/install agent-team-pipeline
Agent Team Pipeline
Overview
Coordinate OpenClaw as the brain dispatching multiple Codex instances in parallel: one for coding, one for testing, one for code review. Each agent works in an isolated git worktree to avoid conflicts.
When to Use
- Need to implement a feature with separate code/test/review phases
- Want parallel execution of independent tasks
- Building a mini development team workflow
Not for:
- Single simple tasks (use single agent)
- Exploratory discussions requiring multi-round dialogue
Core Pattern
User → OpenClaw (brain) → Codex Coder → Codex Tester → Codex Reviewer
→ Codex Tester (parallel)
→ Codex Reviewer (parallel)
Setup
1. Create Isolated Worktrees
cd /Users/liuchang/.openclaw/workspace
git worktree add -b coder /Users/liuchang/agent-coder HEAD
git worktree add -b tester /Users/liuchang/agent-tester HEAD
git worktree add -b reviewer /Users/liuchang/agent-reviewer HEAD
2. Task Distribution Script
#!/bin/bash
CODER_DIR="/Users/liuchang/agent-coder"
TESTER_DIR="/Users/liuchang/agent-tester"
REVIEWER_DIR="/Users/liuchang/agent-reviewer"
case "$1" in
coder)
cd "$CODER_DIR" && codex exec "$2"
;;
tester)
cd "$TESTER_DIR" && codex exec "$2"
;;
reviewer)
cd "$REVIEWER_DIR" && codex exec "$2"
;;
esac
3. Workflow
- Coder receives task, writes code to
agent-coder/ - Tester receives code, writes tests to
agent-tester/ - Reviewer reviews code, provides feedback
- Loop: Coder addresses feedback → Reviewer confirms
Quick Reference
| Role | Worktree | Command |
|---|---|---|
| Coder | agent-coder |
codex exec "implement X" |
| Tester | agent-tester |
codex exec "test X" |
| Reviewer | agent-reviewer |
codex exec "review X" |
Example
# Coder: Implement feature
codex exec "创建登录功能,使用 JWT"
# Tester: Write tests
codex exec "为 ../agent-coder/login.py 写测试"
# Reviewer: Review code
codex exec "审查 ../agent-coder/login.py"
Common Mistakes
- No worktree isolation → Use git worktree to prevent file conflicts
- Sequential when parallel → Coder+Tester+Reviewer can run in parallel
- Skipping review loop → Always verify fixes with reviewer before accepting
Real-World Impact
Successfully implemented hello.py example:
- Coder created initial code
- Tester wrote pytest file
- Reviewer suggested main() +
__main__protection - Coder applied fixes
- Reviewer confirmed compliance
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-team-pipeline - After installation, invoke the skill by name or use
/agent-team-pipeline - Provide required inputs per the skill's parameter spec and get structured output
What is Agent Team Pipeline?
Use when needing to coordinate multiple AI agents in parallel for code development, testing, and review. It is an AI Agent Skill for Claude Code / OpenClaw, with 222 downloads so far.
How do I install Agent Team Pipeline?
Run "/install agent-team-pipeline" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent Team Pipeline free?
Yes, Agent Team Pipeline is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Agent Team Pipeline support?
Agent Team Pipeline is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent Team Pipeline?
It is built and maintained by liuchang (@liuchang8877); the current version is v1.0.0.