Scans your codebase and documentation to automatically generate and configure a suite of domain-specific expert agents for Claude Code, including critic gates and orchestration, enabling project-aware code review and specialized delegation.
This document defines the canonical structure for critic/architecture agents in `.claude/agents/`.
Intelligently decides which base agents should be split into specialist agents
Generates complete agent prompt files using LLM expertise (no templates!)
Validates generated agent prompts for structure, headers, and quality
Final validation of complete agent suite integrity
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
ClosedLoop is an AI platform that brings the speed of individual AI-driven development to the full software development team. We're offering our agents as open sourced Claude Code plugins because we just couldn't keep this a secret for ourselves — check out our agents for planning, code reviews, judging quality and more that outperform Opus 4.6 and Sonnet 4.5 out of the box.
Bootstrap. Plan. Code. Ship. It's that simple.
LLMs are great at non-deterministic content generation — horrible at being repeatably correct.
That's why we took Claude Code and extended it with a lightweight multi-agent orchestration workflow paradigm that works for us; modeling how we collaborate as a team.
Optimized for efficiency & correctness to produce code that lands without the churn; it's grounded in your codebase and outperforms Opus 4.6 out of the box at half the cost.
What's more impactful is that it allowed our team of engineers to shift left; reviewing and approving sprints-worth of work scope in documented implementation plans and generating the code while we slept.
Tickets become Tasks. Epics become Features. Sections of your quarterly roadmap land in a few PRs.
Multi-repository, adaptive self-learning, & artifact-bound phased workflow gates that loop until correct.
Close the Loop on your SDLC with the same tools that made us 400% faster today.
| Plugin | Description |
|---|---|
| bootstrap | Project bootstrapping and initial setup |
| code | Code generation, implementation planning, and iterative development loop |
| code-review | Automated code review with inline GitHub PR comments |
| judges | LLM-as-judge evaluators for plan and code quality |
| platform | Claude Code expert guidance, prompt engineering, and artifact management |
| self-learning | Pattern capture and organizational knowledge sharing |
# Install a plugin from the marketplace
claude /plugin marketplace install closedloop
# Or install from source for development
git clone [email protected]:closedloop-ai/claude-plugins.git
cd claude-plugins
git config core.hooksPath .githooks
# Bootstrap.
claude /bootstrap:start
# Plan. Code.
claude /code:start --prd requirements.md
See CONTRIBUTING.md for development setup, workflow, and code style guidelines.
Our claude code plugins are a low-key engineering preview of the agents that run the larger ClosedLoop platform. These agents should be used for testing in trusted environments.
Code and planning framework plugin
Code review plugin
Self-learning plugin
ClosedLoop Platform plugin
LLM Judges plugin
npx claudepluginhub closedloop-ai/claude-plugins --plugin bootstrapAutomation bootstrap for Claude Code. Analyzes any project and generates a complete .claude/ structure with agents, pipelines, skills, memory, hooks, and settings.
Code and planning framework plugin
Complete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows
Generic agent harness for Claude Code — pipeline agents, skills, continuation hook, plus the engine setup (re-run per update).
Cross-agent development skills, hooks, orchestration, and optional custom-agent adapters for Claude Code and Codex
Agentic Working Kit — disciplined agents, skills, slash commands, and tool-level gate hooks (commit/push approval, destructive-op & write guards, context-fill measurement, session rehydration) for Claude Code. The git-commit trace/secret/bloat scan needs the full install (start.sh / adopt.sh).