halindrome/cmm-claude-code-setup
Hook-based enforcement layer for codebase-memory-mcp + Claude Code
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit halindrome/cmm-claude-code-setup/.claude ./rig-cmm-claude-code-setup # 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 halindrome/cmm-claude-code-setup/.claude/skills/pr-qa .claude/skills/pr-qa $ npx degit halindrome/cmm-claude-code-setup/skills/cmm-rules .claude/skills/cmm-rules $ npx degit halindrome/cmm-claude-code-setup/skills/ctx-rules .claude/skills/ctx-rules
$ curl -fsSL --create-dirs -o .claude/agents/pr-qa-reviewer.md https://raw.githubusercontent.com/halindrome/cmm-claude-code-setup/main/.claude/agents/pr-qa-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/vbw-architect.md https://raw.githubusercontent.com/halindrome/cmm-claude-code-setup/main/agents/vbw-architect.md $ curl -fsSL --create-dirs -o .claude/agents/vbw-debugger.md https://raw.githubusercontent.com/halindrome/cmm-claude-code-setup/main/agents/vbw-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/vbw-dev.md https://raw.githubusercontent.com/halindrome/cmm-claude-code-setup/main/agents/vbw-dev.md $ curl -fsSL --create-dirs -o .claude/agents/vbw-docs.md https://raw.githubusercontent.com/halindrome/cmm-claude-code-setup/main/agents/vbw-docs.md $ curl -fsSL --create-dirs -o .claude/agents/vbw-lead.md https://raw.githubusercontent.com/halindrome/cmm-claude-code-setup/main/agents/vbw-lead.md $ curl -fsSL --create-dirs -o .claude/agents/vbw-qa.md https://raw.githubusercontent.com/halindrome/cmm-claude-code-setup/main/agents/vbw-qa.md $ curl -fsSL --create-dirs -o .claude/agents/vbw-scout.md https://raw.githubusercontent.com/halindrome/cmm-claude-code-setup/main/agents/vbw-scout.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 (3)
Subagents (8)
| pr-qa-reviewer model: inherit | Read-only PR reviewer for cmm-claude-code-setup. Grounds every finding in GitHub issue acceptance criteria or PR-touched regressions. Produces a Contract Verification table, a 4-axis finding taxonomy, |
| vbw-architect model: inherit | Requirements-to-roadmap agent for project scoping, phase decomposition, and success criteria derivation. |
| vbw-debugger model: inherit | Investigation agent using scientific method for bug diagnosis with full codebase access and persistent debug state. |
| vbw-dev model: inherit | Execution agent with full tool access (denylist-controlled) for implementing plan tasks with atomic commits per task. |
| vbw-docs model: inherit | Documentation agent for READMEs, changelogs, API docs, and guides. Read access to codebase, write access for doc files only. |
| vbw-lead model: inherit | Planning agent that researches, decomposes phases into plans, and self-reviews in one compaction-extended session. |
| vbw-qa model: inherit | Verification agent using goal-backward methodology to validate completed work. Read-only (permissionMode plan). Persists verification results via write-verification.sh through Bash. |
| vbw-scout model: inherit | Research agent for web/doc/codebase scanning and read-only live validation. Writes RESEARCH.md files directly. |
Similar rigs
rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Orchestrator 2.6k tok ·
Yeachan-Heo/oh-my-claudecode
Teams-first Multi-agent orchestration for Claude Code
Orchestrator 14.5k tok ·
alirezarezvani/claude-skills
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, complian
Orchestrator 48.5k tok ·
czlonkowski/n8n-mcp
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
Orchestrator 3.8k tok ·