josephneumann/claude-corps
Production workflow framework for Claude Code — multi-agent orchestration, parallel worktrees, autonomous task execution, and compound engineering skills
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit josephneumann/claude-corps/agents ./rig-claude-corps/agents $ npx degit josephneumann/claude-corps/skills ./rig-claude-corps/skills $ npx degit josephneumann/claude-corps/hooks ./rig-claude-corps/hooks
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.
$ npx degit josephneumann/claude-corps/skills/auto-run .claude/skills/auto-run $ npx degit josephneumann/claude-corps/skills/benchmark .claude/skills/benchmark $ npx degit josephneumann/claude-corps/skills/claudemd-audit .claude/skills/claudemd-audit $ npx degit josephneumann/claude-corps/skills/debug .claude/skills/debug $ npx degit josephneumann/claude-corps/skills/deep-plan .claude/skills/deep-plan $ npx degit josephneumann/claude-corps/skills/design-shotgun .claude/skills/design-shotgun $ npx degit josephneumann/claude-corps/skills/dispatch .claude/skills/dispatch $ npx degit josephneumann/claude-corps/skills/finish-task .claude/skills/finish-task $ npx degit josephneumann/claude-corps/skills/humanizer .claude/skills/humanizer $ npx degit josephneumann/claude-corps/skills/milestone-review .claude/skills/milestone-review $ npx degit josephneumann/claude-corps/skills/multi-review .claude/skills/multi-review $ npx degit josephneumann/claude-corps/skills/orient .claude/skills/orient $ npx degit josephneumann/claude-corps/skills/plan-design-review .claude/skills/plan-design-review $ npx degit josephneumann/claude-corps/skills/plan-eng-review .claude/skills/plan-eng-review $ npx degit josephneumann/claude-corps/skills/product-review .claude/skills/product-review $ npx degit josephneumann/claude-corps/skills/qa .claude/skills/qa $ npx degit josephneumann/claude-corps/skills/reconcile-summary .claude/skills/reconcile-summary $ npx degit josephneumann/claude-corps/skills/retro .claude/skills/retro $ npx degit josephneumann/claude-corps/skills/spec .claude/skills/spec $ npx degit josephneumann/claude-corps/skills/start-task .claude/skills/start-task $ npx degit josephneumann/claude-corps/skills/summarize-session .claude/skills/summarize-session $ npx degit josephneumann/claude-corps/skills/verify .claude/skills/verify $ npx degit josephneumann/claude-corps/skills/writing-skills .claude/skills/writing-skills
$ curl -fsSL --create-dirs -o .claude/agents/best-practices-researcher.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/research/best-practices-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/framework-docs-researcher.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/research/framework-docs-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/git-history-analyzer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/research/git-history-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/repo-research-analyst.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/research/repo-research-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/agent-native-reviewer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/agent-native-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/api-security-reviewer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/api-security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/architecture-strategist.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/architecture-strategist.md $ curl -fsSL --create-dirs -o .claude/agents/code-simplicity-reviewer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/code-simplicity-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/data-integrity-guardian.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/data-integrity-guardian.md $ curl -fsSL --create-dirs -o .claude/agents/data-migration-expert.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/data-migration-expert.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-performance-reviewer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/frontend-performance-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/nextjs-reviewer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/nextjs-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/pattern-recognition-specialist.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/pattern-recognition-specialist.md $ curl -fsSL --create-dirs -o .claude/agents/performance-oracle.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/performance-oracle.md $ curl -fsSL --create-dirs -o .claude/agents/python-backend-reviewer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/python-backend-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-sentinel.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/security-sentinel.md $ curl -fsSL --create-dirs -o .claude/agents/tailwind-reviewer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/tailwind-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/ux-reviewer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/review/ux-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/spec-flow-analyzer.md https://raw.githubusercontent.com/josephneumann/claude-corps/main/agents/workflow/spec-flow-analyzer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (23)
auto-runbenchmarkclaudemd-auditdebugdeep-plandesign-shotgundispatchfinish-taskhumanizermilestone-reviewmulti-revieworientplan-design-reviewplan-eng-reviewproduct-reviewqareconcile-summaryretrospecstart-tasksummarize-sessionverifywriting-skills
Subagents (19)
| best-practices-researcher model: inherit | Use this agent when you need to research and gather external best practices, documentation, and examples for any technology, framework, or development practice. This includes finding official document |
| framework-docs-researcher model: inherit | Use this agent when you need to gather comprehensive documentation and best practices for frameworks, libraries, or dependencies in your project. This includes fetching official documentation, explori |
| git-history-analyzer model: inherit | Use this agent when you need to understand the historical context and evolution of code changes, trace the origins of specific code patterns, identify key contributors and their expertise areas, or an |
| repo-research-analyst model: inherit | Use this agent when you need to conduct thorough research on a repository's structure, documentation, and patterns. This includes analyzing architecture files, examining GitHub issues for patterns, re |
| agent-native-reviewer model: inherit | Use this agent when reviewing code to ensure features are agent-native - that any action a user can take, an agent can also take, and anything a user can see, an agent can see. This enforces the princ |
| api-security-reviewer model: inherit | Use this agent when reviewing API endpoints, routes, or controllers for security issues specific to HTTP APIs. This includes rate limiting, pagination bounds, response data filtering, CORS configurati |
| architecture-strategist model: inherit | Use this agent when you need to analyze code changes from an architectural perspective, evaluate system design decisions, or ensure that modifications align with established architectural patterns. Th |
| code-simplicity-reviewer model: inherit | Use this agent when you need a final review pass to ensure code changes are as simple and minimal as possible. This agent should be invoked after implementation is complete but before finalizing chang |
| data-integrity-guardian model: inherit | Use this agent when you need to review database migrations, data models, or any code that manipulates persistent data. This includes checking migration safety, validating data constraints, ensuring tr |
| data-migration-expert model: inherit | Use this agent when reviewing PRs that touch database migrations, data backfills, or any code that transforms production data. This agent validates ID mappings against production reality, checks for s |
| frontend-performance-reviewer model: inherit | Review frontend code for performance impact: Core Web Vitals (LCP, CLS, INP), bundle size, rendering efficiency, and network patterns. Use when reviewing components with images, new dependencies, data |
| nextjs-reviewer model: inherit | Use this agent to review Next.js App Router code for correctness, performance, and best practices. This includes Server vs Client Component boundaries, Server Actions security, metadata API usage, rou |
| pattern-recognition-specialist model: inherit | Use this agent when you need to analyze code for design patterns, anti-patterns, naming conventions, and code duplication. This agent excels at identifying architectural patterns, detecting code smell |
| performance-oracle model: inherit | Use this agent when you need to analyze code for performance issues, optimize algorithms, identify bottlenecks, or ensure scalability. This includes reviewing database queries, memory usage, caching s |
| python-backend-reviewer model: inherit | Use this agent to review Python backend code including FastAPI, SQLAlchemy, Alembic, and general Python patterns. This covers async endpoints, dependency injection, Pydantic validation, ORM patterns, |
| security-sentinel model: inherit | Use this agent when you need a deep security review of code changes. Specializes in business logic vulnerabilities, authorization bypass, IDOR, absence detection (missing controls), and AI-difficult-t |
| tailwind-reviewer model: inherit | Use this agent to review Tailwind CSS, shadcn/ui, and Radix UI code for consistency, accessibility, and responsive design. This includes utility class patterns, component composition, WCAG compliance, |
| ux-reviewer model: inherit | Review frontend code for UX quality: interaction flows, state completeness, form patterns, component API consistency, screen reader narrative, and cognitive load. Use when reviewing UI components, for |
| spec-flow-analyzer model: inherit | Use this agent when you have a specification, plan, feature description, or technical document that needs user flow analysis and gap identification. This agent should be used proactively when:\n\n<exa |
Similar rigs
BonJarber/claude-config
Claude Code configuration
Orchestrator 924 tok ·
timurgaleev/vibestack
Sixty commands for AI coding assistants — /office-hours to shape an idea, /review before you merge, /ship to open the PR — plus the standing rules they assume. One install covers Claude Code, Cursor, Kiro and Codex CLI. Plain bash, MIT, no
Skill Collector 7.1k tok ·
g4rcez/dotfiles
My dotfiles for awesome shell
Skill Collector 6.5k tok ·
lamngockhuong/aiteamkit
Multi-harness AI plugin for Claude Code, Cursor and Codex CLI: skills that run the delivery lifecycle of a project team - intake, estimate, design, spec, breakdown, plan, implement, fix, review, QA, verify, release, incident, retro, onboard
Skill Collector 26.8k tok ·