ClosedLoop.AI Claude Plugins
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.
Plugins
| Plugin | Description |
|---|
| bootstrap | Project bootstrapping and initial setup |
| code | Code generation, implementation planning, and iterative development loop |
| vibe | Vibe sessions and ClosedLoop ticket workflows |
| closedloop-core | Shared planning, intelligence, diagrams, review, QA, measurement, and PR monitoring |
| code-review | Automated code review with inline GitHub PR comments |
| platform | Claude Code expert guidance, prompt engineering, and artifact management |
| self-learning | Pattern capture and organizational knowledge sharing |
Prerequisites
Quick Start
One-line install — installs the four Symphony runtime plugins at user scope and keeps them auto-updated:
curl -fsSL https://raw.githubusercontent.com/closedloop-ai/claude-plugins/main/install.sh | bash
The installer installs code, code-review, 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.
Or install interactively from within Claude Code:
claude /plugin marketplace install closedloop
Codex example
The code, vibe, closedloop-core, and code-review plugins include Codex
manifests and marketplace entries:
codex plugin marketplace add https://github.com/closedloop-ai/claude-plugins
codex plugin add closedloop-core@closedloop-ai
codex plugin add vibe@closedloop-ai
Engineers can also install code@closedloop-ai and code-review@closedloop-ai.
Codex requires core to be installed explicitly; Claude Code installs it through
the code, vibe, and platform dependencies. Restart the app after installation.
Then start using the plugins:
# Plan. Code.
claude /code:code --prd requirements.md
# Review.
claude /code-review:start
git clone [email protected]:closedloop-ai/claude-plugins.git
cd claude-plugins
git config core.hooksPath .githooks
Benchmarks
Contributing
See CONTRIBUTING.md for development setup, workflow, and code style guidelines.
Evals and production telemetry
The evals/code-review/ directory contains a small human-review eval set for
review finding quality, finding verification, and inline PR comment drafting.
The cases are harness-neutral so the same plugin behavior can be checked in
Claude Code, Codex, or another agent workspace before release.
If you publish plugins through Telvine, keep runtime telemetry metadata-only:
skill.invocation.start, skill.invocation.end, and skill.invocation.error
for skill behavior, plus plugin.component.invoked and
plugin.component.error for commands, agents, tools, or other non-skill
components. Do not emit prompts, repository file contents, connector payloads,
tool arguments, GitHub tokens, inline comment bodies, or model outputs.
Disclaimer
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.
License
Apache License 2.0
