ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit gaborbernat/dotfiles/private_dot_claude ./rig-dotfiles # inspect, then merge into .claude/ 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 gaborbernat/dotfiles/dot_agents/skills/brief .claude/skills/brief $ npx degit gaborbernat/dotfiles/dot_agents/skills/commit-pr .claude/skills/commit-pr $ npx degit gaborbernat/dotfiles/dot_agents/skills/commit .claude/skills/commit $ npx degit gaborbernat/dotfiles/dot_agents/skills/drift .claude/skills/drift $ npx degit gaborbernat/dotfiles/dot_agents/skills/fb .claude/skills/fb $ npx degit gaborbernat/dotfiles/dot_agents/skills/no-slop .claude/skills/no-slop $ npx degit gaborbernat/dotfiles/dot_agents/skills/pr .claude/skills/pr $ npx degit gaborbernat/dotfiles/dot_agents/skills/rev .claude/skills/rev $ npx degit gaborbernat/dotfiles/dot_agents/skills/revr .claude/skills/revr $ npx degit gaborbernat/dotfiles/dot_agents/skills/sec .claude/skills/sec $ npx degit gaborbernat/dotfiles/dot_agents/skills/simp .claude/skills/simp $ npx degit gaborbernat/dotfiles/dot_agents/skills/style .claude/skills/style
$ curl -fsSL --create-dirs -o .claude/agents/haiku-impl.md https://raw.githubusercontent.com/gaborbernat/dotfiles/main/private_dot_claude/agents/haiku-impl.md $ curl -fsSL --create-dirs -o .claude/agents/opus-review.md https://raw.githubusercontent.com/gaborbernat/dotfiles/main/private_dot_claude/agents/opus-review.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (12)
Subagents (2)
| haiku-impl model: claude-haiku-5-5 | Mechanical implementation, search and lookup work handed off by the main session. Use for edits whose design is already decided, file searches, and fact lookups; never for review or validation. |
| opus-review model: claude-opus-5-5 | Fresh-context reviewer, finding validator, docs auditor or fresh reader. Reports findings with evidence; may write reproducer tests as scratch but never edits tracked files. |
Similar rigs
ramarlina/agx
agx: Run AI coding agents as a persistent team with objectives, memory, and coordinated work. The same agents built this tool — 167+ merged PRs, 93% clean.
Minimalist 167 tok · · Q0
dirien/my-claude-apm-setup
A self-contained APM-managed Claude Code + Codex setup — pinned skills, agents, guardrail hooks, MCP, LSP, and single-source generated context.
Pragmatist 669 tok · · Q0
jasonlong/dotfiles
Files. With dots in front of them.
Pragmatist 336 tok · · Q0
nickineering/setup
My personal mac setup
Pragmatist 674 tok · · Q0