RohiRIK/claude-code-config
Personal Claude Code global config — hooks, agents, skills, commands
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
Copy this rig
# review before running: this installs third-party code $ npx degit RohiRIK/claude-code-config/agents ./rig-claude-code-config/agents $ npx degit RohiRIK/claude-code-config/commands ./rig-claude-code-config/commands $ npx degit RohiRIK/claude-code-config/skills ./rig-claude-code-config/skills $ npx degit RohiRIK/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 RohiRIK/claude-code-config/skills/PreCommitSanitize .claude/skills/PreCommitSanitize $ npx degit RohiRIK/claude-code-config/skills/WorkflowGuide .claude/skills/WorkflowGuide
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/build-error-resolver.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/build-error-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/code-simplifier.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/code-simplifier.md $ curl -fsSL --create-dirs -o .claude/agents/database-reviewer.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/database-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/doc-updater.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/doc-updater.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-runner.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/e2e-runner.md $ curl -fsSL --create-dirs -o .claude/agents/intune-summarizer.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/intune-summarizer.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/python-reviewer.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/python-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/security-reviewer.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/security-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/RohiRIK/claude-code-config/main/agents/tdd-guide.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "tool == \"Skill\"",
"hooks": [
{
"type": "command",
"command": "bun ~/.claude/hooks/SkillGuard/SkillGuard.ts"
}
]
},
{
"matcher": "tool == \"Bash\" && tool_input.command matches \"git \"",
"hooks": [
{
"type": "command",
"command": "bun ~/.<redacted>.ts"
}
]
},
{
"matcher": "tool == \"Bash\" && tool_input.command matches \"(npm run dev|pnpm( run)? dev|yarn dev|bun run dev)\"",
"hooks": [
{
"type": "command",
"command": "bun ~/.claude/hooks/DevServerBlocker/DevServerBlocker.ts"
}
]
},
{
"matcher": "tool == \"Bash\" && tool_input.command matches \"(npm (install|test)|pnpm (install|test)|yarn (install|test)|bun (install|t",
"hooks": [
{
"type": "command",
"command": "bun ~/.claude/hooks/TmuxSuggest/TmuxSuggest.ts"
}
]
},
{
"matcher": "tool == \"Write\" && tool_input.file_path matches \"\\\\.(md|txt)$\" && !(tool_input.file_path matches \"README\\\\.md|CLAUDE\\\\.m",
"hooks": [
{
"type": "command",
"command": "bun ~/.claude/hooks/WriteBlocker/WriteBlocker.ts"
}
]
},
{
"matcher": "tool == \"Edit\" || tool == \"Write\"",
"hooks": [
{
"type": "command",
"command": "bun ~/.claude/hooks/SuggestCompact/SuggestCompact.ts"
}
]
}
]
}
} Skills (2)
Subagents (13)
| 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 |
| build-error-resolver model: opus | Build and TypeScript error resolution. Use PROACTIVELY when build fails or type errors occur. Minimal diffs only, no architectural edits — green build fast. |
| code-reviewer model: opus | General code review for quality and maintainability, immediately after writing or modifying code. Routes: Python changes → python-reviewer; security-sensitive code → security-reviewer; post-impl clean |
| code-simplifier model: opus | Post-implementation cleanup. Use PROACTIVELY after completing a feature or fix. Simplifies and verifies changed files only — not repo-wide (use refactor-cleaner for that). |
| 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 |
| doc-updater model: opus | Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides. |
| e2e-runner model: opus | Playwright E2E specialist. Use PROACTIVELY to generate, maintain, and run E2E tests. Quarantines flaky tests, uploads artifacts, keeps critical user flows green. |
| intune-summarizer model: sonnet | Summarizes Intune screenshots, policy exports, or config text into structured Monday.com/Notion updates. Use when Intune content needs to be shared with the team. |
| planner model: opus | Codebase-driven planning for complex features and refactoring — plans from code exploration alone. For memory-informed planning that recalls past LTM decisions first, use openltm:planner instead. |
| 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. |
| refactor-cleaner model: opus | Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely r |
| security-reviewer model: opus | Security review specialist. Use PROACTIVELY after writing code handling user input, auth, APIs, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, OWASP Top 10. |
| tdd-guide model: opus | Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage. |
Hooks (14)
| event | matcher | runs |
|---|---|---|
| PreToolUse | tool == "Skill" | bun ~/.claude/hooks/SkillGuard/SkillGuard.ts |
| PreToolUse | tool == "Bash" && tool_input.command matches "git " | bun ~/.<redacted>.ts |
| PreToolUse | tool == "Bash" && tool_input.command matches "(npm run dev|pnpm( run)? dev|yarn dev|bun run dev)" | bun ~/.claude/hooks/DevServerBlocker/DevServerBlocker.ts |
| PreToolUse | tool == "Bash" && tool_input.command matches "(npm (install|test)|pnpm (install|test)|yarn (install|test)|bun (install|t | bun ~/.claude/hooks/TmuxSuggest/TmuxSuggest.ts |
| PreToolUse | tool == "Write" && tool_input.file_path matches "\\.(md|txt)$" && !(tool_input.file_path matches "README\\.md|CLAUDE\\.m | bun ~/.claude/hooks/WriteBlocker/WriteBlocker.ts |
| PreToolUse | tool == "Edit" || tool == "Write" | bun ~/.claude/hooks/SuggestCompact/SuggestCompact.ts |
| UserPromptSubmit | * | bun ~/.claude/hooks/SessionAutoName/SessionAutoName.ts |
| UserPromptSubmit | * | bun ~/.claude/hooks/PrePlan/PrePlan.ts |
| PostToolUse | tool == "Bash" | bun ~/.claude/hooks/PRDetect/PRDetect.ts |
| PostToolUse | tool == "Edit" && tool_input.file_path matches "\\.(ts|tsx|js|jsx)$" | bun ~/.claude/hooks/PostEditCheck/PostEditCheck.ts |
| PostToolUse | tool == "Edit" || tool == "Write" | bun ~/.<redacted>.ts |
| Stop | * | bun ~/.claude/hooks/Cleanup/Cleanup.ts |
| SessionStart | * | "~/.claude/hooks/context-mode-cache-heal.mjs" |
| SessionStart | * | bun ~/.claude/hooks/SkillsMountCheck/SkillsMountCheck.ts |
Slash commands (7)
/code-review/commit-push-pr/dev/e2e/plan/test-coverage/update-docs
Plugins (3)
context-mode@context-modecaveman@cavemanopenltm@OpenLtm
Permissions
deny (0)
—
ask (0)
—
allow (1)
mcp__plugin_openltm_memory
Similar rigs
Yuutokata/claude-code-setup
🔄 One Claude Code setup for my desktop and MacBook, synced through git, with guardrails that keep secrets out.
Fort Knox 1.1k tok ·
cfrs2005/claude-init
Claude Code 中文开发套件 - 为中国开发者定制的零门槛 AI 编程环境。一键安装完整中文化体验，集成 MCP 服务器、智能上下文管理、安全扫描，支持免翻墙访问。让 AI 编程更简单。
Orchestrator 1.5k tok ·
mh2-lee/everything-claude-code
Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
Orchestrator 1.2k tok ·
hirokami3/everything-claude-code
Claude Code configs collection - agents, skills, hooks, commands, rules, and MCP configurations
Orchestrator 1.2k tok ·