wpfleger96/ai-agent-rules
Manage configs for Claude Code, Codex, Gemini CLI, Goose, and Amp from one repo — symlinks, merge pipeline, profile inheritance, cross-machine sync
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/wpfleger96/ai-agent-rules 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 wpfleger96/ai-agent-rules/src/ai_rules/config/profiles/skills/writing-as-will .claude/skills/writing-as-will $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/agents-md .claude/skills/agents-md $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/code-reviewer .claude/skills/code-reviewer $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/continue-crash .claude/skills/continue-crash $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/crossfire .claude/skills/crossfire $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/dev-docs .claude/skills/dev-docs $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/doc-writer .claude/skills/doc-writer $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/handoff .claude/skills/handoff $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/pr-creator .claude/skills/pr-creator $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/prompt-critique .claude/skills/prompt-critique $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/prompt-engineer .claude/skills/prompt-engineer $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/rebase .claude/skills/rebase $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/research .claude/skills/research $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/session-search .claude/skills/session-search $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/test-writer .claude/skills/test-writer $ npx degit wpfleger96/ai-agent-rules/src/ai_rules/config/skills/worktree-cleanup .claude/skills/worktree-cleanup
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 *)"
]
}
} 
