OrdinaryUsr/claude-code-config
Claude Code dotfiles — custom agents, coding rules, and reusable skills for automated development
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details
Copy this rig
# review before running: this installs third-party code $ npx degit OrdinaryUsr/claude-code-config/agents ./rig-claude-code-config/agents $ npx degit OrdinaryUsr/claude-code-config/commands ./rig-claude-code-config/commands $ npx degit OrdinaryUsr/claude-code-config/skills ./rig-claude-code-config/skills $ npx degit OrdinaryUsr/claude-code-config/hooks ./rig-claude-code-config/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 OrdinaryUsr/claude-code-config/skills/api-design .claude/skills/api-design $ npx degit OrdinaryUsr/claude-code-config/skills/article-writing .claude/skills/article-writing $ npx degit OrdinaryUsr/claude-code-config/skills/autonomous-loops .claude/skills/autonomous-loops $ npx degit OrdinaryUsr/claude-code-config/skills/backend-patterns .claude/skills/backend-patterns $ npx degit OrdinaryUsr/claude-code-config/skills/codebase-onboarding .claude/skills/codebase-onboarding $ npx degit OrdinaryUsr/claude-code-config/skills/continuous-agent-loop .claude/skills/continuous-agent-loop $ npx degit OrdinaryUsr/claude-code-config/skills/cost-aware-llm-pipeline .claude/skills/cost-aware-llm-pipeline $ npx degit OrdinaryUsr/claude-code-config/skills/database-migrations .claude/skills/database-migrations $ npx degit OrdinaryUsr/claude-code-config/skills/deep-research .claude/skills/deep-research $ npx degit OrdinaryUsr/claude-code-config/skills/deployment-patterns .claude/skills/deployment-patterns $ npx degit OrdinaryUsr/claude-code-config/skills/design-system .claude/skills/design-system $ npx degit OrdinaryUsr/claude-code-config/skills/developer-device-platform-basics .claude/skills/developer-device-platform-basics $ npx degit OrdinaryUsr/claude-code-config/skills/docker-patterns .claude/skills/docker-patterns $ npx degit OrdinaryUsr/claude-code-config/skills/eval-harness .claude/skills/eval-harness $ npx degit OrdinaryUsr/claude-code-config/skills/find-skills .claude/skills/find-skills $ npx degit OrdinaryUsr/claude-code-config/skills/frontend-patterns .claude/skills/frontend-patterns $ npx degit OrdinaryUsr/claude-code-config/skills/iterative-retrieval .claude/skills/iterative-retrieval $ npx degit OrdinaryUsr/claude-code-config/skills/js-coding-standards .claude/skills/js-coding-standards $ npx degit OrdinaryUsr/claude-code-config/skills/mcp-server-patterns .claude/skills/mcp-server-patterns $ npx degit OrdinaryUsr/claude-code-config/skills/nextjs-turbopack .claude/skills/nextjs-turbopack $ npx degit OrdinaryUsr/claude-code-config/skills/postgres-patterns .claude/skills/postgres-patterns $ npx degit OrdinaryUsr/claude-code-config/skills/python-patterns .claude/skills/python-patterns $ npx degit OrdinaryUsr/claude-code-config/skills/python-testing .claude/skills/python-testing $ npx degit OrdinaryUsr/claude-code-config/skills/pytorch-patterns .claude/skills/pytorch-patterns $ npx degit OrdinaryUsr/claude-code-config/skills/quality-nonconformance .claude/skills/quality-nonconformance $ npx degit OrdinaryUsr/claude-code-config/skills/ralphinho-rfc-pipeline .claude/skills/ralphinho-rfc-pipeline $ npx degit OrdinaryUsr/claude-code-config/skills/regex-vs-llm-structured-text .claude/skills/regex-vs-llm-structured-text $ npx degit OrdinaryUsr/claude-code-config/skills/safety-guard .claude/skills/safety-guard $ npx degit OrdinaryUsr/claude-code-config/skills/santa-method .claude/skills/santa-method $ npx degit OrdinaryUsr/claude-code-config/skills/search-first .claude/skills/search-first $ npx degit OrdinaryUsr/claude-code-config/skills/security-review .claude/skills/security-review $ npx degit OrdinaryUsr/claude-code-config/skills/strategic-compact .claude/skills/strategic-compact $ npx degit OrdinaryUsr/claude-code-config/skills/tdd-workflow .claude/skills/tdd-workflow $ npx degit OrdinaryUsr/claude-code-config/skills/team-builder .claude/skills/team-builder $ npx degit OrdinaryUsr/claude-code-config/skills/vercel-react-native-skills .claude/skills/vercel-react-native-skills $ npx degit OrdinaryUsr/claude-code-config/skills/verification-loop .claude/skills/verification-loop
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/OrdinaryUsr/claude-code-config/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/OrdinaryUsr/claude-code-config/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/database-reviewer.md https://raw.githubusercontent.com/OrdinaryUsr/claude-code-config/main/agents/database-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/loop-operator.md https://raw.githubusercontent.com/OrdinaryUsr/claude-code-config/main/agents/loop-operator.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/OrdinaryUsr/claude-code-config/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/python-reviewer.md https://raw.githubusercontent.com/OrdinaryUsr/claude-code-config/main/agents/python-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/OrdinaryUsr/claude-code-config/main/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/OrdinaryUsr/claude-code-config/main/agents/tdd-guide.md $ curl -fsSL --create-dirs -o .claude/agents/typescript-reviewer.md https://raw.githubusercontent.com/OrdinaryUsr/claude-code-config/main/agents/typescript-reviewer.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": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(**/.env.*)",
"Read(**/secrets/**)",
"Read(**/*.pem)",
"Read(**/*.key)",
"Read(**/id_rsa)",
"Read(**/id_ed25519)",
"Read(**/.aws/credentials)",
"Read(~/.ssh/**)",
"Read(~/.gnupg/**)",
"Read(~/.aws/**)",
"Read(~/.azure/**)",
"Read(~/.kube/**)",
"Read(~/.docker/config.json)",
"Read(~/.npmrc)",
"Read(~/.npm/**)",
"Read(~/.pypirc)",
"Read(~/.gem/credentials)",
"Read(~/.git-credentials)",
"Read(~/.config/gh/**)",
"Read(~/.netrc)",
"Edit(~/.bashrc)",
"Edit(~/.zshrc)",
"Edit(~/.zshenv)",
"Edit(~/.zprofile)",
"Edit(~/.bash_profile)",
"Edit(~/.profile)",
"Write(~/.bashrc)",
"Write(~/.zshrc)",
"Write(~/.zshenv)",
"Write(~/.zprofile)",
"Write(~/.bash_profile)",
"Write(~/.profile)",
"Bash(sudo:*)",
"Bash(git push:*)"
]
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "python3 ~/.claude/hooks/allow-readonly-bash.py"
}
]
}
]
}
} Skills (36)
api-designarticle-writingautonomous-loopsbackend-patternscodebase-onboardingcontinuous-agent-loopcost-aware-llm-pipelinedatabase-migrationsdeep-researchdeployment-patternsdesign-systemdeveloper-device-platform-basicsdocker-patternseval-harnessfind-skillsfrontend-patternsiterative-retrievalcoding-standardsmcp-server-patternsnextjs-turbopackpostgres-patternspython-patternspython-testingpytorch-patternsquality-nonconformanceralphinho-rfc-pipelineregex-vs-llm-structured-textsafety-guardsanta-methodsearch-firstsecurity-reviewstrategic-compacttdd-workflowteam-buildervercel-react-native-skillsverification-loop
Subagents (9)
| architect model: opus | Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions |
| code-reviewer model: sonnet | Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes. |
| database-reviewer model: sonnet | PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database p |
| loop-operator model: sonnet | Operate autonomous agent loops, monitor progress, and intervene safely when loops stall. |
| planner model: opus | Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for p |
| python-reviewer model: sonnet | Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects. |
| security-reviewer model: sonnet | Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injectio |
| tdd-guide model: sonnet | Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage. |
| typescript-reviewer model: sonnet | Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all TypeScript and JavaScript code changes. MUST BE USED f |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | python3 ~/.claude/hooks/allow-readonly-bash.py |
Slash commands (1)
/commit
Plugins (7)
pyright-lsp@claude-plugins-officialtypescript-lsp@claude-plugins-officialfrontend-design@claude-plugins-officialsuperpowers@claude-plugins-officialcode-simplifier@claude-plugins-officialsecurity-guidance@claude-plugins-officialclaude-md-management@claude-plugins-official
Permissions
deny (37)
Read(./.env)
Read(./.env.*)
Read(**/.env)
Read(**/.env.*)
Read(**/secrets/**)
Read(**/*.pem)
Read(**/*.key)
Read(**/id_rsa)
Read(**/id_ed25519)
Read(**/.aws/credentials)
Read(~/.ssh/**)
Read(~/.gnupg/**)
Read(~/.aws/**)
Read(~/.azure/**)
Read(~/.kube/**)
Read(~/.docker/config.json)
Read(~/.npmrc)
Read(~/.npm/**)
Read(~/.pypirc)
Read(~/.gem/credentials)
Read(~/.git-credentials)
Read(~/.config/gh/**)
Read(~/.netrc)
Edit(~/.bashrc)
Edit(~/.zshrc)
Edit(~/.zshenv)
Edit(~/.zprofile)
Edit(~/.bash_profile)
Edit(~/.profile)
Write(~/.bashrc)
Write(~/.zshrc)
Write(~/.zshenv)
Write(~/.zprofile)
Write(~/.bash_profile)
Write(~/.profile)
Bash(sudo:*)
Bash(git push:*)
ask (0)
—
allow (77)
Bash(echo:*)
Bash(ls:*)
Bash(cd:*)
Bash(cat:*)
Bash(head:*)
Bash(tail:*)
Bash(grep:*)
Bash(rg:*)
Bash(find:*)
Bash(fd:*)
Bash(wc:*)
Bash(sed:*)
Bash(awk:*)
Bash(cut:*)
Bash(sort:*)
Bash(uniq:*)
Bash(tr:*)
Bash(diff:*)
Bash(file:*)
Bash(stat:*)
Bash(tree:*)
Bash(xargs:*)
Bash(jq:*)
Bash(isort:*)
Bash(black:*)
Bash(pyright:*)
Bash(pytest:*)
Bash(eslint:*)
Bash(tsc:*)
Bash(jest:*)
Bash(vitest:*)
Bash(prettier:*)
Bash(biome:*)
Bash(npm run lint:*)
Bash(npm run test:*)
Bash(npm test:*)
Bash(npm run typecheck:*)
Bash(npm run type-check:*)
Bash(npm run tsc:*)
Bash(npm run format:*)
Bash(npm run jest:*)
Bash(npm run vitest:*)
Bash(npx eslint:*)
Bash(npx tsc:*)
Bash(npx jest:*)
Bash(npx vitest:*)
Bash(npx prettier:*)
Bash(npx biome:*)
Bash(yarn lint:*)
Bash(yarn test:*)
Bash(yarn typecheck:*)
Bash(yarn type-check:*)
Bash(yarn tsc:*)
Bash(yarn format:*)
Bash(yarn jest:*)
Bash(yarn vitest:*)
Bash(yarn eslint:*)
Bash(yarn prettier:*)
Bash(pnpm lint:*)
Bash(pnpm test:*)
Similar rigs
xu-xiang/everything-claude-code-zh
everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic 黑客松获胜者的实战配置，助力中文工程师高效理解与使用 Claude Code。
Orchestrator 28.2k tok ·
reevesc88/jarvis-cc-public
✨ Start building with Claude Code or Codex. Beginner-friendly skills, specialist agents and setup checks by AI1AU Solutions.
Orchestrator 3.3k tok ·
eugenezhangco-spec/foreman
A 14-agent engineering team for Claude Code. Plans before it builds, reviews before it ships, and never says 'it works' without proof.
Skill Collector 8.5k tok ·
ndhananj/codex-agent-setup
A set up agent frameworks based on "affaan/everything-claude-code"
Orchestrator 2.2k tok ·