Repository
closedloop-ai/claude-plugins agent skills
- skills
- 43
- GitHub stars
- 122
GitHub description: “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. ”
- Stars
- 122 (16 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Mar 2026
- ai-agents
- claude-code
- developer-tools
- llm
- anthropic
- agentic-ai
- automation
- devtools
- multi-agent
Install all skills
npx skills add closedloop-ai/claude-pluginsAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in closedloop-ai/claude-plugins, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Run Codex to review a plan file and return structured feedback with a verdict. | closedloop-ai/ | 122 | — | ~1.4k | Automated safety check: Notes | Apache-2.0 | today |
| 2 | Check if critic reviews are still valid before re-running Phase 2.5 critics. | closedloop-ai/ | 122 | — | ~528 | Automated safety check: Notes | Apache-2.0 | today |
| 3 | Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. | closedloop-ai/ | 122 | — | ~683 | Automated safety check: Notes | Apache-2.0 | today |
| 4 | Check for a cached plan-evaluation.json result before launching the plan-evaluator agent. | closedloop-ai/ | 122 | — | ~516 | Automated safety check: Notes | Apache-2.0 | today |
| 5 | This skill should be used when needing to locate files within the Claude Code plugins cache directory (~/.claude/plugins/cache). | closedloop-ai/ | 122 | — | ~812 | Automated safety check: Pass | Apache-2.0 | today |
| 6 | Start a detached GitHub pull-request monitor that wakes the exact launching Codex Desktop or CLI root through the managed Codex App Server when review, CI, conflict, merge-queue, closure, readiness… | closedloop-ai/ | 122 | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | today |
| 7 | 7.Handoff Finish a vibe session in symphony-alpha and hand it to design, then engineering. | closedloop-ai/ | 122 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | today |
| 8 | Deterministic plan.json validation via Python script, replacing most plan-validator agent calls. | closedloop-ai/ | 122 | — | ~1.2k | Automated safety check: Notes | Apache-2.0 | today |
| 9 | This skill helps PMs draft lightweight PRDs. An agent skill from closedloop-ai/claude-plugins. | closedloop-ai/ | 122 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | Guide for creating NEW skills from scratch. An agent skill from closedloop-ai/claude-plugins. | closedloop-ai/ | 122 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | today |
| 11 | Upload a file as a ClosedLoop document (PRD, implementation plan, feature, or template). | closedloop-ai/ | 122 | — | ~1.4k | Automated safety check: Notes | Apache-2.0 | today |
| 12 | This skill should be used when working with Claude Code infrastructure including agents, skills, slash commands, hooks, plugins, settings.json, or CLAUDE.md files. | closedloop-ai/ | 122 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | today |
| 13 | This skill should be used when designing prompts, system prompts, or context windows for Claude. | closedloop-ai/ | 122 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | today |
| 14 | 14.Toon Format This skill should be used when writing or parsing TOON (Token-Oriented Object Notation) files. | closedloop-ai/ | 122 | — | ~684 | Automated safety check: Pass | Apache-2.0 | today |
| 15 | Skip Phase 7 rebuild when no code changed since Phase 5 build passed. | closedloop-ai/ | 122 | — | ~411 | Automated safety check: Notes | Apache-2.0 | today |
| 16 | Produce a private, read-only HTML report of all ClosedLoop work assigned to the authenticated user in one project, grouped into evidence-backed page or capability feature units with verified… | closedloop-ai/ | 122 | — | ~6.8k | Automated safety check: Pass | Apache-2.0 | today |
| 17 | A skill your agent uses to run the Claude Design to ClosedLoop pipeline against the current web-ui. | closedloop-ai/ | 122 | — | ~7.4k | Automated safety check: Pass | Apache-2.0 | today |
| 18 | Sync plan.md with plan.json content. An agent skill from closedloop-ai/claude-plugins. | closedloop-ai/ | 122 | — | ~437 | Automated safety check: Pass | Apache-2.0 | today |
| 19 | 19.Cl Execute Draft and upload ClosedLoop implementation plans with Mermaid scope flowcharts, then execute one ClosedLoop feature ticket or a parent-approved coherent multi-ticket feature end to end on Codex… | closedloop-ai/ | 122 | — | ~6.4k | Automated safety check: Pass | Apache-2.0 | today |
| 20 | Inspect the relevant code first to map the implementation blast area, then find ClosedLoop issue tickets related to a product area, behavior, requirement, incident, ticket, or pull request and give… | closedloop-ai/ | 122 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | today |
| 21 | Derive and run an interactive, evidence-recorded manual QA session for a code change, ticket, branch, or pull request. | closedloop-ai/ | 122 | — | ~6.3k | Automated safety check: Pass | Apache-2.0 | today |
| 22 | A skill your agent uses when optimizing, benchmarking, profiling, or running a performance experiment; when evaluating whether a change actually helped; or when recording or checking past… | closedloop-ai/ | 122 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | today |
| 23 | Conventions for editing plan.json implementation plans including task format, structured arrays, and plan structure rules. | closedloop-ai/ | 122 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | today |
| 24 | Render the operator-facing local-mode code review results at stage29present. | closedloop-ai/ | 122 | — | ~3.9k | Automated safety check: Pass | Apache-2.0 | today |
| 25 | 25.Run Judges Orchestrate parallel judge agent execution, aggregate CaseScore results, write plan-judges.json, code-judges.json, prd-judges.json, or feature-judges.json, and validate output. | closedloop-ai/ | 122 | — | ~15k | Automated safety check: Notes | Apache-2.0 | today |
| 26 | PLN-725 single-agent dispatch for stage11extractsignals and stage15coveragecritic. | closedloop-ai/ | 122 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 27 | Dispatch and collect the finding-verifier fleet at stage23verifyfindings (PLN-722). | closedloop-ai/ | 122 | — | ~2k | Automated safety check: Pass | Apache-2.0 | today |
| 28 | Run a worker-backed code review using the workflow prompt pack's strongest review lenses: approach correctness, architecture ownership, correctness, guardrails, validation, compatibility, and… | closedloop-ai/ | 122 | — | ~16k | Automated safety check: Pass | Apache-2.0 | today |
| 29 | 29.Cl Policy Shared ClosedLoop access and routing policy for local ClosedLoop automation skills. | closedloop-ai/ | 122 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | today |
| 30 | A skill your agent uses when the user wants a code-grounded decision table for current behavior, wants to compare current behavior against a plan or work item, or needs a control-flow artifact for… | closedloop-ai/ | 122 | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | today |
| 31 | Protocol for iteratively refining sub-agent queries through follow-up questions to ensure sufficient context | closedloop-ai/ | 122 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | today |
| 32 | This skill should be used when a user asks to explain a complex idea, concept, or system architecture, or when a diagram would be helpful to visualize control flows, system architectures, data… | closedloop-ai/ | 122 | — | ~525 | Automated safety check: Pass | Apache-2.0 | today |
| 33 | 33.Cl Analyze Analyze one ClosedLoop feature ticket from a URL or FEA slug before execution. | closedloop-ai/ | 122 | — | ~9.8k | Automated safety check: Pass | Apache-2.0 | today |
| 34 | 34.Cl Split Split one top-level high-complexity ClosedLoop feature ticket into smaller executable child tickets when safe. | closedloop-ai/ | 122 | — | ~5.4k | Automated safety check: Pass | Apache-2.0 | today |
| 35 | Spawn and collect the reviewer fleet at stage20spawnreviewers. | closedloop-ai/ | 122 | — | ~12k | Automated safety check: Pass | Apache-2.0 | today |
| 36 | Compresses artifacts for judge evaluation. An agent skill from closedloop-ai/claude-plugins. | closedloop-ai/ | 122 | — | ~2.1k | Automated safety check: Notes | Apache-2.0 | today |
| 37 | 37.Cl Sweep Report or coordinate ClosedLoop work assigned to the user in one project. | closedloop-ai/ | 122 | — | ~15k | Automated safety check: Pass | Apache-2.0 | today |
| 38 | 38.Fix Verify and fix BLOCKING/HIGH code review findings from a prior review session via category-dispatch, then run project verification. | closedloop-ai/ | 122 | — | ~4.7k | Automated safety check: Notes | Apache-2.0 | today |
| 39 | Structured format for capturing high-quality learnings during ClosedLoop runs | closedloop-ai/ | 122 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 40 | Canonical reusable orchestration procedures for the ClosedLoop planning/implementation orchestrators — PLANVALIDATIONSEQUENCE and AWAITINGUSERSEQUENCE. | closedloop-ai/ | 122 | — | ~777 | Automated safety check: Pass | Apache-2.0 | today |
| 41 | Keep symphony-alpha's vibe seed (the throwaway, fully seeded data behind just vibe-up and the vibe skill's seeded Vercel environments) in step with main. | closedloop-ai/ | 122 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | today |
| 42 | Provides ClosedLoop environment paths (CLOSEDLOOPWORKDIR, CLAUDEPLUGINROOT) to agents. | closedloop-ai/ | 122 | — | ~391 | Automated safety check: Pass | Apache-2.0 | today |
| 43 | ClosedLoop ticket + codebase intelligence over a shared remote instance. | closedloop-ai/ | 122 | — | ~2k | Automated safety check: Pass | Apache-2.0 | today |
Questions, answered from the data.
What is the best skill in closedloop-ai/claude-plugins?
Codex Review from closedloop-ai/claude-plugins ranks first of the 43 skills in closedloop-ai/claude-plugins listed here, with the highest score: its repository has 122 GitHub stars, its SKILL.md loads about 1.4k tokens and it has informational notes only in the automated safety check. Next come Critic Cache and Cross Repo Cache.
Are the skills in closedloop-ai/claude-plugins official?
None yet. All 43 skills in closedloop-ai/claude-plugins listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from closedloop-ai/claude-plugins?
Run npx skills add closedloop-ai/claude-plugins in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.