Nowely/agent-skills
Run Codex as a Claude Code subagent with rights declared per call — read-only analysis, or writing and running tests inside a git worktree — and an exit code that reflects what actually ran.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/Nowely/agent-skills 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 Nowely/agent-skills/plugins/entrust/plugin/skills/advisor .claude/skills/advisor $ npx degit Nowely/agent-skills/plugins/entrust/plugin/skills/cleanup .claude/skills/cleanup $ npx degit Nowely/agent-skills/plugins/entrust/plugin/skills/codex .claude/skills/codex $ npx degit Nowely/agent-skills/plugins/entrust/plugin/skills/opencode .claude/skills/opencode $ npx degit Nowely/agent-<redacted> .claude/skills/orchestrate $ npx degit Nowely/agent-skills/plugins/entrust/plugin/skills/prepare-feedback .claude/skills/prepare-feedback $ npx degit Nowely/agent-skills/plugins/entrust/plugin/skills/swarm .claude/skills/swarm $ npx degit Nowely/agent-skills/plugins/terse/plugin/skills/audit .claude/skills/audit $ npx degit Nowely/agent-skills/plugins/terse/plugin/skills/clarity .claude/skills/clarity $ npx degit Nowely/agent-skills/plugins/terse/plugin/skills/rethink .claude/skills/rethink $ npx degit Nowely/agent-skills/plugins/terse/plugin/skills/rewrite .claude/skills/rewrite
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 (11)
Similar rigs
snaplyze/claude-orchestration
Claude Code plugin for orchestration: five specialist subagents with explicit model and effort, subscription profiles, user-scope install, and runtime verification
Pragmatist 3.2k tok ·
darkroomengineering/cc-settings
Claude Code configuration — agents, skills, hooks & settings for Darkroom Engineering
Skill Collector 9.9k tok ·
quisbaum-prog/occam
Occam's razor for Claude Code and Codex: a 30-line rule set. Benchmarks vs base: 51-55% lower estimated task cost on Opus/Sonnet 5.5 max with more tests passed. 8.3% fewer tokens in a Sol 6.1 max pilot. Raw data, Docker setup and comparison
Minimalist 67 tok ·
fALECX/agentic-harness-tips
Claude Code setup tips: one tip, one picture, one snippet — plus a plugin that audits your repo against the list.
Minimalist 393 tok ·