martinliworking-debug/claude-config-public
A complete working Claude Code setup: global CLAUDE.md, hooks, statusline, orchestration subagents, 26 skills, MCP templates
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 martinliworking-debug/claude-config-public/agents ./rig-claude-config-public/agents $ npx degit martinliworking-debug/claude-config-public/skills ./rig-claude-config-public/skills $ npx degit martinliworking-debug/claude-config-public/hooks ./rig-claude-config-public/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 martinliworking-debug/claude-config-public/skills/agents-sdk .claude/skills/agents-sdk $ npx degit martinliworking-debug/claude-config-public/skills/archify .claude/skills/archify $ npx degit martinliworking-debug/claude-config-public/skills/brainstorming .claude/skills/brainstorming $ npx degit martinliworking-debug/claude-config-public/skills/cloudflare-email-service .claude/skills/cloudflare-email-service $ npx degit martinliworking-debug/claude-config-public/skills/cloudflare-one-migrations .claude/skills/cloudflare-one-migrations $ npx degit martinliworking-debug/claude-config-public/skills/cloudflare-one .claude/skills/cloudflare-one $ npx degit martinliworking-debug/claude-config-public/skills/cloudflare .claude/skills/cloudflare $ npx degit martinliworking-debug/claude-config-public/skills/documents .claude/skills/documents $ npx degit martinliworking-debug/claude-config-public/skills/durable-objects .claude/skills/durable-objects $ npx degit martinliworking-debug/claude-config-public/skills/find-skills .claude/skills/find-skills $ npx degit martinliworking-debug/claude-config-public/skills/frontend-slides .claude/skills/frontend-slides $ npx degit martinliworking-debug/claude-config-public/skills/impeccable .claude/skills/impeccable $ npx degit martinliworking-debug/claude-config-public/skills/markitdown .claude/skills/markitdown $ npx degit martinliworking-debug/claude-config-public/skills/officecli .claude/skills/officecli $ npx degit martinliworking-debug/claude-config-public/skills/planning-with-files .claude/skills/planning-with-files $ npx degit martinliworking-debug/claude-config-public/skills/playwright-cli .claude/skills/playwright-cli $ npx degit martinliworking-debug/claude-config-public/skills/publish-to-web .claude/skills/publish-to-web $ npx degit martinliworking-debug/claude-config-public/skills/sandbox-sdk .claude/skills/sandbox-sdk $ npx degit martinliworking-debug/claude-config-public/skills/skill-creator .claude/skills/skill-creator $ npx degit martinliworking-debug/claude-config-public/skills/skill-vetter .claude/skills/skill-vetter $ npx degit martinliworking-debug/claude-config-public/skills/stop-slop .claude/skills/stop-slop $ npx degit martinliworking-debug/claude-config-public/skills/theme-factory .claude/skills/theme-factory $ npx degit martinliworking-debug/claude-config-public/skills/turnstile-spin .claude/skills/turnstile-spin $ npx degit martinliworking-debug/claude-config-public/skills/web-perf .claude/skills/web-perf $ npx degit martinliworking-debug/claude-config-public/skills/workers-best-practices .claude/skills/workers-best-practices $ npx degit martinliworking-debug/claude-config-public/skills/wrangler .claude/skills/wrangler
$ curl -fsSL --create-dirs -o .claude/agents/deep-reasoner.md https://raw.githubusercontent.com/martinliworking-debug/claude-config-public/main/agents/deep-reasoner.md $ curl -fsSL --create-dirs -o .claude/agents/fast-worker.md https://raw.githubusercontent.com/martinliworking-debug/claude-config-public/main/agents/fast-worker.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 (26)
agents-sdkarchifybrainstormingcloudflare-email-servicecloudflare-one-migrationscloudflare-onecloudflaredocumentsdurable-objectsfind-skillsfrontend-slidesimpeccablemarkitdownofficecliplanning-with-filesplaywright-clipublish-to-websandbox-sdkskill-creatorskill-vetterstop-sloptheme-factoryturnstile-spinweb-perfworkers-best-practiceswrangler
Subagents (2)
| deep-reasoner model: claude-opus-5 | Use this agent only for reasoning-intensive phases. Focus on analysis, architecture, planning, and difficult problem solving. Use proactively for context-heavy sub-investigations that must stay out of |
| fast-worker model: claude-opus-5 | Use this agent for mechanical implementation tasks, boilerplate generation, refactoring, testing, and routine execution. Use proactively when implementation is parallelisable or multi-file with a clea |
Hooks (5)
| event | matcher | runs |
|---|---|---|
| SessionStart | startup | git -C ~/.claude pull --rebase --autostash --quiet 2>&1 | head -5 |
| SessionEnd | * | bash ~/.claude/hooks/auto-backup.sh |
| PostToolUse | Bash|PowerShell|mcp__excel__excel_write_to_sheet|mcp__excel__excel_create_table | bash "$HOME/.claude/hooks/validate-workbook.sh" |
| PostToolUse | Edit|Write|MultiEdit | node "$HOME/.claude/skills/impeccable/scripts/hook.mjs" |
| Stop | * | powershell.exe -NoProfile -ExecutionPolicy Bypass -File "$HOME/.claude/hooks/commit-reminder.ps1" |
Plugins (3)
andrej-karpathy-skills@karpathy-skillscodex@openai-codexmattpocock-skills@mattpocock
Permissions
deny (0)
—
ask (0)
—
allow (7)
Bash(tasklist*)
Bash(where *)
Bash(npm view *)
mcp__claude_ai_Gmail__search_threads
mcp__claude_ai_Google_Drive__search_files
mcp__claude_ai_Gmail__get_thread
mcp__claude_ai_Google_Drive__read_file_content
Similar rigs
Jxck/dotfiles
dotfiles
Skill Collector 14.2k tok ·
adrienlupo/Claude-code-config
CLAUDE.md, Skills, Commands, Agents...
Skill Collector 2.1k tok ·
heshengtao/super-agent-party
⭐ All-in-one AI companion! Super Agent Party = Self hosted neuro sama + openclaw! ⭐ 全能AI伴侣！超级智能体派对 = 自托管neuro sama + openclaw!
Minimalist 1.6k tok ·
ArthurDanjou/ai-sync-dotfiles
One source of truth for MCP servers, skills and slash commands across Claude Code, OpenCode, Codex, Zed and more — plus classic dotfiles.
Skill Collector 13.1k tok ·