pr-pm/prpm
The universal registry for AI coding tools
field: unknown workflow: CI/CD & deployTesting & TDDPlanning & specsDebuggingPR / code review runs codex in CI
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github $ npx degit pr-pm/prpm/.claude ./rig-prpm # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add github -e GITHUB_PERSONAL_ACCESS_<redacted> -- npx -y @modelcontextprotocol/server-github $ npx degit pr-pm/prpm/.agents/skills/creating-agent-skills .claude/skills/creating-agent-skills $ npx degit pr-pm/prpm/.claude/skills/adding-new-ai-format .claude/skills/adding-new-ai-format $ npx degit pr-pm/prpm/.claude/skills/agent-builder .claude/skills/agent-builder $ npx degit pr-pm/prpm/.claude/skills/aws-beanstalk-expert .claude/skills/aws-beanstalk-expert $ npx degit pr-pm/prpm/.claude/skills/beanstalk-deploy .claude/skills/beanstalk-deploy $ npx degit pr-pm/prpm/.claude/skills/claude-hook-writer .claude/skills/claude-hook-writer $ npx degit pr-pm/prpm/.claude/skills/creating-agents-md .claude/skills/creating-agents-md $ npx degit pr-pm/prpm/.claude/skills/creating-claude-agents .claude/skills/creating-claude-agents $ npx degit pr-pm/prpm/.claude/skills/creating-claude-commands .claude/skills/creating-claude-commands $ npx degit pr-pm/prpm/.claude/skills/creating-claude-hooks .claude/skills/creating-claude-hooks $ npx degit pr-pm/prpm/.claude/skills/creating-claude-rules .claude/skills/creating-claude-rules $ npx degit pr-pm/prpm/.claude/skills/creating-continue-packages .claude/skills/creating-continue-packages $ npx degit pr-pm/prpm/.claude/skills/creating-copilot-packages .claude/skills/creating-copilot-packages $ npx degit pr-pm/prpm/.claude/skills/creating-cursor-commands .claude/skills/creating-cursor-commands $ npx degit pr-pm/prpm/.claude/skills/creating-cursor-rules-skill .claude/skills/creating-cursor-rules-skill $ npx degit pr-pm/prpm/.claude/skills/creating-kiro-agents .claude/skills/creating-kiro-agents $ npx degit pr-pm/prpm/.claude/skills/creating-kiro-packages .claude/skills/creating-kiro-packages $ npx degit pr-pm/prpm/.claude/skills/creating-opencode-agents .claude/skills/creating-opencode-agents $ npx degit pr-pm/prpm/.claude/skills/creating-opencode-plugins .claude/skills/creating-opencode-plugins $ npx degit pr-pm/prpm/.claude/skills/creating-skills .claude/skills/creating-skills $ npx degit pr-pm/prpm/.claude/skills/creating-windsurf-packages .claude/skills/creating-windsurf-packages $ npx degit pr-pm/prpm/.claude/skills/creating-zed-extensions .claude/skills/creating-zed-extensions $ npx degit pr-pm/prpm/.claude/skills/documentation-standards .claude/skills/documentation-standards $ npx degit pr-pm/prpm/.claude/skills/elastic-beanstalk-deployment .claude/skills/elastic-beanstalk-deployment $ npx degit pr-pm/prpm/.claude/skills/github-actions-testing .claude/skills/github-actions-testing $ npx degit pr-pm/prpm/.claude/skills/human-writing .claude/skills/human-writing $ npx degit pr-pm/prpm/.claude/skills/integrating-stripe-webhooks .claude/skills/integrating-stripe-webhooks $ npx degit pr-pm/prpm/.claude/skills/karen-repo-reviewer .claude/skills/karen-repo-reviewer $ npx degit pr-pm/prpm/.claude/skills/npm-trusted-publishing .claude/skills/npm-trusted-publishing $ npx degit pr-pm/prpm/.claude/skills/osgrep-skill .claude/skills/osgrep-skill $ npx degit pr-pm/prpm/.claude/skills/postgres-migrations .claude/skills/postgres-migrations $ npx degit pr-pm/prpm/.claude/skills/prpm-development .claude/skills/prpm-development $ npx degit pr-pm/prpm/.claude/skills/prpm-json-best-practices .claude/skills/prpm-json-best-practices $ npx degit pr-pm/prpm/.claude/skills/pulumi-troubleshooting .claude/skills/pulumi-troubleshooting $ npx degit pr-pm/prpm/.claude/skills/self-improving .claude/skills/self-improving $ npx degit pr-pm/prpm/.claude/skills/slash-command-builder .claude/skills/slash-command-builder $ npx degit pr-pm/prpm/.claude/skills/testing-prpm-cli .claude/skills/testing-prpm-cli $ npx degit pr-pm/prpm/.claude/skills/thoroughness .claude/skills/thoroughness $ npx degit pr-pm/prpm/.claude/skills/typescript-type-safety .claude/skills/typescript-type-safety
$ curl -fsSL --create-dirs -o .claude/agents/blog-writer.md https://raw.githubusercontent.com/pr-pm/prpm/main/.claude/agents/blog-writer.md $ curl -fsSL --create-dirs -o .claude/agents/code-archaeologist.md https://raw.githubusercontent.com/pr-pm/prpm/main/.claude/agents/code-archaeologist.md $ curl -fsSL --create-dirs -o .claude/agents/core-principles.md https://raw.githubusercontent.com/pr-pm/prpm/main/.claude/agents/core-principles.md $ curl -fsSL --create-dirs -o .claude/agents/format-conversion.md https://raw.githubusercontent.com/pr-pm/prpm/main/.claude/agents/format-conversion.md $ curl -fsSL --create-dirs -o .claude/agents/testing-patterns.md https://raw.githubusercontent.com/pr-pm/prpm/main/.claude/agents/testing-patterns.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| GitHub MCP · "github" env: GITHUB_PERSONAL_ACCESS_TOKEN | npm | 18.0k |
Skills (39)
creating-agent-skillsadding-new-ai-formatagent-builderaws-beanstalk-expertbeanstalk-deployclaude-hook-writercreating-agents-mdcreating-claude-agentscreating-claude-commandscreating-claude-hookscreating-claude-rulescreating-continue-packagescreating-copilot-packagescreating-cursor-commandscreating-cursor-rules-skillcreating-kiro-agentscreating-kiro-packagescreating-opencode-agentscreating-opencode-pluginscreating-skillscreating-windsurf-packagescreating-zed-extensionsdocumentation-standardselastic-beanstalk-deploymentgithub-actions-testinghuman-writingintegrating-stripe-webhookskaren-repo-reviewernpm-trusted-publishingosgreppostgres-migrationsprpm-developmentprpm-json-best-practicespulumi-troubleshootingself-improvingslash-command-buildertesting-prpm-clithoroughnesstypescript-type-safety
Subagents (5)
| prpm-blog-writer | Expert agent for creating PRPM blog posts - ensures consistent structure, tone, format, and technical depth aligned with PRPM's vision of distributable intelligence |
| code-archaeologist model: opus | Analyzes repository git history and pull requests to discover coding patterns, reviewer feedback, and team conventions, then generates skills, rules, and agents based on the findings |
| prpm-core-principles | Expert agent for developing PRPM (Prompt Package Manager) - applies core architecture principles, quality standards, and development best practices for building the universal package manager for AI pr |
| format-conversion-expert | Expert agent for converting between AI prompt formats (Cursor, Claude, Continue, Windsurf) - ensures lossless conversions, quality scoring, and round-trip validation |
| prpm-testing-patterns | Expert agent for testing PRPM codebase with Vitest - applies testing patterns, coverage standards, and provides MCP-assisted test execution guidance |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | node .claude/hooks/development-workflow/dist/hook.js |
| UserPromptSubmit | * | node .claude/hooks/blog-workflow/dist/hook.js |
Slash commands (4)
/create-slash-command/karen/compare/karen/quick-score/karen/review
Cursor rules (23)
beanstalk-deploycore-principles · alwayscreating-agents-mdcreating-claude-agentscreating-claude-commandscreating-claude-hookscreating-continue-packagescreating-copilot-packagescreating-cursor-commandscreating-cursor-rulescreating-kiro-agentscreating-kiro-packagescreating-skillscreating-windsurf-packageselastic-beanstalk-deploymentformat-conversion · alwaysgithub-actions-testing · alwayskaren-repo-reviewerprpm-json-best-practicesself-improve-cursor · alwaystesting-patterns · alwaystypescript-type-safetytypescript-type-specialist · always
Similar rigs
AgentWorkforce/relay
Infrastructure for coding agents
Orchestrator 8.0k tok · · Q18
lee-to/ai-workspace
AI Workspace - Give your AI agents memory that spans across projects.
Pragmatist 19.7k tok · · Q0
ChooJeongHo/MovieFinder
TMDB API를 활용한 영화 검색 Android 앱
Pragmatist 25.0k tok · · Q0
heyong4725/claude-setup
Claude Code professional setup for Rust development
Pragmatist 19.1k tok · · Q0