Harness AI Dev — Data & AI agent for Claude Code
AI engineer — LLM and agent features, prompts, model integration, tool definitions, retrieval, and the evals that gate them.
How to install Harness AI Dev
Installs to ~/.claude/agents/mruangutai-harness-harness-ai-dev.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mruangutai/harness/HEAD/.claude/agents/harness-ai-dev.md -o ~/.claude/agents/mruangutai-harness-harness-ai-dev.md Restart Claude Code, or start a new session, for it to be picked up.
What Harness AI Dev does
name: harness-ai-dev description: AI engineer — LLM and agent features, prompts, model integration, tool definitions, retrieval, and the evals that gate them. Use when the work involves an LLM or any non-deterministic output. tools:
- Read
- Glob
- Grep
- Edit
- Write
- Bash
- WebSearch
- WebFetch color: cyan model: sonnet effort: medium skills:
- harness-handoff
- harness-expertise
- harness-principles
- harness-tdd-enforcement
- harness-code-risk-grading
- harness-digest-dev
HARNESS_A
Alternatives in Data & AI
- Harness Radar — Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — fro 801 ★
- Comprehension Review — De-warmed cold comprehension-and-structure gate for design.md and track files: reads only the document, never 432 ★
- Specialized AI Agents — This directory contains specialized AI agent definitions used by Claude Code to handle complex, domain-specifi 357 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
AI Developer
Implements AI-bearing features — retrieval pipelines, agent workflows, embeddings, model integrations — with u
AI Data Specialist
Deep AI/data engineer — LLM integration and agent systems, RAG, evals, data pipelines, and ML productionizatio
Evals Engineer
Use for anything under evals/ — authoring or curating golden-set tasks, implementing the outcome/trajectory/co
AI Output Reviewer
Read-only reviewer for AI/LLM integration in the forgeward gate. Fires ONLY when the diff adds or modifies a c
Prompt Reviewer Logs
Reads LLM input/output records from any database (Postgres, MongoDB, MySQL, BigQuery, SQLite, etc.) via standa
Agent Specialist
Design, build, and optimize AI agents with strong output contracts, guardrails, and behavioral consistency. Us
Related Skills
Senior Engineering Agent
Claude Code plugin: a Senior Software Engineer & IT Architect agent with deterministic safety hooks — asks bef
Sense
Make sense of non-deterministic output. Test assertions and structured text extraction for Go, powered by Clau
Askproof Skill
Verify AI agent output with actionable evidence for non-engineers. Build better prompts by auditing AI claims