{
  "markdown": "# ClosedLoop.AI Claude Plugins\n\n<div>\n  <img src=\"https://img.shields.io/badge/license-Apache%202.0-green\" alt=\"License\" />\n  <img src=\"https://img.shields.io/badge/python-3.11+-blue\" alt=\"Python 3.11+\" />\n  <img src=\"https://img.shields.io/badge/claude--code-plugin-purple\" alt=\"Claude Code Plugin\" />\n</div>\n\n<br/>\n\n<img alt=\"Multi-Agent SDLC Grounded in Your Codebase\" src=\"docs/images/hero.png\" />\n\nClosedLoop 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.\n\n**Bootstrap. Plan. Code. Ship.** It's that simple.\n\nLLMs are great at non-deterministic content generation — horrible at being repeatably correct.\n\nThat'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.\n\nOptimized 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.\n\nWhat'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.\n\nTickets become Tasks. Epics become Features. Sections of your quarterly roadmap land in a few PRs.\n\nMulti-repository, adaptive self-learning, & artifact-bound phased workflow gates that loop until correct.\n\n**Close the Loop on your SDLC with the same tools that made us 400% faster today.**\n\n## Plugins\n\n| Plugin | Description |\n|--------|-------------|\n| [**bootstrap**](plugins/bootstrap/) | Project bootstrapping and initial setup |\n| [**code**](plugins/code/) | Code generation, implementation planning, and iterative development loop |\n| [**code-review**](plugins/code-review/) | Automated code review with inline GitHub PR comments |\n| [**judges**](plugins/judges/) | LLM-as-judge evaluators for plan and code quality |\n| [**platform**](plugins/platform/) | Claude Code expert guidance, prompt engineering, and artifact management |\n| [**self-learning**](plugins/self-learning/) | Pattern capture and organizational knowledge sharing |\n\n## Prerequisites\n\n- Python 3.11+ (3.13 recommended)\n- [jq](https://jqlang.github.io/jq/)\n- [Claude Code](https://claude.ai/code)\n\n## Quick Start\n\n**One-line install** — installs the five Symphony runtime plugins at user scope and keeps them auto-updated:\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/closedloop-ai/claude-plugins/main/install.sh | bash\n```\n\nThe installer installs `code`, `code-review`, `judges`, `platform`, and `self-learning`, then verifies those runtime plugins are present with existing install paths and enabled user-scoped entries. It re-enables disabled user-scoped runtime plugins and attempts to remove stale project-scoped duplicates when Claude reports a usable `projectPath`. If Claude reports a project-scoped entry without a usable project path, the installer prints the project-directory uninstall command and still repairs the user-scoped install. The `bootstrap` plugin remains available in the marketplace for manual installation, but it is not part of the default runtime install.\n\nOr install interactively from within Claude Code:\n\n```bash\nclaude /plugin marketplace install closedloop\n```\n\n### Codex example\n\nThis PR adds Codex metadata for the `code-review` plugin as a first\nrepresentative cross-harness install path:\n\n```bash\ncodex plugin marketplace add https://github.com/closedloop-ai/claude-plugins\n```\n\nThen install **ClosedLoop Code Review** from the Codex Plugins UI. The same\n`.codex-plugin/plugin.json` and `.agents/plugins/marketplace.json` pattern can\nbe repeated for the other ClosedLoop plugins.\n\nThen start using the plugins:\n\n```bash\n# Plan. Code.\nclaude /code:code --prd requirements.md\n\n# Review.\nclaude /code-review:start\n```\n\n<details>\n<summary><strong>Development setup</strong></summary>\n\n```bash\ngit clone git@github.com:closedloop-ai/claude-plugins.git\ncd claude-plugins\ngit config core.hooksPath .githooks\n```\n\n</details>\n\n## Benchmarks\n<img width=\"1421\" height=\"862\" alt=\"image\" src=\"https://github.com/user-attachments/assets/82e42af7-9386-4a36-9bc0-2fd5d3564eba\" />\n\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for development setup, workflow, and code style guidelines.\n\n## Evals and production telemetry\n\nThe `evals/code-review/` directory contains a small human-review eval set for\nreview finding quality, finding verification, and inline PR comment drafting.\nThe cases are harness-neutral so the same plugin behavior can be checked in\nClaude Code, Codex, or another agent workspace before release.\n\nIf you publish plugins through Telvine, keep runtime telemetry metadata-only:\n`skill.invocation.start`, `skill.invocation.end`, and `skill.invocation.error`\nfor skill behavior, plus `plugin.component.invoked` and\n`plugin.component.error` for commands, agents, tools, or other non-skill\ncomponents. Do not emit prompts, repository file contents, connector payloads,\ntool arguments, GitHub tokens, inline comment bodies, or model outputs.\n\n## Disclaimer\nOur 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.\n\n## License\n\n[Apache License 2.0](LICENSE)\n",
  "bytes": 5589,
  "sha": "51e33e09ce9caac931c3d3f7d2061de266ca3c9ee112f93713878d214905e9e7",
  "repo_slug": "closedloop-ai/claude-plugins",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_closedloop_ai_claude_plugins_closedloop_84c4c476/readme"
}