~ / rigs / xhqing / agents-infra

xhqing/agents-infra

Shared infrastructure for a pi agent fleet: global rules, skills, extensions, helper scripts and docs mirrored byte-for-byte from ~/.pi/agent, plus the configs of the terminal apps the agents run in (ghostty, cmux). | pi 智能体舰队的共享基础设施:全局规则、技

↗ GitHub ★ 1 MIT updated 1d ago project Claude CodeCodex
field: unknown workflow: Git & commitsDocsCI/CD & deploy
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~18.4k tokens
Context hog · 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 xhqing/agents-infra/.claude ./rig-agents-infra  # 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 xhqing/agents-infra/.claude/skills/capability-manager .claude/skills/capability-manager
$ npx degit xhqing/agents-infra/pi/agent/skills/add .claude/skills/add
$ npx degit xhqing/agents-infra/pi/agent/skills/agent-reach .claude/skills/agent-reach
$ npx degit xhqing/agents-infra/pi/agent/skills/anysearch .claude/skills/anysearch
$ npx degit xhqing/agents-infra/pi/agent/skills/backup .claude/skills/backup
$ npx degit xhqing/agents-infra/pi/agent/skills/bump .claude/skills/bump
$ npx degit xhqing/agents-infra/pi/agent/skills/commit .claude/skills/commit
$ npx degit xhqing/agents-infra/pi/agent/skills/dev-workflow .claude/skills/dev-workflow
$ npx degit xhqing/agents-infra/pi/agent/skills/icon-design .claude/skills/icon-design
$ npx degit xhqing/agents-infra/pi/agent/skills/image-ocr .claude/skills/image-ocr
$ npx degit xhqing/agents-infra/pi/agent/skills/keep-awake .claude/skills/keep-awake
$ npx degit xhqing/agents-infra/pi/agent/skills/macmini-use .claude/skills/macmini-use
$ npx degit xhqing/agents-infra/pi/agent/skills/md2pdf .claude/skills/md2pdf
$ npx degit xhqing/agents-infra/pi/agent/skills/release .claude/skills/release
$ npx degit xhqing/agents-infra/pi/agent/skills/skill-creator .claude/skills/skill-creator

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 (15)

Similar rigs

copied ✓