agentrigs
+ submit rig
~ / rigs / PRFactory-app / agent-team-forge

PRFactory-app/agent-team-forge

Free, local agent-team daemon: your lead agent hands work to Claude Code, Codex, Pi, Cursor and Droid agents that survive crashes. Need tickets, workflow templates, portable agents and teamwork? Add PRFactory → https://app.prfactory.dev

↗ GitHub ★ 4 no license updated today project Claude CodeCodex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~1.6k tokens
Featherweight · 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 PRFactory-app/agent-team-forge/.claude ./rig-agent-team-forge  # 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 PRFactory-app/agent-team-forge/.claude/skills/agent-orchestration .claude/skills/agent-orchestration
$ npx degit PRFactory-app/agent-team-forge/.claude/skills/desktop-visual-qa .claude/skills/desktop-visual-qa
$ npx degit PRFactory-app/agent-team-forge/.claude/skills/external-member-invite .claude/skills/external-member-invite
$ npx degit PRFactory-app/agent-team-forge/.claude/skills/external-member-join .claude/skills/external-member-join

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 (4)

agent-orchestrationdesktop-visual-qaexternal-member-inviteexternal-member-join

Similar rigs

lixuvip/codex-agent-orchestration-skill
Codex agent orchestration skill with adaptive thread thinking, callbacks, QA/review gates, fenced automations, project autopilot, and optional agy/Gemini review.
★ 9 collection Codex 2 skills 19d ago
Minimalist 628 tok ·
codeaholicguy/ai-devkit
The control plane for AI coding agents.
★ 1,639 project Claude Code 28 skills 4d ago
Skill Collector 1.8k tok ·
shengdabai/Tony-Claude-Code-Skills
320+ curated Claude Code skills, 9 agents, 39 commands, sanitized configs & a Codex bridge — auto-indexed from skills/.
★ 2 collection Claude CodeCodexCursor 10 mcp 110 skills 20d ago
MCP Hoarder 124.0k tok ·
yonatangross/orchestkit
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.
★ 286 project Claude CodeCodex 1 mcp 117 skills 4d ago
Skill Collector 10.2k tok ·
copied ✓