rjmurillo/ai-agents
Open-source multi-agent toolkit for Claude Code and GitHub Copilot CLI: 22 agents, plan-to-ship workflows, review and security gates, plugin marketplace.
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 serena -- uvx --from git+https://github.com/oraios/serena serena start-mcp-server --project ${workspaceFolder:-.} --context claude-code --port 24282 $ claude mcp add --transport http deepwiki https://mcp.deepwiki.com/mcp $ npx degit rjmurillo/ai-agents/.claude ./rig-ai-agents # 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 serena -- uvx --from git+https://github.com/oraios/serena serena start-mcp-server --project ${workspaceFolder:-.} --context claude-code --port 24282 $ claude mcp add --transport http deepwiki https://mcp.deepwiki.com/mcp
$ npx degit rjmurillo/ai-agents/.claude/skills/adr-generator .claude/skills/adr-generator $ npx degit rjmurillo/ai-agents/.claude/skills/adr-review .claude/skills/adr-review $ npx degit rjmurillo/ai-agents/.claude/skills/agent-harness-reference .claude/skills/agent-harness-reference $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-architecture-contract .claude/skills/ai-agents-architecture-contract $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-build-and-env .claude/skills/ai-agents-build-and-env $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-change-control .claude/skills/ai-agents-change-control $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-config-catalog .claude/skills/ai-agents-config-catalog $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-debugging-playbook .claude/skills/ai-agents-debugging-playbook $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-diagnostics-toolkit .claude/skills/ai-agents-diagnostics-toolkit $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-docs-of-record .claude/skills/ai-agents-docs-of-record $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-empirical-probe-toolkit .claude/skills/ai-agents-empirical-probe-toolkit $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-external-claims .claude/skills/ai-agents-external-claims $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-failure-archaeology .claude/skills/ai-agents-failure-archaeology $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-generation-and-release .claude/skills/ai-agents-generation-and-release $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-portability-campaign .claude/skills/ai-agents-portability-campaign $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-research-frontier .claude/skills/ai-agents-research-frontier $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-research-methodology .claude/skills/ai-agents-research-methodology $ npx degit rjmurillo/ai-agents/.claude/skills/ai-agents-validation-and-qa .claude/skills/ai-agents-validation-and-qa $ npx degit rjmurillo/ai-agents/.claude/skills/analysis-provenance .claude/skills/analysis-provenance $ npx degit rjmurillo/ai-agents/.claude/skills/analyze .claude/skills/analyze $ npx degit rjmurillo/ai-agents/.claude/skills/autoplan .claude/skills/autoplan $ npx degit rjmurillo/ai-agents/.claude/skills/avoiding-manufactured-work .claude/skills/avoiding-manufactured-work $ npx degit rjmurillo/ai-agents/.claude/skills/benchmark-models .claude/skills/benchmark-models $ npx degit rjmurillo/ai-agents/.claude/skills/business-strategy .claude/skills/business-strategy $ npx degit rjmurillo/ai-agents/.claude/skills/buy-vs-build-framework .claude/skills/buy-vs-build-framework $ npx degit rjmurillo/ai-agents/.claude/skills/chaos-experiment .claude/skills/chaos-experiment $ npx degit rjmurillo/ai-agents/.claude/skills/checkpoint .claude/skills/checkpoint $ npx degit rjmurillo/ai-agents/.claude/skills/chestertons-fence .claude/skills/chestertons-fence $ npx degit rjmurillo/ai-agents/.claude/skills/code-qualities-assessment .claude/skills/code-qualities-assessment $ npx degit rjmurillo/ai-agents/.claude/skills/codebase-documenter .claude/skills/codebase-documenter $ npx degit rjmurillo/ai-agents/.claude/skills/codeql-scan .claude/skills/codeql-scan $ npx degit rjmurillo/ai-agents/.claude/skills/context-gather .claude/skills/context-gather $ npx degit rjmurillo/ai-agents/.claude/skills/context-hub-setup .claude/skills/context-hub-setup $ npx degit rjmurillo/ai-agents/.claude/skills/context-optimizer .claude/skills/context-optimizer $ npx degit rjmurillo/ai-agents/.claude/skills/curating-memories .claude/skills/curating-memories $ npx degit rjmurillo/ai-agents/.claude/skills/cva-analysis .claude/skills/cva-analysis $ npx degit rjmurillo/ai-agents/.claude/skills/cynefin-classifier .claude/skills/cynefin-classifier $ npx degit rjmurillo/ai-agents/.claude/skills/decision-critic .claude/skills/decision-critic $ npx degit rjmurillo/ai-agents/.claude/skills/doc-accuracy .claude/skills/doc-accuracy $ npx degit rjmurillo/ai-agents/.claude/skills/dx-review .claude/skills/dx-review
$ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/analyst.md $ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-simplifier.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/code-simplifier.md $ curl -fsSL --create-dirs -o .claude/agents/comment-analyzer.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/comment-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/critic.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/critic.md $ curl -fsSL --create-dirs -o .claude/agents/debug.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/debug.md $ curl -fsSL --create-dirs -o .claude/agents/dependency-auditor.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/dependency-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/devops.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/devops.md $ curl -fsSL --create-dirs -o .claude/agents/explainer.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/explainer.md $ curl -fsSL --create-dirs -o .claude/agents/high-level-advisor.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/high-level-advisor.md $ curl -fsSL --create-dirs -o .claude/agents/implementer.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/implementer.md $ curl -fsSL --create-dirs -o .claude/agents/independent-thinker.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/independent-thinker.md $ curl -fsSL --create-dirs -o .claude/agents/issue-feature-review.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/issue-feature-review.md $ curl -fsSL --create-dirs -o .claude/agents/janitor.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/janitor.md $ curl -fsSL --create-dirs -o .claude/agents/merge-resolver.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/merge-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/milestone-planner.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/milestone-planner.md $ curl -fsSL --create-dirs -o .claude/agents/negotiation.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/negotiation.md $ curl -fsSL --create-dirs -o .claude/agents/orchestrator.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/orchestrator.md $ curl -fsSL --create-dirs -o .claude/agents/pr-comment-responder.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/pr-comment-responder.md $ curl -fsSL --create-dirs -o .claude/agents/pr-test-analyzer.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/pr-test-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/qa.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/qa.md $ curl -fsSL --create-dirs -o .claude/agents/quality-auditor.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/quality-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/retrospective.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/retrospective.md $ curl -fsSL --create-dirs -o .claude/agents/roadmap.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/roadmap.md $ curl -fsSL --create-dirs -o .claude/agents/security.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/security.md $ curl -fsSL --create-dirs -o .claude/agents/silent-failure-hunter.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/silent-failure-hunter.md $ curl -fsSL --create-dirs -o .claude/agents/skillbook.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/skillbook.md $ curl -fsSL --create-dirs -o .claude/agents/task-decomposer.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/task-decomposer.md $ curl -fsSL --create-dirs -o .claude/agents/type-design-analyzer.md https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/agents/type-design-analyzer.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(git *--output*)",
"Bash(git *--exec-path*)",
"Bash(git *diff.external=*)",
"Bash(git *core.pager=*)",
"Bash(git *core.sshCommand=*)",
"Bash(git *core.fsmonitor=*)",
"Bash(git *textconv=*)",
"Bash(git *uploadpack.packObjectsHook=*)",
"Bash(git push *--force)",
"Bash(git push *--force *)",
"Bash(git push -f *)",
"Bash(git push * -f)",
"Bash(git push * -f *)",
"Bash(git push *--force-with-lease)",
"Bash(git push *--force-with-lease *)",
"Bash(git push * +*)",
"Bash(git push *--mirror*)",
"Bash(git commit *--no-verify)",
"Bash(git commit *--no-verify *)",
"Bash(git commit -n *)",
"Bash(git commit * -n)",
"Bash(git commit * -n *)",
"Bash(git push *--no-verify)",
"Bash(git push *--no-verify *)",
"Bash(rm -rf *)",
"Bash(rm -fr *)",
"Bash(rm -Rf *)",
"Bash(rm -fR *)",
"Bash(rm -r -f *)",
"Bash(rm -f -r *)",
"Bash(rm --recursive --force *)",
"Bash(rm --force --recursive *)",
"Bash(gh repo delete*)",
"Bash(gh repo archive*)",
"Bash(gh repo rename*)",
"Bash(gh repo edit*)",
"Bash(gh release delete*)",
"Bash(gh issue delete*)",
"Bash(gh label delete*)",
"Bash(gh secret *)",
"Bash(gh variable set*)",
"Bash(gh variable delete*)",
"Bash(gh pr merge *--admin*)",
"Bash(gh api *-X DELETE*)",
"Bash(gh api *-XDELETE*)",
"Bash(gh api *--method DELETE*)",
"Bash(gh api *--method=DELETE*)",
"Bash(gh api *branches/*/protection*)",
"Bash(gh api *collaborators*)",
"Bash(gh api *pending_deployments*)"
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| Serena | git | 8.0k |
| DeepWiki | remote · remote | 900 |
Skills (107)
adr-generatoradr-reviewagent-harness-referenceai-agents-architecture-contractai-agents-build-and-envai-agents-change-controlai-agents-config-catalogai-agents-debugging-playbookai-agents-diagnostics-toolkitai-agents-docs-of-recordai-agents-empirical-probe-toolkitai-agents-external-claimsai-agents-failure-archaeologyai-agents-generation-and-releaseai-agents-portability-campaignai-agents-research-frontierai-agents-research-methodologyai-agents-validation-and-qaanalysis-provenanceanalyzeautoplanavoiding-manufactured-workbenchmark-modelsbusiness-strategybuy-vs-build-frameworkchaos-experimentcheckpointchestertons-fencecode-qualities-assessmentcodebase-documentercodeql-scancontext-gathercontext-hub-setupcontext-optimizercurating-memoriescva-analysiscynefin-classifierdecision-criticdoc-accuracydx-reviewexecution-plansfix-markdown-fencesgit-advanced-workflowsgithub-url-interceptgithubgolden-principlesmemory-consolidatememory-documentarymemory-enhancementmemory-gatememory-maintenancememory-reflexionmemory-searchmemorymerge-resolvermetricsnegotiationobservabilityorphan-ref-validatorpanning-for-goldpipeline-validatorplanplannerpr-autofixpr-comment-responderpr-quality-allpr-quality-analystpr-quality-architectpr-quality-devopspr-quality-qapr-quality-roadmappr-quality-securitypr-reviewpre-mortemprogramming-advisorprompt-engineerprose-self-checkpush-prquality-gradesreflectrequirements-interviewresearchretroretrospectivereviewreviewer-findingssecurity-detectionsecurity-reviewsecurity-scanshipskillforgeslo-designersoftware-engineering-libraryspec-generatorspecsteering-matcherstuck-detectionstyle-enforcementsynctaste-lintsthreat-modelingusing-serena-symbolsvalidate-pr-descriptionvalidation-authoritywindows-image-updaterwork-operating-modelworld-model-diagnostic
Subagents (30)
| analyst | Research and investigation specialist who digs deep into root causes, surfaces unknowns, and gathers evidence before implementation. Methodical about documenting findings, evaluating feasibility, and |
| architect | Technical authority on system design who guards architectural coherence, enforces patterns, and maintains boundaries. Creates ADRs, conducts design reviews, and ensures decisions align with principles |
| code-reviewer model: haiku | Use this agent when you need to review code changes for correctness, discovered project-convention compliance, and duplicated logic. Invoke proactively after writing or modifying code, and before comm |
| code-simplifier | Use this agent when code has been written or modified and needs to be simplified for clarity, consistency, and maintainability while preserving all functionality. This agent should be triggered automa |
| comment-analyzer | Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. Use cases include large documentation comments or docstrings, pull requests that add or |
| critic | Constructive reviewer who stress-tests plans before implementation, validates completeness, identifies gaps, catches ambiguity. Challenges assumptions, checks alignment, and blocks approval when risks |
| debug | Debug your application to find and fix a bug. Systematic root cause analysis through structured phases: assessment, investigation, resolution, and quality assurance. |
| dependency-auditor | Audit dependencies for vulnerabilities, outdated versions, and deprecations. C#/.NET first (dotnet list package), with extensible patterns for npm, pip, and cargo. Use on a schedule or before releases |
| devops | DevOps specialist fluent in CI/CD pipelines, build automation, and deployment workflows. Thinks in reliability, security, and developer experience. Designs GitHub Actions, configures build systems, ma |
| explainer | Documentation specialist who writes PRDs, explainers, and technical specifications that junior developers understand without questions. Uses explicit language, INVEST criteria for user stories, and un |
| high-level-advisor | Brutally honest strategic advisor who cuts through comfort and delivers unfiltered truth. Prioritizes ruthlessly, challenges assumptions, exposes blind spots, and resolves decision paralysis with clea |
| implementer | Execution-focused engineering expert who implements approved plans with production-quality code. Applies rigorous software design methodology with explicit quality standards. Enforces testability, enc |
| independent-thinker | Contrarian analyst who challenges assumptions with evidence, presents alternative viewpoints, and declares uncertainty rather than guessing. Intellectually rigorous, respectfully skeptical, cites sour |
| issue-feature-review | Review GitHub feature requests with constructive skepticism. Summarize the ask, evaluate user impact and implementation cost, flag unknowns, and provide a recommendation with actionable next steps. |
| janitor | Perform janitorial tasks on any codebase including cleanup, simplification, and tech debt remediation. |
| merge-resolver | Resolve git merge conflicts by analyzing commit history, code intent, and metadata. Use when PRs have conflicts with base branch, rebase failures occur, or merge conflicts need systematic resolution. |
| milestone-planner | Use when you say "break this epic into milestones", "plan this roadmap item", or hand it a roadmap epic. Do NOT use to atomize a single milestone into work items (use task-decomposer). High-rigor plan |
| negotiation | Negotiation specialist who analyzes offers, drafts counter-proposals, and surfaces deal intelligence using behavioral frameworks and agent-era research findings. Use when reviewing any offer (real est |
| orchestrator | Enterprise task orchestrator who autonomously coordinates specialized agents end-to-end, routing work, managing handoffs, and synthesizing results. Classifies complexity, triages delegation, and seque |
| pr-comment-responder | PR review coordinator who gathers comment context, acknowledges every piece of feedback, and ensures all reviewer comments are addressed systematically. Triages by actionability, tracks thread convers |
| pr-test-analyzer | Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new fun |
| qa | Quality assurance specialist who verifies implementations work correctly for real users, not just passing tests. Designs test strategies, validates coverage against acceptance criteria, and reports re |
| quality-auditor | Periodically scans and grades product domains across architectural layers (agents, skills, scripts, tests, docs, workflows). Produces quality reports with gap tracking and trend analysis. Use when you |
| retrospective | Reflective analyst who extracts learnings through structured retrospective frameworks, diagnosing agent performance, identifying error patterns, and documenting success strategies. Uses Five Whys, tim |
| roadmap | CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against s |
| security | Security specialist with a defense-first mindset. Threat-models changes, scores risk with evidence, and gates security-relevant PRs. Use before shipping any change touching auth, secrets, input handli |
| silent-failure-hunter | Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after |
| skillbook | Skill manager who transforms reflections into high-quality atomic skillbook updates, guarding strategy quality, preventing duplicates, and maintaining learned patterns. Scores atomicity, runs deduplic |
| task-decomposer | Task decomposition specialist who breaks PRDs and epics into atomic, estimable work items with clear acceptance criteria and done definitions. Sequences by dependencies, groups into milestones, sizes |
| type-design-analyzer | Use this agent when you need expert analysis of type design in your codebase. Use cases include introducing a new type, reviewing all types added by a pull request, and refactoring existing types to i |
Hooks (8)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | cd "$CLAUDE_PROJECT_DIR" && ./.claude/hooks/session-start.sh |
| SessionStart | * | cd "$CLAUDE_PROJECT_DIR" && python3 -u .claude/hooks/invoke_dispatch_claude.py --group sessionstart-1-context_loader |
| SessionStart | * | cd "$CLAUDE_PROJECT_DIR" && python3 -u .claude/hooks/invoke_dispatch_claude.py --group sessionstart-2-checkout_freshness |
| SessionStart | * | cd "$CLAUDE_PROJECT_DIR" && python3 -u .claude/hooks/invoke_dispatch_claude.py --group sessionstart-3-plugin_hook_drift |
| UserPromptSubmit | * | cd "$CLAUDE_PROJECT_DIR" && python3 -u .claude/hooks/UserPromptSubmit/invoke_memory_recall.py |
| Stop | * | cd "$CLAUDE_PROJECT_DIR" && python3 -u .claude/hooks/Stop/invoke_reflect_nudge.py || true |
| SessionEnd | * | cd "$CLAUDE_PROJECT_DIR" && python3 -u .claude/hooks/SessionEnd/invoke_memory_reflection.py |
| PreCompact | * | cd "$CLAUDE_PROJECT_DIR" && python3 -u .claude/hooks/PreCompact/invoke_compact_checkpoint.py |
Permissions
deny (50)
Bash(git *--output*)
Bash(git *--exec-path*)
Bash(git *diff.external=*)
Bash(git *core.pager=*)
Bash(git *core.sshCommand=*)
Bash(git *core.fsmonitor=*)
Bash(git *textconv=*)
Bash(git *uploadpack.packObjectsHook=*)
Bash(git push *--force)
Bash(git push *--force *)
Bash(git push -f *)
Bash(git push * -f)
Bash(git push * -f *)
Bash(git push *--force-with-lease)
Bash(git push *--force-with-lease *)
Bash(git push * +*)
Bash(git push *--mirror*)
Bash(git commit *--no-verify)
Bash(git commit *--no-verify *)
Bash(git commit -n *)
Bash(git commit * -n)
Bash(git commit * -n *)
Bash(git push *--no-verify)
Bash(git push *--no-verify *)
Bash(rm -rf *)
Bash(rm -fr *)
Bash(rm -Rf *)
Bash(rm -fR *)
Bash(rm -r -f *)
Bash(rm -f -r *)
Bash(rm --recursive --force *)
Bash(rm --force --recursive *)
Bash(gh repo delete*)
Bash(gh repo archive*)
Bash(gh repo rename*)
Bash(gh repo edit*)
Bash(gh release delete*)
Bash(gh issue delete*)
Bash(gh label delete*)
Bash(gh secret *)
Bash(gh variable set*)
Bash(gh variable delete*)
Bash(gh pr merge *--admin*)
Bash(gh api *-X DELETE*)
Bash(gh api *-XDELETE*)
Bash(gh api *--method DELETE*)
Bash(gh api *--method=DELETE*)
Bash(gh api *branches/*/protection*)
Bash(gh api *collaborators*)
Bash(gh api *pending_deployments*)
ask (0)
—
allow (0)
—
Similar rigs
kapadias/nonna
Your AI agent says done. Nonna makes it prove it: she runs your test suite before a coding agent can stop, and blocks pushes to main and secrets in files. Claude Code plugin, plus git hooks for Codex, Cursor, Copilot, Gemini and more
Fort Knox 3.9k tok ·
qyndex/claude-init
Production-grade Claude Code harness — a spec-driven, TDD-first, verification-gated, security-aware .claude/ scaffold you drop into any repo with one command.
Fort Knox 98.5k tok ·
poshan0126/dotclaude
The standard .claude/ folder structure for everyday development.
Fort Knox 1.7k tok ·
skateddu/claude-code-python-setup
Ready-to-use .claude configuration for Python projects: agents, skills, commands, rules, and MCP server templates for Claude Code.
Fort Knox 7.9k tok ·