Stats
Actions
Available In
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
Multi-agent coding flywheel — deep planning, parallel execution, guided review gates. The Agentic Coding Flywheel.
Audit the codebase for bugs, security issues, test gaps, and dead code.
Clean up orphaned git worktrees from crashed or stopped sessions.
Check if the codebase has drifted from the implementation plan.
Fast path to apply a targeted fix without running the full flywheel.
Full health check of the codebase and flywheel dependencies.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Manage AI coding CLI accounts with sub-100ms switching. Use when hitting rate limits on Claude Max, GPT Pro, or Gemini Ultra subscriptions and need instant account swapping without browser OAuth.
CASS Memory System (cm) for procedural memory. Use when starting non-trivial tasks, learning from past sessions, building playbooks, or preventing repeated mistakes via trauma guard.
Mine past agent sessions for working prompts, decisions, and patterns. Use when "what did I ask?", "find that prompt", session archaeology, or agent history.
Rebuild CHANGELOG.md files and release histories from git, tags, releases, and issue trackers. Use when writing changelogs, version timelines, or agent-facing project history summaries.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Multi-agent coding flywheel for Claude Code. Implements the Agentic Coding Flywheel: deep planning, parallel execution, and guided review gates — all using Claude Code's native Agent tool, skills, hooks, and MCP servers.
agent-flywheel drives a complete development cycle:
# Install br and bv (example)
brew install br bv
# Start agent-mail
uv run python -m mcp_agent_mail.cli serve-http
claude --plugin-dir ./agent-flywheel
Or install permanently:
# Add to your Claude Code settings
claude settings plugins add ./agent-flywheel
cd mcp-server
npm install
npm run build
# 1. Set up prerequisites
/agent-flywheel:flywheel-setup
# 2. Run the full flywheel
/agent-flywheel:flywheel
# 3. Check status
/agent-flywheel:flywheel-status
| Command | Description |
|---|---|
/agent-flywheel:flywheel | Full flywheel: scan → plan → implement → review |
/agent-flywheel:flywheel-stop | Stop session and reset state |
/agent-flywheel:flywheel-status | Show bead progress, inbox messages, next steps |
/agent-flywheel:flywheel-setup | Check and install prerequisites |
/agent-flywheel:flywheel-cleanup | Remove orphaned git worktrees |
/agent-flywheel:flywheel-swarm | Launch parallel swarm of implementation agents |
/agent-flywheel:flywheel-swarm-status | Check swarm health and agent messages |
/agent-flywheel:flywheel-swarm-stop | Stop all swarm agents |
/agent-flywheel:flywheel-research | Deep research on an external GitHub repo |
/agent-flywheel:flywheel-drift-check | Check if code has drifted from plan |
/agent-flywheel:flywheel-rollback | Roll back a completed bead |
/agent-flywheel:flywheel-fix | Fast-path targeted fix (no full flywheel) |
/agent-flywheel:flywheel-audit | 4-agent codebase audit (bugs/security/tests/dead code) |
/agent-flywheel:flywheel-scan | Targeted scan of specific paths or concerns |
/agent-flywheel:flywheel-refine-skills | Improve all skills from session evidence |
/agent-flywheel:flywheel-refine-skill | Refine a specific skill |
/agent-flywheel:flywheel-tool-feedback | Submit feedback on agent-flywheel behavior |
/agent-flywheel:flywheel-healthcheck | Full dependency and codebase health check |
/agent-flywheel:memory | Search or store CASS long-term memory |
Multi-agent coding flywheel — deep planning, parallel execution, guided review gates. The Agentic Coding Flywheel.
burningportranpx claudepluginhub burningportra/claude-orchestrator --plugin agent-flywheelTask-focused agents for test, review, debug, docs, CI, security, refactoring, research, performance, and search-replace — with teammate and subagent role guidance
laurigatesMulti-agent orchestration for code that matters.
ShankarKakumaniPortable Development System — AI-assisted development methodology with skills for consistency and agents for scale.
rmziImplementation planning, execution, and PR creation workflows with multi-agent collaboration
UniswapMulti-agent software evolution. Autonomously study, strategize, build, review, and evaluate code changes using specialist AI agents.
akashgitUniversal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
CloudAI-X