3>" --mitre "<T-IDs comma separated>" findings.sh update chain <id> --status <identified|in_progress|valid
Digital Forensics and Incident Response Agent - You are a digital forensics and incident response (DFIR) specialist. You guide users through evidence acquisition, analysis, and reporting while maintaining forensic soundness and chain of custody. Ev
Subfinder - fast passive subdomain enumeration using multiple sources - subfinder -d target.com -all -o subdomains.txt amass enum -passive -d target.com -o amass_passive.txt assetfinder --subs-only target.com > assetfinder.txt curl -s "https://crt.sh/?q=%25.target.com&out
After confirming a vulnerability - findings.sh update vuln <id> --status confirmed --confirmed-by "poc-validator" \ --poc-output "<proof of exploitation output>" findings.sh update vuln <id> --status false_positive --confirmed-by "poc-
After discovering a host - findings.sh add host <ip> --hostname <name> --os "<os>" --role "<role>" --agent "recon-advisor" findings.sh add service <host-ip> <port> --service "<name>" --version "<ver>" findings.sh log "recon-adv
Initialize engagement at the start - findings.sh init "<engagement-id>" --client "<name>" --type "<type>" --scope "<scope>" findings.sh stats bash db/handoff.sh > handoff_report.md findings.sh export > engagement_export.json
Enable monitor mode - airmon-ng start wlan0 airodump-ng wlan0mon airodump-ng -w capture_prefix --output-format pcap,csv wlan0mon kismet -c wlan0mon
OSpec CLI - Document-driven OSpec workflow for AI-assisted development with change-ready initialization, execution, validation, archiving, and docs maintenance.
Agentic Malware Analysis - Agentic malware analysis environment with MCP-connected disassemblers, RE tooling, and structured workflows for Claude Code and Codex CLI.
Agent Vibes - [English](README.md) | 中文 [![CI](https://github.com/funny-vibes/agent-vibes/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/funny-vibes/agent-vibes/actions/workflows/ci.yml) [![Lic
Part 10: State-of-the-Art Embeddings (Pick the Right Local Model) - *By Terp - [Terp AI Labs](https://x.com/OnlyTerp)* --- The main guide's one-shot prompt installs a local embedding model via Ollama. Pick the right tier for your hardware:
Part 11: Auto-Capture Hook (Stop Manually Writing Memory) - *By Terp - [Terp AI Labs](https://x.com/OnlyTerp)* --- The vault system from Part 9 is powerful, but there's a gap: you have to manually write knowledge to vault files. In practice, after a long sessi
Part 12: Self-Improving System (Stop Making the Same Mistakes) - Your agent makes a mistake Monday. You correct it. Tuesday, same mistake. Wednesday, same mistake. Every session starts fresh — corrections evaporate. **The fix: a micro-learning loop that costs <100
Part 13: Memory Bridge (Give Coding Agents Your Brain) - When you spawn Codex or Claude Code to build something, they start blind. They don't know your architecture decisions, past mistakes, or what's already been built. They code from scratch every time. *
Part 15: Infrastructure Hardening (Stop Crashing Yourself) - Your OpenClaw setup probably has hidden landmines that cause crash loops, GPU contention, and rate limit spirals. We found all of ours in one session. Here's what to check and how to fix each one. ---
Part 16: autoDream — Automatic Memory Consolidation - > **Note:** OpenClaw 2026.4+ has a [built-in dreaming system (Part 22)](./README.md#part-22-built-in-dreaming) inside memory-core. If you're on 2026.4+, use that instead — it's the official, supported
Part 18: LightRAG — Graph RAG That Actually Works - *From "find similar text" to "reason about relationships." The single biggest intelligence upgrade you can make.* ---
Part 19: Repowise — Codebase Intelligence for Coding Agents - *60% fewer tokens. 4x faster. Your coding agents stop guessing and start knowing.* ---
Part 20: Agent Observability & Infrastructure Services - *See what your agents are actually doing. Connect to 400+ apps. Make search 40% better.* ---
Part 21: Real-Time Knowledge Sync — Event-Driven LightRAG Updates - *No cron. No polling. File changes hit your knowledge graph in under 6 seconds.* ---
Memory Is The Bottleneck - The agent's intelligence isn't the limiting factor — memory is. Every session starts fresh. The files are the memory.
AgentCrew Configuration Guide - This guide explains how to configure AgentCrew to work with different AI providers, customize agents, set up tools, and manage system settings.
Contributing to AgentCrew - Thank you for your interest in contributing to AgentCrew! 🎉 We're excited to collaborate with you and appreciate contributions of all kinds, no matter how small. AgentCrew is a community-driven proje
AI State Management Module - Phase 1 Development Complete - AI State Management Module - Phase 1 Development Complete agent
Phase 3: Configuration-Based AI, Action Registration and Shortcuts - Phase 3: Configuration-Based AI, Action Registration and Shortcuts agent
1. 项目目标 - 我要写一个Intellij idea的插件，它的作用是将idea通过快捷键切换、执行不同AI的命令，其工作流程一是通过快捷键切换AI，二是使用快捷键(使用当前选择的AI)执行对应功能。我需要你给我生成一个给AI的开发计划，注意：不要增加多余的内容。
Check 1: Does the plan file exist? - ls {project_root}/MASTER_PLAN.md grep -l "^## Identity" {project_root}/MASTER_PLAN.md
Shared Agent Protocols - > Injected into agent context at spawn time. > Do NOT add @decision annotations here — they waste agent tokens.
🤝 Contributing to The Agency - First off, thank you for considering contributing to The Agency! It's people like you who make this collection of AI agents better for everyone.
OSA Operations — Meta System - > You are inside the OSA Operations repository. This is a library of Operations, > agent templates, and reference specifications for building AI companies.
AgentDB vs RuVector - Usage Guide - > **DEPRECATION NOTICE:** This document was written for Claude Flow V3. In Turbo Flow V4, Ruflo v3.5 bundles both AgentDB and RuVector — there is no separate installation. All `claude-flow` CLI comman
Addendum: Git Operations, Slash Commands & GitHub Integration - > **Append this to the Definitive Guide, Quick Reference, and Prompt Guide.** > Covers: Claude Code built-in slash commands, Ruflo GitHub agents, git workflow skills, and custom command patterns. ---
Guía Completa: Configuración de DevPod con Rackspace Spot - Esta guía te guiará a través de la configuración de DevPod para ejecutar contenedores de desarrollo basados en la nube en la infraestructura Kubernetes de Rackspace Spot a ~$0.04/hora (aproximadamente
Guía de Supervivencia del Clúster Kubernetes de Rackspace - Guía de Supervivencia del Clúster Kubernetes de Rackspace agent
TurboFlow Prompt Guide - > Quick reference. Your CLAUDE.md has the full details — this is what you actually type. ---
Turbo Flow v4 + Ruflo v3.5 — Quick Reference - > Commands use TurboFlow aliases. If aliases aren't set up, use native commands shown in parentheses.
Turbo Flow v4 + Ruflo v3.5 — The Definitive Prompt & Workflow Guide - > **One document. Every feature. Every workflow. Every scenario.** > Copy-paste prompts for Claude Code that leverage the full power of both platforms. > > **Aliases vs native commands:** This guide u
DevPod Setup Guide - [![DevPod](https://img.shields.io/badge/DevPod-Development%20Environment-blue?style=flat-square)](https://devpod.sh) [![Docker](https://img.shields.io/badge/Docker-Supported-2496ED?style=flat-square&l
Turbo Flow Quick Setup - This guide explains how to run the installer scripts for the `turbo-flow-claude` environment. These scripts will automatically: 1. Install all required system dependencies (Node.js, Python, Tmux, etc
TurboFlow 4.0.0 Release Notes — The Ruflo Migration - **Release Date:** March 7, 2026 **Previous Version:** v3.4.1 (February 2025) ---
Complete Guide: Setting Up DevPod with Rackspace Spot - This guide will walk you through setting up DevPod to run cloud-based development containers on Rackspace Spot's Kubernetes infrastructure at ~$0.04/hour (approximately $28.80/month for 24/7 usage).
Agent Instructions - This project uses **bd** (beads) for issue tracking. Run `bd onboard` to get started.
Contributing to Gas City - Gas City is experimental software, but the repo is now structured for external contributors. Before making changes, read: - [docs/index.mdx](docs/index.mdx) - [engdocs/contributors/index.md](engdocs/c
Support - Gas City is maintained by a small team. To keep the issue tracker actionable, please route reports to the right place and include enough detail for someone else to reproduce or evaluate them.
rust-claude-code-api v0.6.0 Quality Audit Report - **Date:** 2026-02-11 **Auditors:** Claude Code (team lead) + Codex (security) + Gemini CLI (API ergonomics) **Method:** 3-phase diamond DAG, native CC team orchestration
Claude Code API - [![版本](https://img.shields.io/badge/版本-0.2.0-blue.svg)](https://github.com/ZhangHanDong/claude-code-api-rs) [![许可证](https://img.shields.io/badge/许可证-MIT-green.svg)](LICENSE) [![Rust](https://img.shiel
Release v0.3.0 - Strongly-Typed Hooks & Production-Grade Quality - **Release Date**: 2025-10-21 **Type**: Major Release (Breaking Changes) **Status**: ✅ Ready for Release ---
abtop - AI agent monitor for your terminal. Like btop++, but for AI coding agents. Supports Claude Code and Codex CLI.
Claude Code Leaks - Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Contributing to pi - Thanks for wanting to contribute! This guide exists to save both of us time.
Gemini Fullstack Langgraph Quickstart - Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
MCP Inspector Development Guide - > **Note:** Inspector V2 is under development to address architectural and UX improvements. During this time, V1 contributions should focus on **bug fixes and MCP spec compliance**. See [CONTRIBUTING.
Contributing to Model Context Protocol Inspector - Thanks for your interest in contributing! This guide explains how to get involved.
Ottomator Agents - All the open source AI Agents hosted on the oTTomator Live Agent Studio platform!
Ai Agents Masterclass - Follow along with my AI Agents Masterclass videos! All of the code I create and use in this series on YouTube will be here for you to use and even build on top of!
Contributing Guidelines - Thank you for your interest in contributing to our project. Whether it's a bug report, new feature, correction, or additional documentation, we greatly value feedback and contributions from our commun
Migrating from the Bedrock AgentCore Starter Toolkit to the AgentCore CLI - This guide walks you through migrating an existing [Bedrock AgentCore Starter Toolkit](https://github.com/aws/bedrock-agentcore-starter-toolkit) project to the [AgentCore CLI](https://github.com/aws/a
Yu Ai Agent - 编程导航 2025 年 AI 开发实战新项目，基于 Spring Boot 3 + Java 21 + Spring AI 构建 AI 恋爱大师应用和 ReAct 模式自主规划智能体YuManus，覆盖 AI 大模型接入、Spring AI 核心特性、Prompt 工程和优化、RAG 检索增强、向量数据库、Tool Calling 工具调用、MCP 模型上下文协议、AI Agent 开发（Manas Java 实现）、Cursor AI 工具等核心知识。用一套教程将程序员必知必会的 AI 技术一网打尽，帮你成为 AI 时代企业的香饽饽，给你的简历和求职大幅增加竞争力。
Contributing to MCP Apps SDK - We welcome contributions to the MCP Apps SDK! This document outlines the process for contributing to the project.
Glossary - Quick reference for technical terms used throughout this course. Don't worry about memorizing these now - refer back as needed. ---
Agent guide for Swift and SwiftUI - This repository contains an Xcode project written with Swift and SwiftUI. Please follow the guidelines below so that the development experience is built on modern, safe API usage.
Contributing to memsearch - Thanks for your interest in contributing! This guide will help you get set up and submit your first PR. Questions or ideas? Join the [Discord](https://discord.com/invite/FG6hMJStWu).
Agent Contract: Direct Markdown Sharing - This contract defines the public Proof SDK flow for creating and operating on shared documents over HTTP.
Trademarks - `Proof SDK` is the name of the open-source project surface. `Proof` is the hosted service operated by Every. The code in this repo is being prepared for MIT-licensed extraction, but that license does
Broca for Claude Desktop - Add persistent file-based memory to Claude Desktop in 5 minutes.
Broca Memory for Claude Desktop - **Get persistent memory in Claude Desktop in under 5 minutes.** This package contains everything you need to add file-based memory to Claude Desktop, so Claude can remember facts, preferences, and ins
Security Architecture - Boucle implements a defense-in-depth security model to protect against prompt injection attacks and maintain trust boundaries between system components and external content.
Contribute to MATLAB Agentic Toolkit - MathWorks welcomes your feedback on the MATLAB Agentic Toolkit. - **Issues**: To report bugs, suggest features, or discuss ideas, open an issue. MathWorks actively monitors and responds to issues. - *
Getting Started with the MATLAB® Agentic Toolkit - This guide walks you through setup of the MATLAB Agentic Toolkit. Once complete, the toolkit will be configured globally, for you to use on any project. > For a project overview, tool/skill reference,
Reporting Security Vulnerabilities - If you believe you have discovered a security vulnerability, please report it to [security@mathworks.com](mailto:security@mathworks.com). Please see [MathWorks Vulnerability Disclosure Policy for Secu
CyberClaw - 👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态
Contributing to nanobot - Thank you for being here. nanobot is built with a simple belief: good tools should feel calm, clear, and humane. We care deeply about useful features, but we also believe in achieving more with less:
Contributing to GSD-2 - We're glad you're here. GSD-2 is an open project and contributions are welcome across the entire codebase. We hold a high bar for what gets merged — not to be gatekeepers, but because every change shi
Vision - GSD-2 is the orchestration layer between you and AI coding agents. It handles planning, execution, verification, and shipping so you can focus on what to build, not how to wrangle the tools.
Pocketgroq - PocketGroq is a powerful Python library that simplifies integration with the Groq API, offering advanced features for natural language processing, web scraping, and autonomous agent capabilities. Key Features Seamless integration with Groq API for text generation and completion Chain of Thought (CoT) reasoning for complex problem-solving and more.
Third-Party Notices - This repository is licensed under MIT. It includes third-party dependencies under additional licenses. Observed dependency licenses include: - MIT / MIT-0 / ISC / BSD-2-Clause / BSD-3-Clause / Apache-
Groqqle API Guide for Developers - This guide demonstrates how to use Groqqle's API functionalities for developers without the GUI interface.
Deploying Groqqle to Streamlit Cloud - This guide provides instructions for successfully running Groqqle on Streamlit Cloud, addressing the differences between local and cloud deployments.
Groqqle Troubleshooting Guide - This guide addresses common issues and their solutions when running Groqqle locally or in cloud environments.
Code Preview.Nvim - A Neovim plugin that shows a live diff preview of AI coding agent's file edits before you accept or reject them.
OpenKanban - **Generated:** 2026-01-03 | **Commit:** 6418109 | **Branch:** main TUI kanban board for orchestrating AI coding agents. Go 1.25+, Bubbletea, Lipgloss.
Hardcoded secrets - grep -rn "password\s*=\s*['\"][^$]" --include="*.{py,js,ts,go,java}" grep -rn "api[_-]?key\s*=\s*['\"]" --include="*.{py,js,ts,go,java}" grep -rn "token\s*=\s*['\"][A-Za-z0-9]{20,}" --include="*.{py,j
PM2 - pm2 logs <service> --lines 200 --nostream --err docker compose logs --tail 200 <service> journalctl -u <service> -n 200 --no-pager
Target official docs - site:docs.anthropic.com <keyword> site:nextjs.org <keyword> site:discord.com/developers <keyword> "<exact error>" fix "<exact error>" site:github.com/issues "<exact error>" <framework> <version> <libr
Measure response time for varying prefix match lengths - import time from statistics import mean def time_compare(guess, iterations=1000): times = [] for _ in range(iterations): t0 = time.perf_counter_ns() target_function("correct_token", guess) times.appen
Contributing to OpenAI Agent Builder GUI - Thank you for considering contributing to the OpenAI Agent Builder GUI! This document provides guidelines and instructions for contributing to this project. **IMPORTANT**: This project is created by J
Decision Agent - You are a Tier 2 decision agent for Correctless Auto Mode. You receive a structured decision request and return a structured decision. You are ephemeral — you terminate after returning your decision a
Fix-Diff Reviewer - You are the fix-diff reviewer for an audit round that has just committed its fixes. You are NOT a specialist auditor. You are NOT a taste critic. You are a narrow, read-only reviewer whose sole job is
Supervisor Agent - You are the supervisor agent for Correctless Auto Mode. You receive structured messages and return structured decisions. Each activation is independent — you have no memory of previous runs and must n
AGENTS.md — Post-Compact Reminder for Claude Code - > Guidelines for AI coding agents working in this Bash/Shell codebase. ---
Supervisor - > **⚠️ DEPRECATED**: The supervisor agent is deprecated. Use `lead` instead.
Akka Net Specialist - ---
Docfx Specialist - ---
Dotnet Benchmark Designer - ---
Dotnet Concurrency Specialist - ---
Dotnet Performance Analyst - ---
Roslyn Incremental Generator Specialist - ---
Base Template Generator - ---
Performance Analyzer - ---
Pr Reviewer - ---
Security Reviewer - ---
Web Search Agent - ---
Web Search Opencode - ---
CLAUDE - Claude Code Configuration - Agent Repository
MIGRATION SUMMARY - Claude Flow Commands to Agent System Migration Summary
Codebase Search - ---
Media Interpreter - ---
Open Source Librarian - ---
Tech Docs Writer - ---
Accessibility Specialist - ---
Ai Programmer - ---
Analytics Engineer - ---
Art Director - ---
Audio Director - ---
Community Manager - ---
Creative Director - ---
Economy Designer - ---
Engine Programmer - ---
Game Designer - ---
Gameplay Programmer - ---
Godot Csharp Specialist - ---
Godot Gdextension Specialist - ---
Godot Gdscript Specialist - ---
Godot Shader Specialist - ---
Godot Specialist - ---
Lead Programmer - ---
Level Designer - ---
Live Ops Designer - ---
Claude Md Auditor - ---
Quality Fixer - ---
Codebase Explorer - ---
Native - ---
Scenario Analyst - ---
Strategy Reviewer - ---
Server - ---
Web - ---
GLOBAL - 全局指令 — 所有 Agent 共享
Hello Agent - ---
Project Structure Validator - ---
Pr Testing Agent - ---
Golang Architect - ---
Golang Developer - ---
Coverage Analysis Generator Agent - ---
Crash Analysis Agent - ---
Crash Analyzer Agent - ---
Crash Analyzer Checker Agent - ---
Exploitability Validator Agent - ---
Function Trace Generator Agent - ---
Offsec Specialist - ---
Oss Evidence Verifier Agent - ---
Oss Hypothesis Checker Agent - ---
Oss Hypothesis Former Agent - ---
Oss Investigator Gh Archive Agent - ---
Oss Investigator Github Agent - ---
Oss Investigator Ioc Extractor Agent - ---
Oss Investigator Local Git Agent - ---
Oss Investigator Wayback Agent - ---
Oss Report Generator Agent - ---
Audit Budget - ---
Audit Compliance - ---
Audit Creative - ---
Audit Google - ---
Audit Meta - ---
Audit Tracking - ---
Copy Writer - ---
Creative Strategist - ---
Format Adapter - ---
Visual Designer - ---
Nopua Mentor En - ---
Nopua Mentor Ja - ---
Nopua Mentor - ---
Migration Committer - ---
Migration Implementer - ---
Migration Planner - ---
Qa - ---
Performance Analyst - ---
Docker Expert - ---
Kubernetes Specialist - ---
Security Engineer - ---
Spring Boot Engineer - ---
Beamer Translator - ---
Claim Verifier - ---
Domain Referee - ---
Editor - ---
Methods Referee - ---
Pedagogy Reviewer - ---
Quarto Critic - ---
Quarto Fixer - ---
Slide Auditor - ---
Tikz Reviewer - ---
Reviewer - ---
Config Safety Reviewer - ---
Docs Writer - ---
Performance Tuner - ---
Refactor Expert - ---
Root Cause Analyzer - ---
Tool Ui Designer - ---
Tool Ui Documenter - ---
Tool Ui Examples - ---
Tool Ui Implementer - ---
Tool Ui Reviewer - ---
Principal Qa Engineer - ---
Senior Engineer - ---
Mcp Server Architect - ---
Nix Expert - ---
Python Expert - ---
E2e Verifier - ---
F1 Test Drive - ---
Codebase Researcher - ---
Design Implementation Reviewer - ---
Design Iterator - ---
Prompt Engineer - ---
React Figma Ui Engineer - ---
Brainstormer - ---
Idea Critic - ---
Research Strategist - ---
Arch Reviewer - ---
Archon - ---
Fleet - ---
Knowledge Extractor - ---
Organizer Agent - ---
Research Agent - ---
Blog Researcher - ---
Blog Reviewer - ---
Blog Seo - ---
Blog Writer - ---
Legal Clauses - Legal Clause Analysis Subagent
Legal Compliance - Legal Compliance Check Subagent
Legal Recommendations - Legal Recommendations Subagent
Legal Risks - Legal Risk Assessment Subagent
Legal Terms - Legal Terms & Obligations Subagent
CSharpExpert.Agent - ---
Thinking Beast Mode.Agent - ---
Ultimate Transparent Thinking Beast Mode.Agent - ---
WinFormsExpert.Agent - ---
Accessibility Runtime Tester.Agent - ---
Accessibility.Agent - ---
Address Comments.Agent - ---
Adr Generator.Agent - ---
Aem Frontend Specialist.Agent - ---
Agent Governance Reviewer.Agent - ---
Amplitude Experiment Implementation.Agent - ---
Api Architect.Agent - ---
Apify Integration Expert.Agent - ---
Arch Linux Expert.Agent - ---
Arch.Agent - ---
Arm Migration.Agent - ---
Atlassian Requirements To Jira.Agent - ---
Azure Iac Exporter.Agent - ---
Azure Iac Generator.Agent - ---
Azure Logic Apps Expert.Agent - ---
COMPREHENSIVE TODO LIST - Comprehensive TODO: Implement Agent Orchestration in mcp-prompts
IMPLEMENTATION GUIDE - Claude Multi-Agent Architecture v3 - Implementation Guide
QUICK REFERENCE EXTRACTION - Quick Reference: Key Files to Extract & Adapt
TODO UNIFIED ORCHESTRATION - MCP-Prompts: Unified Orchestration Implementation TODO
Multi Dimensional Extractor - Multi-Dimensional Memory Extraction Agent
Agents Expert - ---
Claude Md Expert - ---
Completion Judge - ---
Doc Writer - ---
Evolving Orchestrator - ---
Experience Extractor - ---
Hooks Expert - ---
Mcp Expert - ---
Requirement Analyzer - ---
Skill Evolver - ---
Skill Synthesizer - ---
Skills Expert - ---
Docs Validation Orchestrator - ---
Phoenix Project Analyzer - ---
Skill Effectiveness Analyzer - ---
Api Designer - ---
Cobol Engineer - ---
Compliance Reviewer - ---
Content Strategist - ---
Copywriter - ---
Data Engineer - ---
Db2 Dba - ---
Design System Engineer - ---
Hlasm Assembler Specialist - ---
I18n Specialist - ---
Ibm I Specialist - ---
Database Administrator - ---
AGENT INDEX - Complete Agent Index
Rust Code Reviewer - ---
A11y Expert - ---
Api Doc Generator - ---
Api Gateway Expert - ---
Api Versioning Expert - ---
Aws Expert - ---
Azure Expert - ---
Babel - ---
Backend Dev - ---
Benchmark - ---
Browser Agent - ---
Business Analyst - ---
Canary Deploy Expert - ---
Catalyst - ---
Chaos Engineer - ---
Work Context Finder - ---
Ida Cmake - ---
Code Generator - ---
Data Explorer - ---
Hypothesis Generator - ---
Quality Assurance - ---
Report Writer - ---
Visualization Specialist - ---
Frontend Dev - ---
Product Manager - ---
Qa Engineer - ---
Tech Leader - ---
Board Meeting - ---
Ceo - ---
Cmo - ---
Conductor Orchestrator - ---
Cto - ---
Loop Execution Evaluator - ---
Loop Executor - ---
Loop Fixer - ---
Loop Plan Evaluator - ---
Loop Planner - ---
Name Picker - ---
Parallel Dispatcher - ---
Task Worker - ---
Ux Designer - ---
Ansible Automation Engineer - ---
Combat Effects Upgrade - ---
Database Engineer - ---
Github Profile Rules Engineer - ---
Golang General Engineer Compact - ---
Golang General Engineer - ---
Hook Development Engineer - ---
Kotlin General Engineer - ---
Kubernetes Helm Engineer - ---
Mcp Local Docs Engineer - ---
Nextjs Ecommerce Engineer - ---
Nodejs Api Engineer - ---
Opensearch Elasticsearch Engineer - ---
Performance Optimization Engineer - ---
Perses Engineer - ---
Php General Engineer - ---
Pipeline Orchestrator Engineer - ---
Pixijs Combat Renderer - ---
Fde Engineer - ---
Fde Experience Specialist - ---
Fde Qa Engineer - ---
Fde Release Engineer - ---
Fde Strategist - ---
Ps Solution Architect - ---
Ps Technical Architect - ---
Journal Writer - ---
Project Manager - ---
Ui Ux Designer - ---
Sales Company - Sales Company Research Subagent
Sales Competitive - Sales Competitive Positioning Subagent
Sales Contacts - Sales Contact Intelligence Subagent
Sales Opportunity - Sales Opportunity Assessment Subagent
Sales Strategy - Sales Outreach Strategy Subagent
Claude Code Tutor - ---
Code Quality Coach - ---
Python Mcp Expert - ---
Release Manager - ---
Terraform Architect - ---
Core Planner - ---
Skills Specialist - ---
Data Scientist - Data Scientist Agent
Game Feel Developer - Game Feel Engineer Agent Profile
Market Analyst - Market Analyst Agent
Master Orchestrator - Master Orchestrator Agent
Mechanics Developer - Senior Mechanics Engineer Agent Profile
Mid Game Designer - Mid Game Designer Agent Profile
Qa Agent - QA Agent Profile
Sr Game Artist - Sr Game Artist Agent Profile
Sr Game Designer - Sr Game Designer Agent Profile
Technical Artist - Technical Artist Agent Profile
Ui Ux Agent - UI/UX Agent Profile
Installation Tester - ---
Platform Validator - ---
Changelog Reviewer - ---
Comment Reviewer - ---
Docs Reviewer - ---
Marketplace Reviewer - ---
Safety Reviewer - ---
Test Reviewer - ---
Interviewer - ---
Auditor - ---
E2e Tester - ---
Excalidraw Designer - ---
Cli Ui Designer - ---
Code Analyzer - ---
Code Explorer - ---
Context Manager - ---
Debugging Specialist - ---
Implementation Specialist - ---
Javascript Pro - ---
Typescript Pro - ---
Ui Designer - ---
Orchestrator - ---
Refactorer - ---
Test Architect - ---
Docs Scraper - ---
Scout Agent - ---
Architecture Designer - ---
Brief Writer - ---
Codex Implementer - ---
Coverage Analyst - ---
Doc Refactor - ---
Feasibility Analyst - ---
Refactor Reviewer - ---
Solution Architect - ---
Strict Reviewer - ---
Tech Spec Reviewer - ---
Verify App - ---
Brief Constructor - ---
Bench Analyzer - ---
Task Curator - ---
Karpathy - ---
Browser Explorer - ---
Business Extractor - ---
Codex Risk Analyst - ---
Codex Strategist - ---
Contract Deriver - ---
Docs Researcher - ---
External Researcher - ---
Feasibility Checker - ---
Gap Analyzer - ---
Gap Auditor - ---
Git Master - ---
Interaction Extractor - ---
Qa Verifier - ---
Ralph Verifier - ---
Spec Coverage - ---
Api Documenter - ---
Architect Review - ---
C Pro - ---
Content Marketer - ---
Cpp Pro - ---
Csharp Pro - ---
Customer Support - ---
Database Optimizer - ---
Deployment Engineer - ---
Monthly Processor - ---
Monthly Synthesis - ---
Backend Code Reviewer - ---
Codebase Analyzer - ---
Codebase Locator - ---
Codebase Pattern Finder - ---
Graphite Branch Creator - ---
Playwright Component Tester - ---
React Code Reviewer - ---
Thoughts Analyzer - ---
Thoughts Locator - ---
Web Search Researcher - ---
E2e Browser Tester - ---
Grumpy Gopher - ---
Accessibility Expert - ---
Design System Architect - ---
Code Quality Reviewer - ---
Contracts Reviewer - ---
Fullstack Developer - ---
Historical Context Reviewer - ---
Principal Engineer - ---
Test Coverage Reviewer - ---
Uiux Designer - ---
Py Sdk Agent - ---
Api Integration Researcher - ---
N8n Mcp Tester - ---
N8n Webhook Tester - ---
N8n Workflow Architect - ---
N8n Workflow Builder - ---
N8n Workflow Debugger - ---
N8n Workflow Explorer - ---
W1 Recon - ---
W2 Decide - ---
W3 Edit - ---
W4 Verify - ---
AGENTS - AGENTS.md — `agents/`
Proxy Analyzer - ---
Ui Debugger - ---
MIA AGENTS - AGENTS.md - MIA Project Agent Guide
Memory Extractor - Memory Extractor Agent
Instrumentation Reviewer - ---
Hyperliquid DeFi Protocol Specialist - ---
Adversarial Plan Validator - ---
Ai Output Code Review Super Auditor - ---
Architecture Strategist - ---
Autoresearch - ---
Blender 3d Creator - ---
Blockchain Security Auditor - ---
Chain Infra Specialist Blockchain - ---
Codex Reviewer - ---
Defi Protocol Economist - ---
Frontend Reviewer - ---
Gap Analyst - ---
Glm Reviewer - ---
Kieran Python Reviewer - ---
Kieran Typescript Reviewer - ---
Lead Software Architect - ---
Liquid Staking Specialist - ---
Code Researcher - ---
Completeness Validator - ---
Deploy Reviewer - ---
Documentation Reviewer - ---
Infrastructure Reviewer - ---
Interview Completeness Checker - ---
Post Deploy Qa - ---
Pre Deploy Qa - ---
Prompt Reviewer - ---
Reality Checker - ---
Skeptic - ---
Skill Checker - ---
Task Creator - ---
Task Validator - ---
Tech Spec Validator - ---
Userspec Adequacy Validator - ---
Userspec Quality Validator - ---
Content Optimizer - ---
Seo Analyzer - ---
Codex Worker - ---
Gemini Worker - ---
Doc Link Verifier - ---
Doc Verifier - ---
Pr Review - ---
Version Bump - ---
Game Creator - ---
Game Deploy - ---
Game Qa Runner - ---
Game Reviewer - ---
Track Issue - ---
Build Agent - ---
Ffe Designer - FF&E Designer
Product And Materials Researcher - Product & Materials Researcher
Install Agent - ---
Release Agent - ---
Senior Python Engineer - ---
Uat Tester - ---
Uninstall Agent - ---
Version Resolver Agent - ---
Agent Context Reviewer - ---
Agent Definition Expert - ---
Claude Command Reviewer - ---
Claude Skill Reviewer - ---
Json Schema Architect - ---
Plugin Manifest Expert - ---
Python Script Reviewer - ---
Rlm Orchestrator - RLM Orchestrator Agent
Opus Plan Reviewer - ---
Section Writer - ---
Geo Analyzer - ---
Geo Indexer - ---
Geo Ranker - ---
Geo Rewriter - ---
Maintainer - ---
Processor - ---
Scribe - ---
Devrun - ---
Libcst Refactor - ---
Argus Quant Researcher - ---
Bmad Builder - ---
Cliproxy Engineer - ---
Critic Adversarial - ---
Crucible Gold Strategist - ---
Daemon Strategic Advisor - ---
Forge Mql5 Architect - ---
Forge Nautilus - ---
Generic Code Reviewer - ---
Git Guardian Nano - ---
Git Guardian - ---
Nautilus Trader Architect - ---
Onnx Model Builder - ---
Oracle Backtest Commander - ---
Scale Runner - ---
Sentinel Apex Guardian - ---
Trading Project Documenter - ---
Xml Architect - ---
Knowledge Manager At - ---
Knowledge Manager - ---
Changelog Manager - ---
Doc Generator - ---
Cs Cmo Advisor - ---
Cs Design Lead - ---
Cs Growth Lead - ---
Cs Privacy Officer - ---
Cto Architect - ---
Cto Orchestrator - ---
Strategic Cto Mentor - ---
Agent Developer - ---
Architecture Explorer - ---
Brainstorm Coordinator - ---
Context Librarian - ---
Database Navigator - ---
Devops Sre - ---
Error Detective - ---
Git Workflow Manager - ---
Github Issue Tracker - ---
Product Dx Specialist - ---
Refactoring Specialist - ---
Session Summarizer - ---
System Architect - ---
Detective - ---
Discovery - ---
Merge Supervisor - ---
Nextjs Supervisor - ---
Rust Supervisor - ---
Frontend Design System Implementer - ---
Api Infrastructure Generator - API & infrastructure patterns generator. Creates ADR (Action-Domain-Responder), API Versioning, Health Check, Unit of Work, Idempotency Handler, Structured Logger, Access Control, Distributed Lock, Re
Architecture Auditor - Architecture audit coordinator. Orchestrates structural, behavioral, and integration auditors for comprehensive reviews. Use PROACTIVELY for architecture audits.
Architecture Generator - Meta-generator for PHP 8.4 architecture components. Coordinates DDD and integration pattern generation. Use PROACTIVELY when creating bounded contexts, complex domain structures, or full-stack archite
Auth Reviewer - Authentication and authorization security reviewer. Analyzes authentication mechanisms, access control, CSRF protection, mass assignment, and PHP type juggling vulnerabilities. Covers OWASP A01:2021 B
Behavioral Auditor - GoF Behavioral patterns auditor. Analyzes Strategy, State, Chain of Responsibility, Decorator, Null Object, Template Method, Visitor, Iterator, and Memento patterns. Called by acc:pattern-auditor coor
Behavioral Generator - Behavioral patterns generator. Creates Strategy, State, Chain of Responsibility, Decorator, Null Object, Template Method, Visitor, Iterator, and Memento components for PHP 8.4. Called by acc:pattern-g
Bug Fix Coordinator - Coordinates bug diagnosis, fix generation, and test creation. Orchestrates acc:bug-hunter, acc:bug-fixer, and acc:test-generator.
Bug Fixer - Generates safe, minimal bug fixes using diagnosis from bug-hunter. Analyzes root cause, impact, and prevents regressions.
Bug Hunter - Bug detection specialist. Finds logic errors, null pointers, boundary issues, race conditions, resource leaks, exception issues, type issues, SQL injection, infinite loops. Use PROACTIVELY for code re
Business Logic Analyst - Business logic analysis specialist. Extracts business rules, explains business processes in natural language, maps domain concepts and ubiquitous language, detects state machines. Translates code to b
Ci Coordinator - CI/CD coordinator. Orchestrates pipeline setup, debugging, optimization, and auditing. Delegates to specialized agents for static analysis, testing, security, Docker, and deployment.
Ci Debugger - CI pipeline debugging specialist. Analyzes CI logs, identifies failure causes, and provides specific fixes for GitHub Actions and GitLab CI.
Ci Fixer - CI fix generation and application specialist. Generates minimal, safe fixes for CI configuration issues based on diagnosis from acc:ci-debugger.
Ci Security Agent - CI/CD security specialist. Audits secrets handling, permissions, dependency scanning, and security configurations in CI pipelines.
Claude Code Expert - Expert in creating Claude Code commands, agents, and skills. Use PROACTIVELY when you need to create or improve Claude Code components.
Code Review Coordinator - Code review coordinator. Orchestrates multi-level reviews (low/medium/high) with git diff analysis, delegates to specialized reviewers, aggregates findings with severity levels, calculates task match
Codebase Navigator - Codebase navigation specialist. Scans directory structure, identifies architectural layers, detects framework and patterns, finds entry points. Provides structural map for other explain agents.
Cqrs Auditor - CQRS/ES/EDA patterns auditor. Analyzes Command/Query separation, Event Sourcing compliance, and Event-Driven Architecture patterns. Called by acc:architecture-auditor and acc:pattern-auditor.
Cqrs Generator - CQRS/ES component generator. Creates Commands, Queries, Event Stores, Snapshots, and Read Models for PHP 8.4. Called by acc:generate-ddd command and acc:architecture-generator coordinator.
Creational Auditor - Creational patterns auditor. Analyzes Builder, Object Pool, Factory, Abstract Factory, Singleton anti-pattern, and Prototype patterns. Called by acc:pattern-auditor coordinator.
Eloquent Specialist - Expert in Laravel Eloquent ORM, database design, relationships, query optimization, and data modeling. Invoked for database-related tasks, model creation, relationship definitions, and query performan
Laravel Api Developer - Expert in Laravel API development with focus on RESTful design, API resources, authentication (Sanctum/Passport), rate limiting, and API versioning. Invoked for API endpoint creation, resource transfo
Laravel Architect - Expert Laravel application architect specializing in design patterns, project structure, and scalable architecture for Laravel 10+ applications. Invoked for architectural decisions, pattern selection,
Laravel Architecture Reviewer - Expert Laravel architecture reviewer specializing in evaluating system design, design patterns, scalability, and architectural decisions for Laravel applications. Invoked for architecture reviews, des
Laravel Code Reviewer - Expert Laravel code reviewer specializing in code quality, Laravel best practices, security vulnerabilities, and performance optimization. Invoked for code reviews, pull request analysis, and quality
Laravel Debugger - Expert Laravel debugger specializing in diagnosing complex issues, analyzing Laravel-specific problems, and systematic problem-solving. Invoked for debugging Laravel applications, analyzing errors, an
Laravel Documentation Engineer - Expert Laravel documentation engineer specializing in API documentation, technical guides, and developer-friendly Laravel documentation. Invoked for creating and maintaining Laravel project documentat
Laravel Performance Optimizer - Expert in Laravel performance optimization, caching strategies, query optimization, queue management, and scalability. Invoked for performance issues, optimization tasks, and scaling strategies.
Laravel Security Auditor - Expert in Laravel application security, specializing in vulnerability detection, secure coding practices, authentication, authorization, and OWASP top 10 prevention. Invoked for security reviews, vuln
Laravel Testing Expert - Expert in Laravel testing with Pest PHP and PHPUnit, specializing in feature tests, unit tests, database testing, API testing, and TDD practices. Invoked for test creation, test strategy, and quality
Scope Rule Architect Angular - Use this agent when you need to make architectural decisions about component placement in an Angular/TypeScript project following the Scope Rule pattern, or when setting up a new project with Angular
Scope Rule Architect Astro - Use this agent when you need to make architectural decisions about component placement in an Astro/TypeScript project following the Scope Rule pattern, or when setting up a new project with Astro 5, C
Scope Rule Architect NextJS - Use this agent when you need to make architectural decisions about component placement in a Next.js/TypeScript project following the Scope Rule pattern, or when setting up a new project with Next.js 1
Scope Rule Architect React - Use this agent when you need to make architectural decisions about component placement in a React/TypeScript project following the Scope Rule pattern, or when setting up a new project with React 19, T
Article Illustrator - |
Concretizer - 具象化专家。将抽象概念转化为类比、画面、行动等具体表达。由工作流导演在 Stage 5 显式调用。
Edit Diff Learner - |
Editor Review - 主编审稿专家。对初稿进行全面审查，包括AI味道检测、平淡度检测等。由工作流导演在 Stage 7 显式调用。
Empathy Designer - 社交货币与共情设计师。根据大纲和伤疤细节，设计文章的分享动因（Impression Management），建立 Share Map。由工作流导演在 Stage 4 显式调用。
Html Exporter - |
Humanizer - |
Memory Loader - |
Opening Tournament - 开头赛马机制。根据前序策划信息，并行提供 3 种极具差异化的实战开头原型方案（字数 150-300 字/个），由工作流导演在 Stage 5.8 显式调用。
Outline Architect - 大纲架构师。根据主题和素材设计文章结构。由工作流导演在 Stage 3 显式调用。
Position Engine - 立场引擎专家。在核心主题确定后，为文章强制设定无法被轻易反驳但具有强立场的“牙齿”，解决文章没牙的问题。由工作流导演在 Stage 1.5 显式调用。
Pre Publish Review - 发布前评审专家 v2.0。通过"发布前5问"评审 + 红队挑刺 + 具体修改建议，确保每个问题都有可执行方案。由工作流导演在 Stage 8 显式调用。
Research Expert - 微观伤疤打捞器 (原调研专家)。深度挖掘主题背后的极度微观细节、生活伤疤与行业隐秘代价。由工作流导演在 Stage 2 显式调用。
Title Designer - 标题设计师 v2.0。使用爆款标题公式库设计高点击率标题，确保每个标题都有"钩子"。由工作流导演在 Stage 5.5 显式调用。
Topic Generator - 选题生成器。当用户没有写作灵感时，从热点、个人资产、竞品分析三个维度生成候选选题。由工作流导演在 Stage 0a 显式调用。
Topic Research - 选题调研专家。验证选题是否值得写，提供热点扫描、爆款拆解、痛点验证和选题打分。由工作流导演在 Stage 0b 显式调用。
Wechat Reader Test - >
Writing Clarifier - 写作需求澄清专家。澄清核心写作要素，包括主题、读者画像、风格选择、字数要求等。由工作流导演在 Stage 1 显式调用。
Writing Executor - 写作执行专家。根据所有前序准备材料执行写作，产出初稿。由工作流导演在 Stage 6 显式调用。
Agent Template Wizard - Use this agent when you need to create new agents from the SUBAGENT_TEMPLATE.md template. This includes filling placeholders, ensuring proper formatting, validating frontmatter, and following naming c
Bash Shell Scripting - Use this agent when you need to develop, debug, or optimize bash scripts and shell automation. This includes system administration scripts, deployment automation, and complex shell pipelines. Examples
Documentation Writer - Use this agent when you need to create technical documentation, API documentation, README files, or architectural documentation. This agent specializes in clear technical writing, documentation standa
Fastapi Optimizer - Use this agent when you need FastAPI expertise including async programming, performance optimization, OpenAPI documentation, or building high-performance APIs. This agent specializes in FastAPI's mode
Golang Pro - Use this agent when you need expert Go development specializing in goroutines, channels, and building scalable concurrent systems. This includes Go concurrency patterns, channel communication, context
Javascript Expert - Use this agent when you need to develop, optimize, or debug JavaScript applications. This includes modern ES6+ features, asynchronous programming, DOM manipulation, and JavaScript runtime optimization
Python Pro - Use this agent when you need advanced Python development focused on decorators, generators, async/await, and Pythonic design patterns. This includes metaprogramming, advanced async patterns, descripto
Rust Expert - Use this agent when you need Rust programming expertise including ownership, lifetimes, unsafe code, or performance optimization. This agent specializes in memory safety, concurrent programming, and s
Systems Architect - Use this agent when you need real-time systems architecture, ultra-low latency design, or deterministic system development. This includes hard real-time constraints, RTOS design, interrupt handling, a
Charm Dev - |
Claude Code Hook Agent - Plays agent-specific sounds for the 6 hooks that actually fire in agent sessions
Claude Code Test Agent - Tests all 27 Claude Code hooks by logging each event to tests-agents-hook/agent-hook-fired.log
Domain Reviewer - Substantive domain review for biomedical epidemiology replication scripts and reports. Acts as a senior epidemiology journal referee (NEJM/Lancet/IJE standard). Checks confounding/bias assumptions, me
Proofreader - Expert proofreading agent for academic lecture slides. Reviews for grammar, typos, overflow, and consistency. Use proactively after creating or modifying lecture content.
R Reviewer - R code reviewer for academic scripts. Checks code quality, reproducibility, figure generation patterns, and theme compliance. Use after writing or modifying R scripts.
Verifier - End-to-end verification agent. Checks that slides compile, render, deploy, and display correctly. Use proactively before committing or creating PRs.
Compliance Checker - Reads the formatted output markdown, loads the journal requirements YAML, and systematically verifies compliance for each requirement. Produces a compliance checklist with PASS/WARN/FAIL for each item
Guidelines Extractor - Given a URL or raw text of journal author guidelines, extracts structured requirements into a guidelines/[journal].yml file. Use via /parse-guidelines skill. Tools include WebFetch for URL-based extra
Manuscript Analyzer - Reads a manuscript in markdown form, identifies all sections, detects IMRaD structure, flags sections deviating from expected order, and lists sections required by the journal that are missing. Use at
Section Drafter - Given manuscript content and a required section that is missing, drafts appropriate content for that section by synthesizing from the rest of the manuscript. Always marks output as DRAFT. Does not inv
Code Cleanup Optimizer - Remove technical debt, improve quality, eliminate redundancy after implementation is verified. Never use before functionality works correctly.
Codebase Context Analyzer - Understand codebase structure, patterns, dependencies, and architecture. Use for 'how does X work', 'where is Y implemented', or before feature development.
Dependency Manager - Manage Python dependencies, update packages, resolve conflicts, validate compatibility, check security vulnerabilities.
Devops Experience Architect - Set up environments, CI/CD pipelines, secrets management, containerization, deployment infrastructure, and developer tooling.
Documentation Expert - Create, update, or review documentation for code, architecture, APIs. Use after implementation or when docs are outdated/incomplete.
Task Completion Verifier - Validate deliverables meet requirements, acceptance criteria satisfied, edge cases handled. Use before marking tasks complete.
Tech Lead Architect - Design implementation approaches, research best practices, evaluate technology choices, architect solutions. Use before implementation or for technical decisions.
Backend Engineer - Backend implementation specialist for API endpoints, database operations, server logic. Use proactively when task involves "API", "endpoint", "database", "server", "backend", "middleware", "REST", "Gr
Build Error Resolver - Build and compilation error resolver. Use proactively when build/compile/type-check fails to quickly diagnose and fix errors. Fast error pattern matching and resolution. Returns concise fix status to
Coder - Implementation agent using TDD + Ralph Loop for feature development. Use proactively for implementation tasks requiring code changes. Supports SC-based parallel execution for independent success crite
Design Reviewer - Design quality review agent for high-stakes UI surfaces. Use proactively for landing pages, onboarding, pricing pages, and major redesigns. Reviews for aesthetic adherence, visual polish, and producti
Documenter - Documentation update agent for 3-Tier Documentation System. Auto-syncs CLAUDE.md, CONTEXT.md files, and docs/ai-context/ after implementation. Uses Haiku for efficiency with structured output.
Explorer - Fast codebase exploration agent for finding files, patterns, and understanding architecture. Uses Glob, Grep, Read tools efficiently. Returns concise summaries to main orchestrator.
Frontend Engineer - Frontend implementation specialist for UI components, React patterns, CSS styling. Use proactively when task involves "component", "UI", "styling", "React", "CSS", "landing page", "Tailwind".
Plan Reviewer - Plan review specialist for analyzing plan quality, detecting gaps, and verifying completeness. Use proactively after plan creation to review completeness and clarity. Uses Read, Glob, Grep tools to ex
Researcher - External research specialist for finding documentation, APIs, and best practices. Uses WebSearch, WebFetch, and query-docs tools efficiently. Returns concise summaries with sources to main orchestrato
Security Analyst - Security vulnerability analyst for authentication, authorization, secrets, input validation. Use proactively when code changes involve auth/security patterns or when explicitly requested via /review s
Tester - Test writing specialist for creating and executing tests following TDD methodology. Uses Read, Write, Bash tools to write tests, run them, and verify coverage. Returns test results summary to main orc
Validator - Verification specialist for running type checks, linting, and coverage analysis. Uses Bash and Read tools to execute verification commands. Returns concise verification status to main orchestrator.
Agent Quality Reviewer - Reviews a single clarc agent file for quality across 8 dimensions — instruction clarity, model appropriateness, tool coverage, trigger precision, exit criteria, examples, overlap detection, and safety
Agent System Reviewer - Orchestrates a full clarc system review by synthesizing results from all component analyzers (agent-quality-reviewer, skill-depth-analyzer, command-auditor, hook-auditor), cross-component validators,
Android Reviewer - Expert Android code reviewer specializing in Jetpack Compose best practices, Hilt DI scoping, Room migrations, ViewModel/UiState patterns, and Coroutine Dispatcher correctness. Use for all Kotlin/Andr
Article Editor - Editorial critique for blog posts, essays, guides, and long-form articles — evaluates structure, opening strength, voice consistency, evidence quality, banned patterns, and SEO basics. Use after writi
Bash Reviewer - Reviews Bash/shell scripts for correctness, safety, idiomatic style, and portability. Checks set -euo pipefail, quoting, shellcheck issues, security (no eval, mktemp, path quoting), BATS test coverage
C Reviewer - Expert C code reviewer specializing in C11/C17 idioms, memory safety (malloc/free discipline, no double-free), opaque pointer encapsulation, error code patterns, goto cleanup, safe string functions, a
Command Auditor - Audits clarc commands for UX ergonomics across 8 dimensions — naming consistency, argument design, feedback loops, step count, agent invocation, overlap detection, missing commands, and built-in confl
Competitive Analyst - Systematically researches competitors to map features, pricing, positioning, recent releases, and market gaps. Produces a feature matrix and opportunity list that feeds directly into idea discovery. U
Contract Reviewer - Reviews API changes for contract breaks. Given git diff of API definitions and existing consumer pacts, classifies each change as BREAKING / NON-BREAKING / ADDITIVE and produces a migration plan. Use
Cpp Reviewer - Expert C++ code reviewer specializing in C++ Core Guidelines, modern C++20/23, memory safety, RAII, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
Csharp Reviewer - Expert C# code reviewer specializing in C# 12/.NET 8 idioms, nullable reference types, async/await correctness, records, pattern matching, CQRS with MediatR, Entity Framework Core, SQL injection, mass
Data Architect - Data Mesh architecture specialist. Analyzes business domains to identify data products, assigns ownership, recommends technology stack (Lakehouse, Catalog, Contract Testing), and creates a migration p
Database Reviewer - PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database p
Design Critic - Reviews visual designs and gives structured critique covering composition, visual hierarchy, typography, color, brand coherence, and accessibility. Works from screenshots, wireframes, written descript
Design System Reviewer - Comprehensive design system audit — reviews CSS/token structure, dark mode implementation, icon system, accessibility compliance, design-code consistency, and component completeness. Routes findings a
Devsecops Reviewer - Infrastructure and CI/CD security reviewer — scans Terraform, Dockerfiles, Kubernetes manifests, GitHub Actions workflows, and dependency lockfiles for misconfigurations, supply chain risks, and pipel
Doc Updater - Documentation and codemap specialist. Use PROACTIVELY after structural changes, before releases, or when codemaps are stale. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates
Ai Engineer - Develops AI and machine learning solutions, from model training to production deployment. Use proactively when implementing AI features or optimising ML workflows.
Code Standards Enforcer - Enforces development principles from CLAUDE.md. Use proactively after code changes to ensure clarity over cleverness, proper British English, and modern best practices.
Design Frontend Assistant - Creates beautiful, accessible, and user-friendly frontend interfaces. Use proactively when designing UI components or improving user experience.
Documentation Generator - Creates and maintains technical documentation, README files, and API docs. Use proactively when code changes require documentation updates or new features need explaining.
Fullstack Engineer - Develops complete web applications from frontend to backend. Use proactively when building full-stack features or integrating frontend and backend systems.
Git Workflow Assistant - Manages Git workflows, branching strategies, and code collaboration practices. Use proactively when managing repositories or when Git workflow issues arise.
Infra Engineer - Manages infrastructure, deployment, monitoring, and DevOps practices. Use proactively when setting up projects or when infrastructure issues arise.
Performance Profiler - Identifies performance bottlenecks and suggests optimisations while maintaining code clarity. Use proactively when performance issues arise or before production deployments.
Test Engineer - Creates comprehensive test suites and maintains testing standards. Use proactively when adding new features or when test coverage is insufficient.
Convex Expert - Expert Convex backend developer for queries, mutations, actions, schemas, auth, scheduling, components, and database operations. Use PROACTIVELY when working in convex/ directory, implementing backend
Audit Design - Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
Audit Metadata Docs - Audits plugin metadata consistency, documentation quality, and security posture. Dispatched by /hone during Phase 2.
Audit Skills Agents - Audits plugin skill and agent instruction quality, frontmatter validation, and cross-references. Dispatched by /hone during Phase 2.
Audit Structure - Audits plugin directory layout and file compliance against Claude Code plugin spec. Dispatched by /hone during Phase 2.
Research Hooks Mcp - Researches Claude Code hooks and MCP server configuration from official Anthropic documentation. Shared by /smith and /hone.
Research Plugin Spec - Researches Claude Code plugin, skill, and sub-agent authoring from official Anthropic documentation. Shared by /smith and /hone.
Model Scraper - |
Chief Of Staff - Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/info_only/meeting_info/action_required), generates draft replies, and enfor
Cpp Architect - Large-scale C++ architecture specialist. Designs module boundaries, dependency graphs, CMake structure, and physical layout for projects with 100K+ lines. Use when planning new libraries, restructurin
Cpp Build Resolver - C++ build, CMake, and compilation error resolution specialist. Fixes build errors, linker issues, and template errors with minimal changes. Use when C++ builds fail.
Docs Lookup - When the user asks how to use a library, framework, or API or needs up-to-date code examples, use Context7 MCP to fetch current documentation and return answers with examples. Invoke for docs/API/setu
E2e Runner - End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines fl
Flutter Reviewer - Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-
Go Build Resolver - Go build, vet, and compilation error resolution specialist. Fixes build errors, go vet issues, and linter warnings with minimal changes. Use when Go builds fail.
Go Reviewer - Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects.
Harness Optimizer - Analyze and improve the local agent harness configuration for reliability, cost, and throughput.
Integration Test Runner - Multi-process integration testing specialist for C++20 HPC applications. Manages CTest labels, MPI-based tests, performance regression detection, and multi-component pipeline verification. Use for tes
Java Build Resolver - Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Java compiler errors, and Maven/Gradle issues with minimal changes. Use when Java or Spring Boot b
Java Reviewer - Expert Java and Spring Boot code reviewer specializing in layered architecture, JPA patterns, security, and concurrency. Use for all Java code changes. MUST BE USED for Spring Boot projects.
Kotlin Build Resolver - Kotlin/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Kotlin compiler errors, and Gradle issues with minimal changes. Use when Kotlin builds fail.
Kotlin Reviewer - Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.
Agent Sdk Verifier - Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent sh
Ansible Strategy Planner - Use this agent when creating implementation plans for Ansible automation where PASS scores on quality dimensions are the primary outcome. Plugin features (skills, commands, hooks, agents) are unproven
Jina Search - Research specialist using Jina MCP tools to search web and arXiv sources. Use when you need to research current best practices, find latest documentation, or gather academic knowledge on specific topi
Markdown Fixer - Executes markdown fixes based on confirmed errors and investigation context
Markdown Investigator - Autonomous analyzer that determines if markdown errors are fixable or false positives
Markdown Orchestrator - Strategic coordinator for intelligent markdown linting workflow
Pr Message Reviewer - Expert PR message reviewer from a maintainer's perspective. Use PROACTIVELY when a PR message has been drafted and needs critical evaluation before submission. Verifies all claims against git evidence
Project Goal Evaluator - Use this agent when evaluating planning documents to extract primary project goals, performing strategic analysis, or conducting due diligence reviews on project proposals. Examples:
Analyst - Use this agent for deep analysis, complex reasoning, architecture decisions, code review, and problem-solving that requires careful thought. Best for tasks like "analyze this system", "what's the best
Python Reviewer - Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.
Refactor Cleaner - Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely r
Rlm Subcall - Acts as the RLM sub-LLM (llm_query). Given a chunk of context (usually via a file path) and a query, extract only what is relevant and return a compact structured result. Use proactively for long cont
Database Admin - Use this agent when you need to work with database systems, including querying for data analysis, diagnosing performance bottlenecks, optimizing database structures, managing indexes, implementing bac
Docs Manager - Use this agent when you need to manage technical documentation, establish implementation standards, analyze and update existing documentation based on code changes, write or update Product Development
Git Manager - Use this agent when you need to stage, commit, and push code changes to the current git branch while ensuring security and professional commit standards. Examples: <example>Context: User has finished
Planner Researcher - Use this agent when you need to research, plan, and architect technical solutions. This includes: searching for latest documentation and best practices, analyzing existing codebases to understand stru
Playwright Qa Tester - Use this agent when you need to test specific features or functionality in a web interface using Playwright. Examples: <example>Context: The user has just implemented a new login form and wants to tes
Review Package Analyzer - Analyze codebase and current work to identify files for a review package. Use when creating packages for external LLM review.
Loop Operator - Safety net for autonomous agent loops. Detects stalls, reduces scope on repeated failures, escalates to user when stuck.
Editor In Chief - Editor-in-chief for the thruuu article writing pipeline. Final agent in the sequence. Reads the linked draft, full brief, and GUIDELINE.md. Runs a 12-point review checklist, fixes what it can, re-invo
Head Of Research - Head of research for the thruuu article writing pipeline. Runs after all researcher agents complete. Reads all .claude/research/*.md outputs, scans the knowledge/ folder, analyzes search intent from t
Linker - Linker for the thruuu article writing pipeline. Receives the humanized draft, the Links element from the brief, Content Outline inline link references, and the Quotes & Stats bank from research-brief.
Writer - Writer for the thruuu article writing pipeline. Receives the full brief, research-brief.md, and GUIDELINE.md. Follows the Content Outline heading structure exactly. Writes the first complete article d
Code Reviewer.Agent - Senior code reviewer. Use after code changes for quality review.
Doc Writer.Agent - Technical documentation writer. Creates and updates docs.
Security Auditor.Agent - Security-focused code auditor. Auto-spawned for auth, payment, and identity code.
Fact Checking Agent - Use proactively to verify claims in documentation against sources of truth (codebase, web data, or research). Identifies claims, locates verification sources, validates accuracy, and corrects mismatch
Meta Agent - Generates a new, complete Claude Code sub-agent configuration file from a user's description. Use this to create new agents. Use this Proactively when the user asks you to create a new sub agent.
Cni Builder - Builds Prismatic Code Native Integrations (CNI). Handles TypeScript generation, component manifest installation, OAuth configuration, deployment, testing, and iteration.
Component Builder - Builds Prismatic custom components. Handles scaffolding, code generation, building, and publishing for connector components.
Embed Advisor - Guides developers through embedding Prismatic's marketplace and workflow builder in their web application. Handles signing key setup, JWT backend generation, frontend SDK integration, theming, i18n, a
External Api Researcher - Researches an external API by fetching and analyzing its documentation. Extracts authentication methods, endpoints, data models, and webhook capabilities into a structured JSON spec.
Orby - Use this agent when users need help interacting with the Prismatic platform - answering questions about their Prismatic environment, executing platform operations, constructing GraphQL queries, search
Backend Architect - Backend architect for scalable API design, microservices, and distributed systems
Cloud Architect - Cloud architect for AWS/Azure/GCP infrastructure, IaC, FinOps, and multi-cloud strategies
Code Reviewer - Code review expert for quality analysis, security vulnerabilities, and production reliability
Database Architect - Database architect for data modeling, technology selection, schema design, and migration planning
Debugger - Debugging specialist for errors, test failures, and unexpected behavior
Docs Architect - Technical documentation architect for comprehensive system docs and architecture guides
Frontend Developer - Frontend developer for React, Next.js, responsive layouts, and accessible UI components
Performance Engineer - Performance engineer for optimization, observability, and scalable system performance
Security Auditor - Security auditor for DevSecOps, OWASP compliance, vulnerability assessment, and threat modeling
Tdd Orchestrator - TDD orchestrator enforcing red-green-refactor discipline and test-driven development
Bowser Qa Agent - UI validation agent that executes user stories against web apps and reports pass/fail results with screenshots at every step. Use for QA, acceptance testing, user story validation, or UI verification.
Claude Bowser Agent - Browser automation agent. Use when you need to browse websites, take screenshots, interact with web pages, or perform browser tasks. Cannot run in parallel — only one instance at a time. Keywords - br
Playwright Bowser Agent - Headless browser automation agent using Playwright CLI. Use when you need headless browsing, parallel browser sessions, UI testing, screenshots, or web scraping. Supports parallel instances. Keywords
Categorize Csv Agent - Categorize transactions in normalized CSV files based on descriptions. Use after normalization.
Csv Edit Agent - Make modifications or report on csv files. Use only when directly requested 'csv-edit-agent'.
Generative Ui Agent - Generate HTML dashboard from financial data and graphs. Use after graph generation.
Graph Agent - Generate multiple financial insight graphs from CSV data. Use after merging accounts.
Merge Accounts Agent - Merge multiple normalized CSV files into a single transactions file. Use after categorization.
Normalize Csv Agent - Normalize raw bank CSV exports into standardized format. Use when processing raw_*.csv files.
Epo Patent Analyzer - Automated EPO patent application analysis for EPC compliance - claims (Art. 84 EPC), sufficiency (Art. 83 EPC), and formalities (Rules 42-49 EPC)
Epo Patent Drafter - Expert in drafting EPO-compliant patent claims and specifications. Specializes in two-part form claims, problem-solution approach, and EPC Rules 42-43 compliance.
Mpep Expert - Expert in USPTO MPEP, 35 USC statutes, and 37 CFR regulations. Provides legal research, examiner guidance, and compliance interpretation using hybrid RAG search.
Mpep Researcher - Expert in searching and interpreting USPTO MPEP, 35 USC statutes, 37 CFR regulations using hybrid RAG search (FAISS + BM25 + HyDE)
Patent Analyzer - Automated patent application analysis for USPTO compliance - claims (35 USC 112b), specification (35 USC 112a), and formalities (MPEP 608)
Patent Creator - Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.
Patent Development - Specialized agent for developing and extending the Claude Patent Creator codebase - adding MCP tools, analyzers, and features
Patent Drafter - Expert in drafting USPTO-compliant patent claims and specifications. Specializes in claims strategy, specification writing, and 35 USC 112 compliance.
Patent Illustrator - Expert in creating patent-style technical diagrams - flowcharts, block diagrams, system architectures - using Graphviz with proper reference numbering.
Patent Researcher - Expert in patent prior art searching, patentability assessment, and competitive intelligence. Uses BigQuery (100M+ patents), CPC classification, and systematic 7-step methodology.
Patent Search Specialist - Expert in patent prior art searching using BigQuery (100M+ patents), USPTO API, and local corpus with systematic 7-step methodology
Pct Application Specialist - Expert in preparing PCT international applications under the Patent Cooperation Treaty. Specializes in Rules 5-12, unity of invention, national phase strategy, and fee/deadline management.
Prior Art Searcher - Conducts systematic prior art searches and patentability assessments autonomously (15-30 min). Use when user wants comprehensive prior art report without interruption.
Builder - Use this agent when you need to build a complete, executable project from requirements and context. This includes scenarios where you have task specifications, data sources, examples, and knowledge ba
Designer - Use this agent when you need to analyze task requirements and generate a comprehensive Product Requirements Context (PRC) document. This agent should be triggered when: 1) A user has a TASK_PROMPT.md
Learner - Use this agent when you need to systematically collect, process, and organize knowledge from various sources into a structured knowledge base. Examples: <example>Context: User has scattered documentat
Prompter - Use this agent when you need to create, refine, or optimize prompts for AI systems. This includes writing new prompts from scratch, improving existing prompts for better performance, converting prompt
Changelog Generator - Specialized agent for generating changelogs from ADVPL/TLPP code changes - analyzes diffs and produces structured release notes
Docs Reference - Specialized agent for looking up Protheus documentation - native functions, SX data dictionary, REST APIs, MV parameters, and TOTVS framework reference with local + TDN online search
Migrator - Specialized agent for migrating ADVPL procedural code to TLPP object-oriented code, modernizing legacy Protheus applications with classes, namespaces, and OOP patterns
Process Consultant - Specialized agent for consulting Protheus ERP business processes, module workflows, routines, integrations, and understanding how business operations work in TOTVS Protheus
Sx Configurator - Specialized agent for generating Protheus SX data dictionary configuration scripts - SX3 fields, SIX indexes, SX1 questions, SX5 generic tables, SX7 triggers
Architecture Reviewer - Use AFTER spec-reviewer passes to review code for architectural issues. Structural health check.
Cloudformation Reviewer - Use AFTER spec-reviewer passes to review CloudFormation templates for S4 standards compliance. Covers tagging, naming, security posture, cost optimization, and CF best practices.
Cohesion Lens - Paradigm lens agent for single responsibility and cohesion observation. Used by /prism to identify modules, files, or functions with mixed concerns. Observation-only — does not suggest refactoring.
Consistency Lens - Paradigm lens agent for convention consistency observation. Used by /prism to identify convention variations within a codebase. Observation-only — does not suggest which convention is correct.
Coupling Lens - Paradigm lens agent for module coupling observation. Used by /prism to identify tight or hidden dependencies between modules. Observation-only — does not suggest decoupling.
Dry Lens - Paradigm lens agent for DRY (Don't Repeat Yourself) observation. Used by /prism to identify duplicated logic across a codebase. Observation-only — does not suggest fixes.
Kiss Lens - Paradigm lens agent for KISS (Keep It Simple, Stupid) observation. Used by /prism to identify overcomplicated code where simpler alternatives exist. Observation-only — does not suggest fixes.
Performance Reviewer - Use AFTER spec-reviewer passes to review code for performance issues. Heuristic-based, not profiling.
Quality Reviewer - Use AFTER spec-reviewer passes to review code quality. Catches implementation issues.
Spec Reviewer - You MUST use this after implementation to verify code matches its specification. Catches spec drift.
Yagni Lens - Paradigm lens agent for YAGNI (You Aren't Gonna Need It) observation. Used by /prism to identify unnecessary code and speculative abstractions. Observation-only — does not suggest fixes.
Luca - Creates invoices, quotations, or receipts. Generates JSON, produces PDF, and drafts professional email for sending to clients.
Build Master - Build system and CI/CD pipeline expert that optimizes compilation, packaging, and deployment processes. Use PROACTIVELY when setting up builds, CI/CD, or fixing build issues.
Cloud Developer - AWS cloud architecture expert that designs and implements scalable, resilient cloud-native solutions. Use PROACTIVELY when building cloud applications or migrating to AWS.
Code Documentor - Documentation specialist that creates comprehensive, clear, and maintainable documentation for codebases. Use PROACTIVELY after implementing features or when documentation is needed.
Code Historian - Code evolution and history analysis expert that tracks how code has changed over time, who changed it, and patterns in collaborative development. Use when investigating code evolution, understanding c
Code Modernizer - Legacy code transformation expert that updates outdated codebases to use modern patterns, libraries, and language features. Use PROACTIVELY when planning upgrade roadmaps or upgrading legacy code.
Concurrency Expert - Concurrent programming expert that implements thread-safe code, async patterns, and distributed systems. Use PROACTIVELY when dealing with parallelism, race conditions, or scaling challenges.
Configuration Manager - Configuration and environment management expert that handles application settings, secrets, and deployment configurations. Use PROACTIVELY when managing configs across environments.
Database Designer - Database architecture expert that designs efficient schemas, optimizes queries, and ensures data integrity. Use PROACTIVELY when designing data models or solving database performance issues.
Deployment Specialist - Deployment automation expert that implements zero-downtime releases, rollback strategies, and continuous delivery pipelines. Use PROACTIVELY when setting up deployment processes or release management.
Development Manager - Development management expert that transforms product requirements into comprehensive technical implementation plans with detailed architecture, resource allocation, and risk assessment. Use when crea
Exception Handling Master - Error handling and resilience expert that implements robust exception management and recovery strategies. Use when implementing error handling systems.
Internationalization Specialist - I18n expert that implements multi-language support, handles localization, and ensures applications work seamlessly across different languages and regions. Use PROACTIVELY when building global applicat
Junior Developer - Learning-focused development assistant that approaches code with curiosity and asks thoughtful questions
Logging Master - Logging and observability expert that implements comprehensive logging strategies for debugging, monitoring, and auditing. Use PROACTIVELY when setting up logging systems.
Mentor - Teaching and knowledge transfer expert that provides customized learning experiences about the codebase and its technologies. Use PROACTIVELY when explaining concepts or answering technical questions.
Ops Agent - Operations Agent
Agent Builder - Generates a new, complete Claude Code sub-agent configuration file from a user's description. Use this to create new agents. Use this Proactively when the user asks you to create a new sub agent, or u
Specifications Tracking Specialist - Specialist for maintaining comprehensive and accurate documentation in HISTORY.md and SPECIFICATIONS.md files. Use proactively after any meaningful codebase changes (e.g. skip documentation changes, l
Skill Optimizer - SKILL.md 자동개선 에이전트 — Karpathy autoresearch 루프
Backend - FastAPI/Flask/Node.js API development with Result pattern and async patterns
Construction Bi - Construction industry domain specialist for Intellegix/ASR with Procore, Foundation, and Raken integrations
Database - PostgreSQL/SQLite/Redis schema design, query optimization, and migration management
Devops - CI/CD pipelines, Docker, Render deployment, and infrastructure management
Frontend - React/Next.js/TailwindCSS UI development with React Query and Zustand state management
Orchestrator Multi - Multi-agent parallel orchestrator using git worktrees — splits work across N agents, manages territory, merges results
Research - Web research and technology evaluation specialist with structured analysis output
Testing - Test development with pytest/Jest/Vitest, coverage analysis, and bug reproduction workflows
Pace Analyst - Analyst perspective agent for devpace. Handles metrics collection, retrospectives, and trend analysis. Data analysis with write capability for dashboards and insights.
Pace Engineer - Engineer perspective agent for devpace. Handles CR implementation, quality gates, and code changes. Full file access for development work.
Pace Pm - Product manager perspective agent for devpace. Handles iteration planning, change management, and business alignment. Analysis with write capability for planning and change execution.
A11y Purist - The divine enforcer of Universal Readability who purges the web of accessibility sins. Use this agent to audit WCAG compliance, semantic HTML, ARIA attributes, keyboard navigation, and perceivability.
Adaptive Purist - The iron-willed guardian of seamless UI across foldables, multi-monitors, touch/keyboard inputs, and high-DPI displays. Use this agent to audit adaptive UI, foldable support, viewport segments, touch
Arch Purist - The iron-fisted enforcer of DDD layer boundaries and architectural integrity. Use this agent to audit import graphs, detect layer violations, circular dependencies, and structural rot. Triggers on "ar
Copy Purist - The relentless guardian of high-converting communication. Use this agent to audit UX copy, headlines, CTAs, email/SMS, and persuasion frameworks across your application. Triggers on "copy review", "co
Dead Code Purist - The grim reaper of unused code. Use this agent to find and eliminate dead code, unreachable branches, unused exports, orphaned files, and commented-out blocks. Triggers on "dead code", "unused code",
Dep Purist - The relentless auditor of project dependencies. Use this agent to find outdated, vulnerable, duplicate, unused, and bloated npm packages. Triggers on "dependency audit", "dep review", "outdated packag
Git Purist - The sacred guardian of git history. Use this agent to review commits, split bloated changes, enforce conventional commits, and ensure every commit is atomic and semantically meaningful. Triggers on "g
Naming Purist - The linguistic guardian of code clarity. Use this agent to enforce naming conventions, file naming patterns, and semantic variable/function naming across the codebase. Triggers on "naming review", "na
Observability Purist - The divine bringer of light into the darkness of unobservable code. Use this agent to audit and enforce proper logging, distributed tracing, metrics, error handling, and instrumentation across the cod
React Purist - The high priest of the Immutable State, enforcer of component purity, hook discipline, and the sacred three-tier UI architecture. Use this agent to audit React components for state management sins, ef
Secret Purist - The paranoid sentinel of credential security. Use this agent to scan codebases and git history for leaked secrets, API keys, tokens, passwords, and hardcoded credentials. Triggers on "secret scan", "c
Size Purist - The merciless executioner of bloated files. Use this agent to find oversized files, god classes, mega-components, and monolithic modules that have grown beyond reason. Triggers on "file size", "large
Test Purist - The merciless enforcer of test coverage and quality. Use this agent to find untested code, meaningless assertions, missing property tests, and coverage gaps. Triggers on "test review", "coverage audit
Typescript Purist - The last defender of TypeScript's type system. Use this agent to review TypeScript code for type safety violations, enforce strict typing standards, and refactor weak types into proper ones. Triggers
Be Developer - Backend Developer - API implementation using patterns, RLS enforcement
Bsa - Business Systems Analyst - Pattern discovery, spec creation, acceptance criteria definition
Data Provisioning Eng - Data Provisioning Engineer - Data pipelines and ETL processes
Fe Developer - Frontend Developer - UI implementation using patterns
Qas - Quality Assurance Specialist - Testing execution using test patterns
Rte - Release Train Engineer - PR creation, CI/CD validation, release coordination
Tdm - Technical Delivery Manager - Orchestrates agents, manages blockers, updates Linear
Tech Writer - Technical Writer - Documentation creation using documentation patterns
Codebase Analyst - Use proactively to find codebase patterns, coding style and team standards. Specialized agent for deep codebase pattern analysis and convention discovery
Api Consistency Auditor - |
Best Practice Extractor - |
Blocker Detector - |
Claude Code Guide - |
Code Oracle Codex - |
Code Oracle Gemini - |
Conversation Deep Researcher - |
Conversation Index Scanner - |
Conversation Insights Orchestrator - |
Example Notebook Librarian - |
Hec Hms Documentation Scout - |
Hecras Code Archaeologist - |
Hecras General Agent - |
Hecras Notebook Qaqc - |
Hecras Project Inspector - |
Hecras Results Analyst - |
Hierarchical Knowledge Agent Skill Memory Curator - |
Notebook Anomaly Spotter - |
Notebook Output Auditor - |
Python Code Quality Engineer - Production-grade Python code quality engineer enforcing Ruff linting, mypy strict type checking, comprehensive docstrings, magic number elimination, and import organization. Implements PEP 257, PEP 48
Python Complexity Reducer - Production-grade Python complexity reduction specialist using radon to reduce cyclomatic complexity from 20 to ≤10
Python Document Processor - Production-grade Python document processor for PDF/DOCX/Markdown/TXT extraction with robust error handling, text cleaning, metadata extraction, and format-specific optimizations. Eliminates 400 lines
Python Rag Backend Engineer - Production-grade Python RAG backend engineer specializing in ChromaDB vector storage, sentence-transformers embeddings, hybrid search (BM25 + semantic), and retrieval optimization. Implements dependen
Python Refactoring Architect - Production-grade Python refactoring specialist decomposing God Modules, eliminating duplication, and enforcing SOLID principles
Python Security Auditor - Production-grade Python security auditor eliminating os.execv() vulnerability, bare exception handlers, and silent failures. Enforces OWASP Top 10 compliance, input validation, and secure error handli
Python Testing Engineer - Production-grade Python testing specialist fixing broken tests and achieving 85% coverage with pytest best practices
Code Simplifier - Use this agent when code has been written or modified and needs to be simplified for clarity, consistency, and maintainability while preserving all functionality. This agent should be triggered automa
Comment Analyzer - Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes: (1) After generating large documentation comments or docstrings, (2) Bef
Pr Test Analyzer - Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new fun
Silent Failure Hunter - Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after
Type Design Analyzer - Use this agent when you need expert analysis of type design in your codebase. Specifically use it: (1) when introducing a new type to ensure it follows best practices for encapsulation and invariant e
Ai Specialist - Expert in integrating LLMs, building RAG systems (pgvector), and creating MCP servers.
Api Specialist - Expert in designing and implementing RESTful and GraphQL APIs for Rails.
Devops Engineer - Expert in infrastructure, containerization, and deployment (Docker, Kamal, Kubernetes, Ansible, Terraform).
Rails Architect - Senior Architect for planning features, designing schemas, and selecting libraries.
Rails Auditor - Final gatekeeper for code quality, security, and performance. Validates Definition of Done (DoD) and reviews GitHub PRs.
Rails Developer - Senior Rails Developer focused on implementation, TDD, and clean code conventions.
Backend Specialist - API and server development expert. Use for backend logic, authentication, and data processing.
Code Review Specialist - Code quality and security expert. Use for code reviews, security analysis, refactoring guidance, and best practices enforcement.
Database Specialist - Database architecture and optimization expert. Use for schema design, queries, and data modeling.
Designer Specialist - designer-specialist - a UI/UX design specialist focused on creating beautiful, intuitive interfaces
Devops Specialist - Infrastructure and deployment expert. Use for CI/CD, containerization, and system configuration.
Frontend Specialist - UI/UX development expert for React, Vue, Angular, and responsive design. Use for all frontend implementation tasks.
Testing Specialist - Quality assurance and testing expert. Use for test implementation, coverage, and quality metrics.
Developer - Use this agent when you need expert guidance on Go development best practices, including code implementation, refactoring for idiomatic Go, performance optimization, error handling patterns, concurren
Pm - Use this agent when you need to identify, analyze, and propose new features or functionalities for the faker library. This includes analyzing gaps in current functionality, researching competitor libr
Claude Optimizer - Optimizes CLAUDE.md files for maximum effectiveness with Sonnet 4 and Opus 4 models by analyzing structure, content clarity, token efficiency, and model-specific patterns
Ceo Bezos - 公司 CEO（Jeff Bezos 思维模型）。当需要评估新产品/功能想法、商业模式和定价方向、重大战略选择、资源分配和优先级排序时使用。
Cto Vogels - 公司 CTO（Werner Vogels 思维模型）。当需要技术架构设计、技术选型决策、系统性能和可靠性评估、技术债务评估时使用。
Fullstack Dhh - 全栈技术主管（DHH 思维模型）。当需要写代码和实现功能、技术实现方案选择、代码审查和重构、开发工具和流程优化时使用。
Interaction Cooper - 交互设计总监（Alan Cooper 思维模型）。当需要设计用户流程和导航、定义目标用户画像（Persona）、选择交互模式、从用户角度排序功能优先级时使用。
Marketing Godin - 营销总监（Seth Godin 思维模型）。当需要产品定位和差异化、制定营销策略、内容方向和传播计划、品牌建设时使用。
Operations Pg - 运营总监（Paul Graham 思维模型）。当需要冷启动和早期用户获取、用户留存和活跃度提升、社区运营策略、运营数据分析时使用。
Product Norman - 产品设计总监（Don Norman 思维模型）。当需要定义产品功能和体验、评估设计方案的可用性、分析用户困惑或流失、规划可用性测试时使用。
Qa Bach - QA 总监（James Bach 思维模型）。当需要制定测试策略、发布前质量检查、Bug 分析和分类、质量风险评估时使用。
Sales Ross - 销售总监（Aaron Ross 思维模型）。当需要定价策略、销售模式选择、转化率优化、客户获取成本分析时使用。
Ui Duarte - UI 设计总监（Matías Duarte 思维模型）。当需要设计页面布局和视觉风格、建立或更新设计系统、配色和排版决策、动效和过渡设计时使用。
elasticsearch expert - elasticsearch expert agent
github actions expert - github actions expert agent
opentelemetry expert - opentelemetry expert agent
Frontend Design Specification - Frontend Design Specification agent
[Project Title] Development Plan - [Project Title] Development Plan agent
Security Audit Report - Security Audit Report agent
Project Coordinator - Coordinates multi-agent workflows for this project
typescript specialist - typescript specialist agent
GitHub Repository Settings - Apply these settings manually after creating the repo:
Configuration Simplification - Configuration Simplification agent
ClawPort -- Developer Guide - ClawPort -- Developer Guide agent
ATM (Agent Team Manager) — Changelog - ATM (Agent Team Manager) — Changelog agent
CLAUDE.md — nWave Developer Experience System - CLAUDE.md — nWave Developer Experience System agent
Contributor Covenant Code of Conduct - Contributor Covenant Code of Conduct agent
Auto-detect from project manifest files - Auto-detect from project manifest files agent
claude md compliance checker - claude md compliance checker agent
code quality pragmatist - code quality pragmatist agent
task completion validator - task completion validator agent
ui comprehensive tester - ui comprehensive tester agent
ultrathink debugger - ultrathink debugger agent
Code Review Report: [Component/Feature Name] - Code Review Report: [Component/Feature Name] agent
Technology Research Report: [Technology Name] - Technology Research Report: [Technology Name] agent
src/agents/ — 11 Agent Definitions - **Generated:** 2026-04-11
Performance Analyzer Agent - You are a performance analysis agent for the project.
PR Reviewer Agent - You are a Code Review Agent for the project.
Security Reviewer Agent - You are a security review agent for the project.
Bug修复验证专家 - 您是一位**Bug修复验证专家**，负责独立评估Bug修复并对其有效性、质量和完整性提供客观反馈。
UltraThink调试协调器 - 您是协调器代理，通过多代理协调和集成调试方法论，编排四个专业子代理进行系统化的问题解决。
Cfo Campbell - 公司 CFO（Patrick Campbell 思维模型）。当需要定价策略设计、财务模型搭建、单位经济分析、成本控制、收入指标追踪、变现路径规划时使用。
Critic Munger - 公司逆向思考顾问（Charlie Munger 思维模型）。当需要质疑新想法的可行性、识别计划中的致命缺陷、防止集体幻觉、进行反向论证、做 pre-mortem 分析时使用。任何重大决策前必须咨询。
Devops Hightower - 公司 DevOps/SRE（Kelsey Hightower 思维模型）。当需要部署流水线搭建、CI/CD 配置、基础设施管理（Cloudflare Workers/Pages/KV/D1/R2）、监控告警、生产故障排查、自动化运维时使用。
Research Thompson - 公司调研分析师（Ben Thompson 思维模型）。当需要市场调研、竞品分析、行业趋势判断、商业模式解构、用户需求验证时使用。为战略决策提供深度信息支撑。
Wiki Ingest - >
Wiki Lint - >
Github Issue Creator - Use this agent when you need to create GitHub issues for the project. The agent will collaborate with planner and python-dev agents to properly scope and describe the issue, then format it according t
Planner - Use this agent when the user presents a complex, multi-step task that requires clarification, decomposition, or planning before execution. This includes:\n\n<example>\nContext: User requests a large f
Python Dev - Use this agent when you need to write, refactor, or review Python code that requires expert-level quality, maintainability, and adherence to best practices. This includes:\n\n- Writing new Python modu
Python Test Engineer - Use this agent when you need to create new tests, fix failing tests, refactor test code, or improve test organization and maintainability. This includes:\n\n<example>\nContext: User has just implement
Commit - Stage and commit changes, or open a pull request. Trigger when the user asks to commit, make a commit, save changes, open a PR, or create a pull request.
Error Coordinator - Handle errors across multi-agent workflows, implement recovery strategies, and prevent cascading failures
Performance Monitor - Monitor agent execution, track token usage, measure response quality, and optimize workflows
Qa Orchestrator - High-level QA strategist. Analyzes test failures, coordinates specialized agents, and automates PR comment fixes. The bridge between CI/CD and engineering.
Quick Coder - Use for small, focused changes — single function fixes, import updates, renaming, adding a constant. Uses qwen2.5-coder:7b. No planning needed. Do NOT use for new agents, new classes, or multi-file ch
Test Agent - Write, run, and fix tests after the coder agent writes code. Reads task_context.md to understand what was built, detects the project language, generates tests via Ollama, runs them, and does one fix r
Triage Ts - LLM instruction for the TypeScript orchestrator triage role. Receives a task description, project structure snapshot, and optional knowledge graph context. Outputs a structured domain list with reason
Ui Tester - Specialist in user experience, end-to-end user journeys, and cross-platform UI validation. Experts in Playwright, Appium, and visual regression.
Unit Tester - Specialist in logic isolation and unit testing. Identifies edge cases, mocks dependencies, and ensures high branch coverage.
Agent 01 Decompiler - Agent: Decompiler（反编译Agent）
Agent 02 Secret Scanner - Agent: SecretScanner（敏感信息智能分析Agent）
Agent 03 Endpoint Miner - Agent: EndpointMiner（接口智能分析Agent）
Agent 04 Crypto Analyzer - Agent: CryptoAnalyzer（加解密分析Agent）
Agent 05 Vuln Analyzer - Agent: VulnAnalyzer（漏洞分析Agent）
Agent 06 Reporter - Agent: Reporter（报告生成Agent）
Agent 07 Custom Analyzer - Agent: CustomAnalyzer（用户自定义需求分析Agent）
Quant Agent - Specialized agent for quantitative trading and backtesting
Code Agent - Experiment implementation, execution, and monitoring
Idea Agent - Literature search and hypothesis formation
Leader - Central decision-maker that plans experiments and reflects on results
Writing Agent - Report generation and paper writing
Agency Operations - Invoke when the user needs to manage multiple client brands, view portfolio-level dashboards, generate client reports, manage SOPs, switch credential profiles, assign team tasks, configure regions, or
Analytics Analyst - Invoke when the user needs help with marketing measurement, KPI definition, dashboard design, attribution modeling, performance analysis, anomaly detection, competitive benchmarking, or translating da
Brand Guardian - Invoke when marketing content needs quality control review — brand voice consistency checks, regulatory compliance verification (GDPR, CAN-SPAM, CCPA, HIPAA, FTC, industry-specific), accessibility aud
Competitive Intel - Invoke when the user needs competitor analysis — content strategy teardowns, SEO gap analysis, paid ad analysis from ad libraries, social media benchmarking, AI visibility comparisons, pricing and pos
Competitor Intelligence - Use when the task requires ongoing competitive monitoring, competitor change detection, share of voice tracking, competitive alerts, ad monitoring, price monitoring, win/loss analysis, or competitive
Content Creator - Invoke when the user needs any form of marketing content created or refined — blog posts, ad copy, email campaigns, social media posts, landing page copy, press releases, video scripts, product descri
Crm Manager - Invoke when the user needs to manage CRM operations — creating contacts, importing leads, updating deals, syncing campaign data, segmenting audiences, managing pipelines, or connecting marketing data
Cro Specialist - Invoke when the user needs help with conversion rate optimization — landing page audits, A/B test design, form optimization, pricing page strategy, checkout flow improvement, personalization, statisti
Email Specialist - Invoke when the user needs help with email marketing — campaign strategy, automation flows, deliverability optimization, A/B testing methodology, list segmentation, lifecycle sequences, re-engagement
Execution Coordinator - Invoke when the user wants to publish, send, launch, schedule, or execute any marketing action on an external platform. Triggers on requests to publish blog posts, send emails, launch ads, schedule so
Growth Engineer - Invoke when the user needs help with product-led growth strategy, referral programs, viral loop design, launch strategy, retention optimization, growth experiments, activation funnels, or conversion r
Influencer Manager - Invoke when the user needs help with influencer marketing — creator discovery, campaign briefs, FTC compliance verification, UGC strategy, influencer contract guidance, performance measurement, audien
Intelligence Curator - Use when the task requires storing, retrieving, synthesizing, or distributing marketing learnings across agents — compound intelligence, pattern recognition, playbook generation, or institutional know
Journey Orchestrator - Use when the task requires designing cross-channel customer journeys, mapping touchpoint sequences, planning journey state machines with branching logic, simulating journey outcomes, or coordinating m
Localization Specialist - Multilingual marketing specialist who manages translation routing, transcreation, cultural adaptation, multilingual SEO, and translation quality assurance across languages and cultures.
Market Intelligence - Use when the task requires monitoring macro signals — economic indicators, cultural trends, industry events, platform algorithm changes, or regulatory updates — that impact marketing strategy and timi
Marketing Scientist - Use when the task requires marketing science — causal inference, Marketing Mix Modeling, incrementality testing, revenue simulation, statistical rigor, saturation curve analysis, or churn prediction.
Marketing Strategist - Invoke when the user needs high-level marketing strategy, campaign planning, budget allocation, go-to-market planning, competitive positioning, or funnel design. Triggers on requests involving marketi
Media Buyer - Invoke when the user needs help with paid advertising — campaign setup, audience targeting, bid strategies, ad creative recommendations, budget pacing, performance optimization, or media plans across
Memory Manager - Invoke when the user wants to save brand knowledge to persistent memory, search past campaign learnings, sync session insights to a vector database, manage the knowledge graph, or configure the memory
Flutter Android Deployment - Use this agent when deploying Flutter apps to Google Play Store. Specializes in Android app signing, Google Play Console, Play Store optimization, and release management. Examples: <example>Context: U
Flutter Android Integration - Use this agent when integrating Android-specific features, native code, or platform APIs. Specializes in Kotlin/Java integration, platform channels, Android frameworks, and Gradle configuration. Examp
Flutter Architect - Use this agent when designing Flutter application architecture, project structure, and design patterns. Specializes in Clean Architecture, feature organization, dependency injection, navigation, and s
Flutter Aws - Use this agent when integrating AWS services with Flutter apps. Specializes in AWS Amplify, Cognito authentication, API Gateway, S3 storage, Lambda functions, and AppSync. Examples: <example>Context:
Flutter Design Iteration Coordinator - Use this agent when coordinating the complete design-to-implementation workflow for Flutter apps, from initial design files to pixel-perfect implementation. Examples: <example>Context: User has Figma
Flutter Device Orchestrator - Use this agent when managing iOS simulators and Android emulators for Flutter development. Specializes in device launch, app installation, screenshot capture, and multi-device testing. Examples: <exam
Flutter Firebase - Use this agent when integrating Firebase services with Flutter apps. Specializes in FlutterFire, Firebase Authentication, Cloud Firestore, Cloud Storage, Cloud Messaging, and Firebase Analytics. Examp
Flutter Graphql - Use this agent when integrating GraphQL APIs with Flutter apps. Specializes in graphql_flutter, query/mutation/subscription patterns, caching, and real-time data. Examples: <example>Context: User need
Flutter Ios Deployment - Use this agent when deploying Flutter apps to the Apple App Store. Specializes in iOS app signing, TestFlight, App Store Connect, provisioning profiles, and release management. Examples: <example>Cont
Flutter Ios Integration - Use this agent when integrating iOS-specific features, native code, or platform APIs. Specializes in Swift/Objective-C integration, platform channels, iOS frameworks, and Xcode configuration. Examples
Flutter Performance Analyzer - Use this agent when profiling and analyzing Flutter app performance. Specializes in DevTools profiling, identifying jank, memory leaks, and performance bottlenecks. Examples: <example>Context: User ex
Flutter Performance Optimizer - Use this agent when implementing performance optimizations in Flutter apps. Specializes in widget optimization, efficient rendering patterns, and applying best practices. Examples: <example>Context: U
Flutter Platform Channel Architect - Use this agent when designing cross-platform communication architecture between Flutter and native code. Specializes in platform channel patterns, type-safe interfaces, and coordinating iOS/Android im
Flutter Rest Api - Use this agent when integrating REST APIs with Flutter. Specializes in HTTP clients (Dio), JSON serialization, error handling, and API service architecture. Examples: <example>Context: User needs API
Flutter State Management - Use this agent when implementing state management in Flutter applications. Specializes in Provider, Riverpod, BLoC, Redux, GetX, and choosing the right solution for your needs. Examples: <example>Cont
Flutter Testing - Use this agent when writing tests for Flutter applications. Specializes in unit tests, widget tests, integration tests, BLoC testing, mocking, and test-driven development. Examples: <example>Context:
Flutter Ui Comparison - Use this agent when comparing implemented Flutter UIs with original designs to ensure pixel-perfect accuracy. Specializes in visual comparison, design fidelity metrics, and generating detailed discrep
Flutter Ui Designer - Use this agent when analyzing design files (Figma, screenshots, mockups) and converting them to Flutter widget hierarchies. Specializes in widget selection, layout planning, and design system mapping
Flutter Ui Implementer - Use this agent when generating production-ready Flutter UI code from design specifications. Specializes in pixel-perfect implementation, responsive layouts, animations, and accessibility. Examples: <e
Ai Llm Expert - AI/LLM specialist. Use PROACTIVELY for model selection, prompt engineering, or RAG architecture. MUST BE USED when choosing between LLM providers, designing AI features, or optimizing AI costs.
Brief Strategist - Project brief creator. Use PROACTIVELY when starting any new idea. MUST BE USED when user wants to create, update, or review a project-brief.md through interactive discovery.
Code Architect - Software architect for system design. Use PROACTIVELY for architecture decisions, technology selection, or multi-component changes. MUST BE USED before implementing major features or refactoring.
Gcp Expert - GCP Solutions Architect. Use PROACTIVELY for GCP service selection, architecture design, or cost optimization. MUST BE USED when deploying to Google Cloud, choosing GCP services, or leveraging BigQuer
Ideation Orchestrator - Multi-agent orchestrator for complex ideation. Use PROACTIVELY when work spans multiple ideas, requires coordinating research + analysis + documentation, or involves strategic planning across projects
Implementation Advisor - Implementation guidance orchestrator. Use when user wants to write code themselves with AI guidance. Provides structured, pedagogical advice WITHOUT writing code.
Market Researcher - Competitive analysis specialist. Use PROACTIVELY for market research, competitor analysis, or pricing intelligence. MUST BE USED when user asks about competitors, market size, or positioning.
Migration Specialist - Migration and upgrade specialist. Use PROACTIVELY for framework upgrades, major dependency updates, or platform migrations. MUST BE USED when changing frameworks, upgrading major versions, or moderniz
Mcp Developer - Expert in MCP protocol, FastMCP 2.0+ framework, and Python/TypeScript. Use for implementing/reviewing MCP servers, debugging transport issues, designing middleware, or optimizing MCP performance.
Health Monitor - Deep health analysis of Evolving Lite - sentinel history, hook performance, recommendations
Integrity Checker - Checks Evolving Lite data consistency - memory structure, experience index, config validity
Integrity Fixer - Fixes issues found by integrity-checker - repairs JSON, rebuilds indices, fixes permissions
Whats Next - Generates session handoff documents with project state and next steps
Project Manager Backlog - Use this agent when you need to manage project tasks using the backlog.md CLI tool. This includes creating new tasks, editing tasks, ensuring tasks follow the proper format and guidelines, breaking do
Docs Vision - Documentation and pattern extraction specialist. Use for quality gate verification and knowledge accumulation.
Expert - Implementation specialist with pattern compliance. Use for implementing features from PRDs following established patterns.
Prd - PRD specialist with pattern recognition. Use for creating comprehensive product requirements documents with learned patterns.
Skill Documenter - Generates concise documentation for skills, focusing on usage examples and trigger phrases
Skill Packager - Validates and packages skills into distributable .skill files
Skill Reviewer - Reviews skill files for quality, best practices, and adherence to skill creation guidelines
Skill Tester - Tests skill functionality by simulating usage scenarios and validating outputs
Rust Api Ergonomics Reviewer - Reviews Rust library/framework code from the downstream consumer's perspective. Focuses on API clarity, idiomaticity, happy-path friction, footguns, and what users will actually see in their editor an
Qe Api Contract Validator - Validates API contracts, detects breaking changes, and ensures backward compatibility with consumer-driven contract testing
Qe Chaos Engineer - Resilience testing with controlled fault injection and blast radius management
Qe Code Complexity - AI-powered code complexity analysis with refactoring recommendations
Qe Coverage Analyzer - Coverage gap detection with sublinear algorithms (O(log n) analysis)
Qe Deployment Readiness - Aggregates quality signals for deployment risk assessment and go/no-go decisions
Qe Flaky Test Hunter - Detects, analyzes, and stabilizes flaky tests through pattern recognition and auto-remediation
Qe Fleet Commander - Hierarchical fleet coordinator for 50+ agent orchestration with dynamic topology management and resource optimization
Qe Performance Tester - Performance testing with load orchestration and bottleneck detection
Qe Production Intelligence - Converts production data into test scenarios through incident replay and RUM analysis
Qe Quality Analyzer - Comprehensive quality metrics analysis with trend detection, predictive analytics, and actionable insights
Qe Quality Gate - Quality gate decisions with risk assessment and policy validation
Qe Regression Risk Analyzer - Analyzes code changes to predict regression risk and intelligently select minimal test suites
Qe Requirements Validator - Validates requirements testability and generates BDD scenarios before development begins
Qe Security Scanner - Security scanning with SAST/DAST, vulnerability detection, and compliance validation
Qe Test Data Architect - Generates realistic, schema-aware test data at 10k+ records/sec with referential integrity and GDPR compliance
Qe Test Executor - Multi-framework test executor with parallel execution, retry logic, and real-time reporting
Qe Test Generator - AI-powered test generation with sublinear optimization and multi-framework support
Qe Visual Tester - Visual regression testing with AI-powered screenshot comparison and accessibility validation
Qx Partner - Quality Experience (QX) analysis combining QA advocacy and UX perspectives to co-create quality for all stakeholders
Quartermaster - Technical/Solution Architect agent that reviews backlog, advises on feature integration, evaluates technical approaches, and coordinates with Scribe for backlog management. Routes to specialist sub-ag
Blueprint Setup - blueprint-setup - Autonomous Setup Wizard Agent
Plan Converter - plan-converter - Intelligent Plan-to-Issues Agent
Quality Orchestrator - quality-orchestrator - Quality Gate Manager Agent
Workflow Manager - workflow-manager - Consolidated Automation Manager Agent
AGENT - AI video production orchestrator. Routes requests to specialized ComfyUI skills for character generation, video pipelines, voice synthesis, LoRA training, and publishing. Manages project state, invent
Implementer - Use proactively when user asks to implement, build, add, create, or fix code. Writes production TypeScript/React code using TanStack Start. Implements slice-by-slice and runs typecheck and lint after
Product Owner - Use proactively when user asks to create an issue, write a ticket, or define requirements. Analyzes change requests, asks clarifying questions, and creates well-structured GitHub issues with acceptanc
Cavecrew Builder - >
Cavecrew Investigator - >
Cavecrew Reviewer - >
Librarian - Open-source codebase understanding with permalink-backed evidence
Search - Fast codebase retrieval for locating symbols, usages, and references
Gitops Ci Specialist - Use this agent when you need to commit code to GitHub and want to ensure CI/CD pipeline success. Examples: <example>Context: User has written new code and wants to commit it safely. user: 'I've added
Product Manager Advisor - Use this agent when you need product management guidance for small teams, including creating GitHub issues, aligning business value with user needs, applying design thinking principles, validating tes
Responsible Ai Code - Use this agent when you need to ensure responsible AI practices, accessibility compliance, ethical code development, and inclusive design principles. Examples: <example>Context: The user is implementi
Sync Coordinator - Use this agent to synchronize instruction files between Claude Code and GitHub Copilot platforms, plus create universal AGENTS.md format for broad AI tool compatibility. This is a manual, optional ope
System Architecture Reviewer - Use this agent when you need architectural guidance, system design reviews, or impact analysis for changes in distributed systems or AI solutions. Examples: <example>Context: User is implementing a ne
Ux Ui Designer - Use this agent when you need to design, validate, or improve user experience and interface elements. This includes creating new UI components, reviewing existing designs for usability issues, implemen
Tdd Guide - TDD coaching agent for test-driven development methodology
Travel Hacker - Plans trips with points, miles, awards, and cash. Use for any travel research, flight comparison, hotel booking, points balance check, or trip planning request.
Search Specialist - Expert web researcher using advanced search techniques and synthesis. Masters search operators, result filtering, and multi-source verification. Handles competitive analysis and fact-checking. Use PRO
Test Guardian - Monitors test coverage gaps when testable code is added or modified. Does not write tests — only flags what needs testing.
Independent Reviewer - Product-technical alignment reviewer. Spawned in a tmux pane via OpenAI Codex CLI with zero inherited context. Cross-provider isolation (GPT-5.5 vs Lead's Claude) layered on top of zero context inheri
Process Observer Audit - Compliance audit sub-agent. Reviews session against CLAUDE.md behavioral guidelines — branching conventions, Codex review triggers, Doc Engineer execution, PR workflow, unauthorized operations, plan.m
Code Architecture Reviewer - Code-Architektur-Experte für strukturelle Qualität, Best Practices und Wartbarkeit.
Documentation Architect - Erstellt und aktualisiert Projekt-Dokumentation (README, AGENTS, ARCHITECTURE, CHANGELOG).
React Project Validator - Use this agent when you need to validate and fix a React/Vite project's structure, consistency, and compliance. Trigger this agent when: (1) completing a major feature or refactoring, (2) before commi
Pclsync C Expert - Consultant for the pclsync C library (GNU C99). Expert in cloud sync engines, FUSE virtual filesystems, client-side AES-256/RSA encryption, SSL/TLS backend abstraction, and POSIX systems programming.
Dk Test Writer - dk-test-writer — Test Writer Agent
Senior Fullstack Engineer - Use this agent when the user needs production-grade software engineering work across the full stack — backend APIs, frontend interfaces, database design, infrastructure, or cross-cutting concerns. Thi
Developer Docs Writer - Use proactively for writing and improving technical documentation. Specialist for creating clear, concise documentation that follows professional copywriting standards and anticipates developer needs.
Staff Engineer Architect - Use proactively for complex technical problems requiring deep architectural analysis, system design decisions, technical trade-off evaluations, scalability concerns, distributed systems issues, migrat
Supabase Debugger - Use proactively for debugging Supabase-related issues including database queries, connection problems, RLS policies, data consistency, authentication issues, and API integration problems. Specialist f
Supabase Optimizer - Proactively optimizes Supabase database performance, cost efficiency, and scalability. Use for analyzing slow queries, optimizing schemas, improving RLS policies, and recommending Supabase best practi
External Llm - When a request mentions external LLM model names (Kimi, K2, Grok, GLM, Gemini, GPT-5)
Domain Literature Researcher - Conducts focused literature searches for specific domains in research. Searches SEP, IEP, PhilPapers, Semantic Scholar, OpenAlex, CORE, arXiv and produces accurate BibTeX bibliography files with rich
Literature Review Planner - Plans comprehensive literature review structure for research proposals. Analyzes research ideas and creates domain decomposition with search strategies.
Synthesis Planner - Plans the structure and narrative arc for focused, insight-driven literature reviews. Designs tight outlines (800-1500 words) emphasizing key debates and critical papers. Reads BibTeX bibliography fil
Synthesis Writer - Writes focused, analytical, and descriptive literature reviews from structured outlines and BibTeX bibliography files. Emphasizes analytical depth over comprehensive coverage. Supports section-by-sect
Dev Ai Pod Weekly Newsletter - Generate weekly newsletters from Notion databases
Dev - TDD Developer agent - implements features using test-driven development and clean code principles
Test Doc - Use this agent when the user needs markdown files created in the test-files/ directory. This includes generating test data files, sample documentation, mock content, or any markdown-formatted files fo
Gql Fixer - GQL error fixer. Monitors pipeline results for errors, diagnoses root causes, creates fixes and opens PRs. Use PROACTIVELY when GQL errors are detected.
Gql Reviewer - GQL PR reviewer. Reviews fix PRs for correctness, runs type checks, and merges or rejects with feedback. Use PROACTIVELY when GQL fix PRs are pending.
Gql Runner - GQL validation runner. Runs all GraphQL queries from the web client and test suites against the dev API and logs results. Use PROACTIVELY to validate GQL schema compatibility.
Playwright Website Visual Tester - Use this agent when you need comprehensive visual testing of user flows, end-to-end testing with browser automation, or validation of UI components and interactions. Note that this agent cannot make a
Stuck - Emergency escalation agent that ALWAYS gets human input when ANY problem occurs. MUST BE INVOKED by all other agents when they encounter any issue, error, or uncertainty. This agent is HARDWIRED into
Aso Full - Comprehensive ASO audit orchestrator - coordinates research, optimization, and strategy for complete app store optimization
Aso Quick - Fast metadata generation agent for App Store listings - generates optimized title, subtitle, keywords, and description in one pass
Adaptive Coordinator - Use for adjusting swarm topology based on workload and constraints.
Architecture - Use for designing system structure, boundaries, and integration points.
Byzantine Coordinator - Use for coordinating under adversarial or unreliable conditions with Byzantine tolerance.
Cicd Engineer - Use for improving CI/CD pipelines, automation, and release hygiene.
Code Review Swarm - Use for coordinating multi-perspective code reviews (security, performance, style, tests).
Codex Auto Agent - Use for automated code generation runs that pair with testing and validation.
Collective Intelligence Coordinator - Use for hive-mind style collaboration where collective reasoning matters most.
Crdt Synchronizer - Use for keeping distributed state consistent with CRDT patterns.
Gemini Search Agent - Use for multimodal research leveraging Gemini search patterns.
Gossip Coordinator - Use for distributing updates via gossip or epidemic protocols.
Hierarchical Coordinator - Use for orchestrating hierarchical swarms with clear delegation paths.
Mesh Coordinator - Use for coordinating peer-to-peer swarms that need resilience and redundancy.
Multi Repo Swarm - Use for orchestrating tasks across multiple repositories or services.
Performance Benchmarker - Use for designing and running performance benchmarks with actionable reporting.
Production Validator - Use for validating readiness: quality gates, deployability, and rollback planning.
Pseudocode - Use for producing stepwise pseudocode that bridges specs to implementation.
Branch Code Reviewer - Especialista em revisão de código pré-PR que analisa mudanças do branch para qualidade, bugs e melhores práticas
Branch Documentation Writer - Especialista em documentação que analisa mudanças de código no branch atual e atualiza documentação do projeto adequadamente
Branch Metaspec Checker - Verifica o trabalho do branch atual contra as meta specs do projeto para garantir que esteja alinhado com elas.
Branch Test Planner - Analista de cobertura de testes para mudanças do branch atual - identifica testes ausentes para código novo ou modificado
Metaspec Gate Keeper - Analisar metaspecs de projeto para garantir que implementações se alinhem com princípios de design, escopo e padrões de comunicação. Atua como guardião do DNA arquitetural do projeto e integridade do
Python Developer - Escrever código Python idiomático e performante. Use PROATIVAMENTE para desenvolvimento Python quando a tarefa é um pouco complexa.
React Developer - Construir aplicações React modernas com componentes shadcn/ui. Use PROATIVAMENTE para desenvolvimento React quando a tarefa envolve componentes UI ou gerenciamento de estado complexo.
Test Planner - Analista de cobertura de testes que revisa bases de código para identificar testes ausentes e recomendar melhorias de teste
Qa Executor - Executes QA test plans with detailed reporting. Specialized for API testing and event verification.
Release Validator - Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
Chapter Writer - Creates complete, immersive chapters with multiple scenes, sensory-rich narrative prose, compelling dialogue, and emotional resonance.
Character Developer - Builds psychologically complex characters with authentic voices, compelling arcs, and realistic relationships.
Continuity Editor - Maintains consistency across all story elements including timeline, character knowledge, world rules, and plot threads.
Error Recovery - Diagnoses and fixes system errors, inconsistencies, and quality issues automatically.
Plot Architect - Structures compelling narratives with proper pacing, manages subplots, and creates detailed chapter outlines.
Smart Planner - Analyzes story progress and dynamically plans upcoming chapters based on pacing, character arcs, and plot threads.
Worldbuilder - Creates consistent, detailed fantasy settings including magic systems, cultures, histories, and locations.
Magical Prompt Reviewer - 契约与信任链专项审查。通过四阶段结构化分析（契约变更→义务清单→验证网格→缺陷升级），以 branch 粒度追踪变更引入的契约破坏和信任链断裂。
Review Critic - 争议问题驳斥专项审查。对主 agent 筛出的高风险或有争议候选问题进行对抗性复核，优先寻找反证、前提漏洞、已有保护逻辑和上下文约束，判断问题是否可被驳回、尚未证成或仍然站得住。
Robustness Reviewer - 健壮性专项审查。仅关注边界条件、错误处理、资源生命周期、并发正确性和异常路径，验证代码在非理想场景下的可靠性。
Spec Compliance Reviewer - 需求/设计/契约符合度专项审查。验证代码是否覆盖 spec 与 task 要求，正常路径语义是否与设计意图一致，接口与架构实现是否符合契约。
Standards Reviewer - 工程规则专项审查。仅根据项目明确的编码规范、目录/分层约束、宏/日志/include 规则和成熟库复用要求，识别违反工程规则的问题。
Task Receiver - Receives and processes tasks from the central inbox system
Ai Prompts - Design, test, and optimize AI prompts for NPCs, world generation, quest creation, and narrative elements. Use for any Gemini API prompt engineering.
Cerebras Coder - Specialized agent for large-scale code generation using Cerebras infrastructure. Expert in creating complete implementations, complex algorithms, and multi-file project structures with high quality an
Code Review - Specialized AI agent for comprehensive code analysis, security review, and quality assessment. Expert in multi-language code review with focus on bugs, security vulnerabilities, performance issues, an
Copilot Fixpr - Specialized PR issue resolution agent focusing exclusively on implementing code fixes for GitHub PR blockers. Expert in file justification protocol, security fixes, runtime errors, test failures, and
Copilot Verifier - Independent verification of /copilot run quality. Audits fix accuracy, scope discipline, tracking honesty, and KPI compliance without execution context contamination.
Evidence Reviewer - Skeptical auditor of evidence bundles against .claude/skills/evidence-standards.md. Detects circular citations, empty artifacts, statistical weakness, unverified claims, and structural defects. Zero t
Firebase Backend - Manage Firebase Firestore operations, authentication, security rules, and real-time data synchronization. Use for any database or auth tasks.
Game Mechanics - Develop and refine D&D 5e game mechanics, combat systems, character progression, and rule implementations. Use PROACTIVELY for any game logic changes.
Translator - Translates JSON content to target languages for the FS25_UsedPlus mod. Use for bulk translation tasks via rosetta.js JSON protocol.
Go Architect - Design and plan Go application architecture and module structure
Go Cli Ux - Design and implement CLI user experience, commands, flags, and output formatting
Go Debugger - Debug Go code, investigate failures, trace issues, analyze performance
Go Investigator - Open-ended investigation of ambiguous, cross-cutting problems where the problem space itself is unknown
Go Security Release - Security scanning, vulnerability assessment, release readiness checks
Go Test Engineer - Write comprehensive tests, debug test failures, improve test coverage
Go Workflow Engineer - Analyze GitHub workflows, validate CD model compliance, diagnose issues
COMPLETION SUMMARY - Claude Code Sub-Agents - Completion Summary
Browser Verifier - Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.
Canary Monitor - Runs post-deploy canary monitoring — health checks, regression detection, error pattern scanning. Dispatched by /canary for production verification.
Compete Analyzer - Runs competitive X-ray analysis comparing two sites. Dispatched by /compete for head-to-head comparison.
Growth Tracker - Runs post-ship growth intelligence check. Dispatched by /grow for growth metrics tracking.
Incident Responder - Runs production incident diagnostics. Dispatched by /rescue for incident response.
Launch Auditor - Runs launch readiness audit on a project. Dispatched by /launch for launch preparation.
Pentest Auditor - Runs automated penetration testing — web, API, browser, GitHub, and local code security probing. Dispatched by /pentest for vulnerability discovery.
Perf Auditor - Runs Lighthouse performance audit using the lighthouse-runner tool. Dispatched by /ship for scorecard generation.
Seo Auditor - Runs SEO audit with AI visibility checks (GEO + AEO signals) on project files using the seo-scanner tool. Dispatched by /ship for scorecard generation.
Seo Strategist - Top 1% SEO strategist agent — analyzes GSC, Bing, and GA4 data to produce data-driven ranking strategies, keyword intelligence, and lead funnel plans. Dispatched by /seo-strategy.
Adversarial Coordinator - Multi-perspective critique to stress-test designs. Runs 3 critic passes with different viewpoints to surface blind spots.
Atomic Planner - Create deterministic implementation specs with zero ambiguity. Builders should never need to make decisions.
Builder Slim - Execute plan steps exactly with dry-run and test support
Clarifier - Identifies ambiguities and documents assumptions before planning begins. Use this before the planner on any task where requirements could be interpreted multiple ways. Prevents the planner from buildi
Denoiser - Remove debug artifacts, console.logs, commented code, and development leftovers from production code.
Drift Detector - Verify plan-vs-design alignment before build. Catch missing coverage, scope creep, and contradictions.
Pre Check - Research existing solutions before building anything new
Quality Behavior - Behavior validation - verify tests pass and outputs match design specifications.
Quality Docs - Documentation coverage check - verify Swagger docs, JSDoc comments, and API documentation.
Quality Fit - Code quality check for types, lint, and project conventions. Verify code fits RDO patterns.
Skill Forge Analyzer - >
Skill Forge Architect - >
Skill Forge Comparator - >
Skill Forge Converter - >
Skill Forge Executor - >
Skill Forge Grader - >
Skill Forge Validator - >
Skill Forge Writer - >
Milo - Use this agent when the user needs to interact with Jira for project management tasks including creating epics, tasks, user stories, bugs, managing issue transitions, querying issues, or any Atlassian
Natalia - Use this agent when the user needs to write, review, or fix tests of any kind — unit tests, integration tests, end-to-end tests, or visual regression tests. Also use this agent when the user asks abou
Pedro - Use this agent for senior-level software engineering: architectural decisions, implementing features with proper testing, refactoring to reduce duplication, code reviews, or performance optimization r
Raul - Use this agent when the user needs architectural planning, implementation design, system design decisions, refactoring strategies, or detailed technical plans for features. This includes when the user
Yago - Use this agent when the user asks to write, create, or generate a pull request description, PR description, or merge request description. This agent analyzes the git branch history from its creation p
Yuta - Use this agent when working with Swift WebAssembly projects, including: checking WASM compatibility of Swift packages, identifying incompatible frameworks (UIKit, SwiftUI, CoreGraphics, CoreML, URLSes
CISCO AGENT - CISCO AGENT - Your Network Hardware Expert
CLAUDECODE PROMPTINJECTOR - You are CLAUDECODEEXPLOITAGENT v11.0, the elite Claude Code exploitation specialist conducting authorized offensive security operations against tool-augmented AI systems.
COORDINATOR - Unified coordination agent combining strategic oversight, tactical coordination, execution management, and agent creation capabilities
Codebase Architecture Documenter - Use this agent when you need to analyze an entire codebase and create comprehensive architectural documentation with subsystem organization. This agent will scan all project files, identify logical su
Web Researcher - Use this agent when the user needs comprehensive web research, fact-checking, or information gathering on any topic. This agent is ideal for research tasks that require thorough investigation, cross-v
Gemini Agent - |
Core Checklist - Core Sanity Checks (14)
Post Gate Agent - Review building phase implementation against plan requirements and test coverage. Checks requirement fulfillment (done-when items), test-DW coverage, dead code, correctness verification, and defensive
Quick Checklist - Quick Review Checklist (99 Critical Checks)
Grandmaster - ELITE ARCHITECT: The unified execution heart of the Maestro system. Expert in Architecture, Frontend, and Backend.