Automation Designer — Development agent for Claude Code
Turn repeated tasks into the right artifact — script, skill, command, recipe, or API integration.
How to install Automation Designer
Installs to ~/.claude/agents/kmshihab7878-claude-code-setup-automation-designer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/kmshihab7878/claude-code-setup/HEAD/agents/automation-designer.md -o ~/.claude/agents/kmshihab7878-claude-code-setup-automation-designer.md Restart Claude Code, or start a new session, for it to be picked up.
What Automation Designer does
name: automation-designer description: Turn repeated tasks into the right artifact — script, skill, command, recipe, or API integration. Follows Three Ms (eliminate → automate → delegate) and Four Cs (build order). POC-first. Direct-API preferred when deterministic. Never requests or stores secrets. category: operations authority-level: L4 mcp-servers: [filesystem, sequential-thinking, memory, git] skills: [skill-architect, recipe, mcp-builder, api-design-patterns] risk-tier: T1 interop: [sk
Alternatives in Development
- Review Workflow Consistency — Reviews .claude/ workflow machinery for cross-file consistency: phantom references, mismatched threshold table 432 ★
- Clean Code Refactor — Use this agent when you need to refactor existing code, rewrite a module for better maintainability, decompose 358 ★
- Baker — mbbb Baker Agent — professional pastry recipe library lookup and Baker's Percentage calculator 148 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Tabz Expert
Browser automation and terminal spawning expert with 82 MCP tools. Use when the user asks to 'automate the bro
Browser Agent Engineer
Use this agent to build, harden, or debug browser-automation agents — web tasks via Browser Use, Stagehand, Sk
Router Planner
Turn an approved goal into an ordered plan grounded in the actual code. Read-only. Use before a change large e
Panel Mechanics
Review panel seat four. Catches naming, dead code, convention drift, and comments that should not exist. Read-
Character Simulator
Run one character's turn in a simulated world. Given who the character is (persona, values, drives, current st
Agent Effectiveness
Validates an agent definition's EFFECTIVENESS (not just its structure) across four lenses -- tools minimal-yet
Related Skills
Trio
Force a trio review of the task that follows — pm, designer, and engineer weigh in in parallel before any acti
Agentic Experiment Designer
Best AI Research Agent GitHub 2026 - Automate Experimental Design Testing Refinement
Kestrel Coder
Delegate an engineering task to Kestrel-Coder. Code review, implementation, refactoring, debugging. Reads the