~ / rigs / anhle9x / ai-worker

anhle9x/ai-worker

See how your company uses Claude and its helper assistants, live, on one board. Claude Code plugin + self-hosted Python/SQLite server.

↗ GitHub ★ 0 MIT updated today project Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~2.1k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit anhle9x/ai-worker/agents ./rig-ai-worker/agents
$ npx degit anhle9x/ai-worker/commands ./rig-ai-worker/commands
$ npx degit anhle9x/ai-worker/skills ./rig-ai-worker/skills
$ npx degit anhle9x/ai-worker/hooks ./rig-ai-worker/hooks

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 anhle9x/ai-worker/skills/browser-testing-with-devtools .claude/skills/browser-testing-with-devtools
$ npx degit anhle9x/ai-worker/skills/codebase-design .claude/skills/codebase-design
$ npx degit anhle9x/ai-worker/skills/diagnosing-bugs .claude/skills/diagnosing-bugs
$ npx degit anhle9x/ai-worker/skills/domain-modeling .claude/skills/domain-modeling
$ npx degit anhle9x/ai-worker/skills/draw-flow .claude/skills/draw-flow
$ npx degit anhle9x/ai-worker/skills/grilling .claude/skills/grilling
$ npx degit anhle9x/ai-worker/skills/handoff .claude/skills/handoff
$ npx degit anhle9x/ai-worker/skills/improve-codebase-architecture .claude/skills/improve-codebase-architecture
$ npx degit anhle9x/ai-worker/skills/interview-me .claude/skills/interview-me
$ npx degit anhle9x/ai-worker/skills/lesson-generator .claude/skills/lesson-generator
$ npx degit anhle9x/ai-worker/skills/make-skill .claude/skills/make-skill
$ npx degit anhle9x/ai-worker/skills/meeting-notes .claude/skills/meeting-notes
$ npx degit anhle9x/ai-worker/skills/qa-site .claude/skills/qa-site
$ npx degit anhle9x/ai-worker/skills/qa-test .claude/skills/qa-test
$ npx degit anhle9x/ai-worker/skills/security-audit .claude/skills/security-audit
$ npx degit anhle9x/ai-worker/skills/tdd .claude/skills/tdd
$ npx degit anhle9x/ai-worker/skills/ui-ux-pro-max .claude/skills/ui-ux-pro-max
$ npx degit anhle9x/ai-worker/skills/write-spec .claude/skills/write-spec
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/anhle9x/ai-worker/main/agents/planner.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 (18)

Subagents (1)

planner
model: opus
Plan a big decision that is hard to undo: security, architecture, data policy. Call it only after the user has agreed in the conversation. It only reads and looks things up, never changes anything; it

Slash commands (6)

/board/help/office-pane/office/update/voice

Similar rigs

copied ✓