clunny/clm
Declare the intent. AI builds the code to match. CLM keeps it matching.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit clunny/clm/.claude ./rig-clm # 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 clunny/clm/plugin/skills/configure .claude/skills/configure $ npx degit clunny/clm/plugin/skills/contribution .claude/skills/contribution $ npx degit clunny/clm/plugin/skills/health .claude/skills/health $ npx degit clunny/clm/plugin/skills/help .claude/skills/help $ npx degit clunny/clm/plugin/skills/init .claude/skills/init $ npx degit clunny/clm/plugin/skills/propose .claude/skills/propose $ npx degit clunny/clm/plugin/skills/triage .claude/skills/triage $ npx degit clunny/clm/plugin/skills/upgrade .claude/skills/upgrade $ npx degit clunny/clm/plugin/skills/verify .claude/skills/verify
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 (9)
Plugins (2)
clm@clmclm-panel@clm
Permissions
deny (0)
—
ask (0)
—
allow (30)
Bash(cargo *)
Bash(npm ci *)
Bash(npm install --ignore-scripts *)
Bash(npm run *)
Bash(npm test *)
Bash(npx playwright test *)
Bash(.github/scripts/ci-check.sh)
Bash(.github/scripts/ci-check.sh *)
Bash(clm apply)
Bash(clm apply *)
Bash(clm branch)
Bash(clm branch *)
Bash(clm check)
Bash(clm check *)
Bash(clm claim)
Bash(clm claim *)
Bash(clm defect)
Bash(clm defect *)
Bash(clm gate)
Bash(clm gate *)
Bash(clm land)
Bash(clm land *)
Bash(clm pr)
Bash(clm pr *)
Bash(clm rebase)
Bash(clm rebase *)
Bash(clm verify)
Bash(clm verify *)
Bash(clm workaround)
Bash(clm workaround *)
Similar rigs
Hasegos/keelkit
Claude Code 플러그인. /keelkit:init 한 줄로 CLAUDE.md, .claude/, docs/ 뼈대를 설치하고 프로젝트에 맞게 채운다. 기존 파일은 지우지 않고 합친다.
Minimalist 188 tok · · Q0
agenticnotetaking/arscontexta
Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you think and work, have a conversation and get a complete second brain as markdown files you own.
Skill Collector 846 tok · · Q0
yigitkonur/plugin-sentry
Claude Code plugin: audit, initialize and harden Sentry in any repo. CLI-first on the sentry v4 CLI; every change proven with a live event.
Skill Collector 1.2k tok · · Q3
marin-ai-tech/sdlc
Gates and human approvals for AI coding agents: agents write the code, people make the decisions. Works with Claude Code, Codex, Cursor, Qwen Code, OpenCode, GigaCode.
Skill Collector 1.2k tok · · Q0