agentrigs
+ submit rig
~ / rigs / kingxiaozhe / cm-workflow

kingxiaozhe/cm-workflow

Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors.

↗ GitHub ★ 104 mit updated 4d ago project Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~5.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit kingxiaozhe/cm-workflow/.claude ./rig-cm-workflow  # 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 kingxiaozhe/cm-workflow/skills/cm-ai .claude/skills/cm-ai
$ npx degit kingxiaozhe/cm-workflow/skills/cm-backend-engineer .claude/skills/cm-backend-engineer
$ npx degit kingxiaozhe/cm-workflow/skills/cm-check .claude/skills/cm-check
$ npx degit kingxiaozhe/cm-workflow/skills/cm-contract-engineer .claude/skills/cm-contract-engineer
$ npx degit kingxiaozhe/cm-workflow/skills/cm-database-engineer .claude/skills/cm-database-engineer
$ npx degit kingxiaozhe/cm-workflow/skills/cm-devops-engineer .claude/skills/cm-devops-engineer
$ npx degit kingxiaozhe/cm-workflow/skills/cm-doc-syncer .claude/skills/cm-doc-syncer
$ npx degit kingxiaozhe/cm-workflow/skills/cm-finance-expert .claude/skills/cm-finance-expert
$ npx degit kingxiaozhe/cm-workflow/skills/cm-fix .claude/skills/cm-fix
$ npx degit kingxiaozhe/cm-workflow/skills/cm-frontend-engineer .claude/skills/cm-frontend-engineer
$ npx degit kingxiaozhe/cm-workflow/skills/cm-idea .claude/skills/cm-idea
$ npx degit kingxiaozhe/cm-workflow/skills/cm-init .claude/skills/cm-init
$ npx degit kingxiaozhe/cm-workflow/skills/cm-miniprogram-engineer .claude/skills/cm-miniprogram-engineer
$ npx degit kingxiaozhe/cm-workflow/skills/cm-prd .claude/skills/cm-prd
$ npx degit kingxiaozhe/cm-workflow/skills/cm-product-manager .claude/skills/cm-product-manager
$ npx degit kingxiaozhe/cm-workflow/skills/cm-qa-engineer .claude/skills/cm-qa-engineer
$ npx degit kingxiaozhe/cm-workflow/skills/cm-refactor .claude/skills/cm-refactor
$ npx degit kingxiaozhe/cm-workflow/skills/cm-runtime .claude/skills/cm-runtime
$ npx degit kingxiaozhe/cm-workflow/skills/cm-security .claude/skills/cm-security
$ npx degit kingxiaozhe/cm-workflow/skills/cm-test .claude/skills/cm-test
$ npx degit kingxiaozhe/cm-workflow/skills/cm-ui-engineer .claude/skills/cm-ui-engineer
$ npx degit kingxiaozhe/cm-workflow/skills/codebase-context .claude/skills/codebase-context
$ npx degit kingxiaozhe/cm-workflow/skills/darwin-skill .claude/skills/darwin-skill
$ npx degit kingxiaozhe/cm-workflow/skills/external-expert .claude/skills/external-expert

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "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(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Skills (24)

cm-aicm-backend-engineercm-checkcm-contract-engineercm-database-engineercm-devops-engineercm-doc-syncercm-finance-expertcm-fixcm-frontend-engineercm-ideacm-initcm-miniprogram-engineercm-prdcm-product-managercm-qa-engineercm-refactorcm-runtimecm-securitycm-testcm-ui-engineercodebase-contextdarwin-skillexternal-expert

Similar rigs

Barnett-Studios/cxpak
Spends CPU cycles so you don't spend tokens. The LLM gets a briefing packet instead of a flashlight in a dark room.
★ 28 project Claude Code 3 skills 11d ago
Minimalist 138 tok ·
obra/superpowers
An agentic skills framework & software development methodology that works.
★ 294k project CodexGemini CLI 15 skills 12d ago
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
★ 180k collection Claude Code 19 skills 4d ago
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
★ 149k project Claude Code 10 skills 6d ago
Skill Collector 1.4k tok ·
copied ✓