Team Tasks — Multi-Agent Pipeline Coordination

Features

Requirements

Installation

# Clone the repo
git clone https://github.com/win4r/team-tasks.git
# No pip install needed — it's a standalone script
python3 team-tasks/scripts/task_manager.py --help

cp -r team-tasks/ /path/to/clawd/skills/team-tasks/

Quick Start

Mode A: Linear Pipeline

TM="python3 scripts/task_manager.py"
# 1. Create project with pipeline order
$TM init my-api -g "Build REST API with tests and docs" \
 -p "code-agent,test-agent,docs-agent,monitor-bot"
# 2. Assign tasks to each stage
$TM assign my-api code-agent "Implement Flask REST API: GET/POST/DELETE /items"
$TM assign my-api test-agent "Write pytest tests, target 90%+ coverage"
$TM assign my-api docs-agent "Write README with API docs and examples"
$TM assign my-api monitor-bot "Security audit and deployment readiness check"
# 3. Check what's next
$TM next my-api
# ▶️ Next stage: code-agent
# 4. Dispatch → work → save result → mark done
$TM update my-api code-agent in-progress
# ... agent does work ...
$TM result my-api code-agent "Created app.py with 3 endpoints"
$TM update my-api code-agent done
# ▶️ Next: test-agent (auto-advance!)
# 5. Check progress anytime
$TM status my-api

📋 Project: my-api
🎯 Goal: Build REST API with tests and docs
📊 Status: active | Mode: linear
▶️ Current: test-agent
 ✅ code-agent: done
 Task: Implement Flask REST API
 Output: Created app.py with 3 endpoints
 🔄 test-agent: in-progress
 Task: Write pytest tests, target 90%+ coverage
 ⬜ docs-agent: pending
 ⬜ monitor-bot: pending
 Progress: [██░░] 2/4

Mode B: DAG (Dependency Graph)

TM="python3 scripts/task_manager.py"
# 1. Create DAG project
$TM init my-feature -m dag -g "Build search feature with parallel workstreams"
# 2. Add tasks with dependencies
$TM add my-feature design -a docs-agent --desc "Write API spec"
$TM add my-feature scaffold -a code-agent --desc "Create project skeleton"
$TM add my-feature implement -a code-agent -d "design,scaffold" --desc "Implement API"
$TM add my-feature write-tests -a test-agent -d "design" --desc "Write test cases from spec"
$TM add my-feature run-tests -a test-agent -d "implement,write-tests" --desc "Run all tests"
$TM add my-feature write-docs -a docs-agent -d "implement" --desc "Write final docs"
$TM add my-feature review -a monitor-bot -d "run-tests,write-docs" --desc "Final review"
# 3. Visualize the DAG
$TM graph my-feature

📋 my-feature — DAG Graph
├─ ⬜ design [docs-agent]
│ ├─ ⬜ implement [code-agent]
│ │ ├─ ⬜ run-tests [test-agent]
│ │ │ └─ ⬜ review [monitor-bot]
│ │ └─ ⬜ write-docs [docs-agent]
│ └─ ⬜ write-tests [test-agent]
└─ ⬜ scaffold [code-agent]
 └─ ⬜ implement (↑ see above)
 Progress: [░░░░░░░] 0/7

# 4. Get ready tasks (parallel dispatch!)
$TM ready my-feature
# 🟢 Ready to dispatch (2 tasks):
# 📌 design → agent: docs-agent
# 📌 scaffold → agent: code-agent
# 5. Dispatch both in parallel, then mark done
$TM update my-feature design done
# 🟢 Unblocked: write-tests ← auto-detected!
$TM update my-feature scaffold done
# 🟢 Unblocked: implement
# 6. Continue until all complete
$TM ready my-feature # Shows newly unblocked tasks

Mode C: Debate (Multi-Agent Deliberation)

TM="python3 scripts/task_manager.py"
# 1. Create debate project
$TM init security-review --mode debate \
 -g "Review auth module for security vulnerabilities"
# 2. Add debaters with roles/perspectives
$TM add-debater security-review code-agent --role "security expert focused on injection attacks"
$TM add-debater security-review test-agent --role "QA engineer focused on edge cases"
$TM add-debater security-review monitor-bot --role "ops engineer focused on deployment risks"
# 3. Start initial round
$TM round security-review start
# 🗣️ Debate Round 1 (initial) started
# Outputs dispatch prompts for each debater
# 4. Collect initial positions
$TM round security-review collect code-agent "Found SQL injection in login()"
$TM round security-review collect test-agent "Missing input validation on email field"
$TM round security-review collect monitor-bot "No rate limiting on auth endpoints"
# ✅ Round 1 (initial) is complete.
# ➡️ Next: round security-review cross-review
# 5. Generate cross-review prompts
$TM round security-review cross-review
# 🔁 Each debater gets others' positions + review instructions
# 6. Collect cross-reviews
$TM round security-review collect code-agent "Agree on validation. Rate limiting is critical."
$TM round security-review collect test-agent "SQL injection is most severe. Adding rate limit tests."
$TM round security-review collect monitor-bot "Both findings valid. Recommending WAF as additional layer."
# 7. Synthesize all positions
$TM round security-review synthesize
# 🧾 Outputs all initial positions + cross-reviews for final synthesis

Question → [Agent A] → Position A ─┐
 → [Agent B] → Position B ─┤── Cross-Review ── Synthesis
 → [Agent C] → Position C ─┘

CLI Reference

All Commands

Status Values

Init Options

python3 scripts/task_manager.py init <project> \
 --goal "Project description" \
 --mode linear|dag|debate \
 --pipeline "agent1,agent2,agent3" # linear only \
 --workspace "/path/to/shared/dir" \
 --force # overwrite existing

Integration with OpenClaw

1. next <project> --json → get next stage info
2. update <project> <agent> in-progress
3. sessions_send(agent, task) → dispatch to agent
4. Wait for agent reply
5. result <project> <agent> "..." → save output
6. update <project> <agent> done → auto-advances to next stage
7. Repeat

1. ready <project> --json → get ALL dispatchable tasks
2. For each ready task (parallel):
 a. update <project> <task> in-progress
 b. sessions_send(agent, task + depOutputs)
3. On reply: result → update done → check newly unblocked
4. Repeat until all tasks complete

Common Pitfalls

⚠️ Linear mode: Stage ID = agent name, NOT a number

# ❌ WRONG — "stage '1' not found"
python3 scripts/task_manager.py assign my-project 1 "Build API"
# ✅ CORRECT
python3 scripts/task_manager.py assign my-project code-agent "Build API"

⚠️ DAG: Dependencies must exist before referencing

# ❌ WRONG — "dependency 'design' not found"
$TM add my-project implement -a code-agent -d "design"
# ✅ CORRECT — add deps first
$TM add my-project design -a docs-agent --desc "Write spec"
$TM add my-project implement -a code-agent -d "design" --desc "Implement"

⚠️ Debate: Cannot add debaters after rounds start

# ❌ WRONG
$TM round my-debate start
$TM add-debater my-debate new-agent # Error!
# ✅ CORRECT — add all debaters before starting
$TM add-debater my-debate agent-a
$TM add-debater my-debate agent-b
$TM round my-debate start

Data Storage

/home/ubuntu/clawd/data/team-tasks/<project>.json

export TEAM_TASKS_DIR=/custom/path

Project Structure

team-tasks/
├── README.md # This file
├── SKILL.md # OpenClaw skill definition
├── SPEC.md # Enhancement spec (debate + workspace)
├── scripts/
│ └── task_manager.py # Main CLI tool (Python 3.12+, stdlib only)
└── docs/
 ├── GAP_ANALYSIS.md # Comparison with Claude Code Agent Teams
 └── AGENT_TEAMS_OFFICIAL_DOCS.md # Reference documentation

License