claude-plugins
byclosedloop-ai· 1 MCP server
Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase. Bootstrap, Plan, & Ship.
How to install claude-plugins?
closedloop-ai/claude-plugins
$git clone https://github.com/closedloop-ai/claude-pluginsInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install claude-plugins by running `git clone https://github.com/closedloop-ai/claude-plugins`, then use it for the current task and follow its documentation at https://github.com/closedloop-ai/claude-plugins.
README.md
| 1 | # ClosedLoop.AI Claude Plugins |
| 2 | |
| 3 | <div> |
| 4 | <img src="https://img.shields.io/badge/license-Apache%202.0-green" alt="License" /> |
| 5 | <img src="https://img.shields.io/badge/python-3.11+-blue" alt="Python 3.11+" /> |
| 6 | <img src="https://img.shields.io/badge/claude--code-plugin-purple" alt="Claude Code Plugin" /> |
| 7 | </div> |
| 8 | |
| 9 | <br/> |
| 10 | |
| 11 | <img alt="Multi-Agent SDLC Grounded in Your Codebase" src="docs/images/hero.png" /> |
| 12 | |
| 13 | 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. |
| 14 | |
| 15 | **Bootstrap. Plan. Code. Ship.** It's that simple. |
| 16 | |
| 17 | LLMs are great at non-deterministic content generation — horrible at being repeatably correct. |
| 18 | |
| 19 | 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. |
| 20 | |
| 21 | 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. |
| 22 | |
| 23 | 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. |
| 24 | |
| 25 | Tickets become Tasks. Epics become Features. Sections of your quarterly roadmap land in a few PRs. |
| 26 | |
| 27 | Multi-repository, adaptive self-learning, & artifact-bound phased workflow gates that loop until correct. |
| 28 | |
| 29 | **Close the Loop on your SDLC with the same tools that made us 400% faster today.** |
| 30 | |
| 31 | ## Plugins |
| 32 | |
| 33 | | Plugin | Description | |
| 34 | |--------|-------------| |
| 35 | | [**bootstrap**](plugins/bootstrap/) | Project bootstrapping and initial setup | |
| 36 | | [**code**](plugins/code/) | Code generation, implementation planning, and iterative development loop | |
| 37 | | [**code-review**](plugins/code-review/) | Automated code review with inline GitHub PR comments | |
| 38 | | [**judges**](plugins/judges/) | LLM-as-judge evaluators for plan and code quality | |
| 39 | | [**platform**](plugins/platform/) | Claude Code expert guidance, prompt engineering, and artifact management | |
| 40 | | [**self-learning**](plugins/self-learning/) | Pattern capture and organizational knowledge sharing | |
| 41 | |
| 42 | ## Prerequisites |
| 43 | |
| 44 | - Python 3.11+ (3.13 recommended) |
| 45 | - [jq](https://jqlang.github.io/jq/) |
| 46 | - [Claude Code](https://claude.ai/code) |
| 47 | |
| 48 | ## Quick Start |
| 49 | |
| 50 | **One-line install** — installs the five Symphony runtime plugins at user scope and keeps them auto-updated: |
| 51 | |
| 52 | ```bash |
| 53 | curl -fsSL https://raw.githubusercontent.com/closedloop-ai/claude-plugins/main/install.sh | bash |
| 54 | ``` |
| 55 | |
| 56 | The 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. |
| 57 | |
| 58 | Or install interactively from within Claude Code: |
| 59 | |
| 60 | ```bash |
| 61 | claude /plugin marketplace install closedloop |
| 62 | ``` |
| 63 | |
| 64 | ### Codex example |
| 65 | |
| 66 | This PR adds Codex metadata for the `code-review` plugin as a first |
| 67 | representative cross-harness install path: |
| 68 | |
| 69 | ```bash |
| 70 | codex plugin marketplace add https://github.com/closedloop-ai/claude-plugins |
| 71 | ``` |
| 72 | |
| 73 | Then install **ClosedLoop Code Review** from the Codex Plugins UI. The same |
| 74 | `.codex-plugin/plugin.json` and `.agents/plugins/marketplace.json` pattern can |
| 75 | be repeated for the other ClosedLoop plugins. |
| 76 | |
| 77 | Then start using the plugins: |
| 78 | |
| 79 | ```bash |
| 80 | # Plan. Code. |
| 81 | claude /code:code --prd requirements.md |
| 82 | |
| 83 | # Review. |
| 84 | claude /code-review:start |
| 85 | ``` |
| 86 | |
| 87 | <details> |
| 88 | <summary><strong>Development setup</strong></summary> |
| 89 | |
| 90 | ```bash |
| 91 | git clone git@github.com:closedloop-ai/claude-plugins.git |
| 92 | cd claude-plugins |
| 93 | git config core.hooksPath .githooks |
| 94 | ``` |
| 95 | |
| 96 | </details> |
| 97 | |
| 98 | ## Benchmarks |
| 99 | <img width="1421" height="862" alt="image" src="https://github.com/user-attachments/assets/82e42af7-9386-4a36-9bc0-2fd5d3564eba" /> |
| 100 | |
| 101 | |
| 102 | ## Contributing |
| 103 | |
| 104 | See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup, workflow, and code style guidelines. |
| 105 | |
| 106 | ## Evals and production telemetry |
| 107 | |
| 108 | The `evals/code-review/` directory contains a small human-review eval set for |
| 109 | review finding quality, finding verification, and inline PR comment drafting. |
| 110 | The cases are harness-neutral so the same plugin behavior can be checked in |
| 111 | Claude Code, Codex, or another agent workspace before release. |
| 112 | |
| 113 | If you publish plugins through Telvine, keep runtime telemetry metadata-only: |
| 114 | `skill |
Related
6 picksType
- code-review-graphLocal-first knowledge graph for token-efficient code review through MCP and CLIJul 2026
- repowiseCodebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.Jul 2026
- mcp-server-atlassian-bitbucketNode.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.Mar 2026
- gemini-mcp-toolMCP server for Gemini CLI integrationJul 2026
- socraticodeEnterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra…Jul 2026
- github-mcpProduction-ready Model Context Protocol server providing Claude with complete GitHub integration - comprehensive tools for repository management, branch operations, file handling, issue tracking, and collaboration features with OAuth 2.0 authentication and MongoDB persistence.Jun 2026
