Swarm Coordinator

Name: Swarm Coordinator
Author: learnprompt

learnprompt/cc-harness-skills

41 installs
231 repo stars
Updated July 10, 2026
learnprompt/cc-harness-skills

Helps with ai & agent building tasks.

About

swarm-coordinator is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.

swarm-coordinator
AI & Agent Building
AI-coding skill

Swarm Coordinator by the numbers

41 all-time installs (skills.sh)
+2 installs in the week ending Aug 2, 2026 (Skillselion tracking)
Ranked #8,148 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Aug 2, 2026 (Skillselion catalog sync)

npx skills add https://github.com/learnprompt/cc-harness-skills --skill swarm-coordinator

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/learnprompt/cc-harness-skills/swarm-coordinator.svg)](https://skillselion.com/skills/learnprompt/cc-harness-skills/swarm-coordinator)

Installs	41
repo stars	★ 231
Last updated	July 10, 2026
Repository	learnprompt/cc-harness-skills ↗

What it does

Helps with ai & agent building tasks.

Files

SKILL.mdMarkdownGitHub ↗

Swarm Coordinator

Use this skill when a task is large enough that one coordinator and several bounded workers are more reliable than one monolithic agent loop.

Use It For

broad codebase exploration
cross-file bug hunts
parallel review or research passes
tasks that benefit from explicit synthesis before implementation

Avoid It For

trivial edits
urgent blocking steps that are faster to do locally
delegation with no ownership boundaries

Quick Start

Generate a task-board skeleton:

python3 {baseDir}/scripts/task_board.py --goal "Investigate flaky CI failure" --worker research --worker implementation --worker verification

Then use the coordinator prompt in references/prompt-template.md.

Core Rule

The coordinator should own planning, routing, and synthesis. Workers should own bounded execution.

Supporting Files

Prompt template: references/prompt-template.md
Source notes: references/source-notes.md
Helper script: python3 {baseDir}/scripts/task_board.py ...

CC Swarm Coordinator

swarm-coordinator is a portable multi-agent coordination skill for tasks that are too large or too noisy for one monolithic agent loop.

It keeps a coordinator focused on planning and synthesis while bounded workers handle research, implementation, and verification. The skill packages the organizational pattern, not a host-specific swarm runtime.

Best For

broad codebase exploration
cross-file bug hunts
parallel review or research passes
tasks that need explicit synthesis before implementation

Included Files

SKILL.md
references/prompt-template.md
references/source-notes.md
scripts/task_board.py

Quick Start

python3 ./scripts/task_board.py \
  --goal "Investigate flaky CI failure" \
  --worker research \
  --worker implementation \
  --worker verification

Then use the coordinator workflow from SKILL.md.

Host Fit

Claude Code: strong fit
Codex: strong fit
OpenClaw: good fit for lightweight or manually coordinated swarms

Portable Prompt Template

You are the coordinator for a multi-agent task.

Goal:
- split work into research, synthesis, implementation, and verification
- keep raw exploration out of the final synthesis
- assign clear ownership for each worker

Inputs:
- overall goal: <goal>
- available workers: <workers>
- task board: <task_board>

Rules:
- the coordinator should not duplicate worker effort
- each worker must have a bounded scope
- one owner per write surface
- synthesis happens before implementation decisions are finalized
- verification is separate from implementation

Return:
1. subtask split
2. ownership and dependencies
3. synthesis plan
4. final merge criteria

#!/usr/bin/env python3
"""Generate a simple coordinator task board."""

from __future__ import annotations

import argparse
import json


def main() -> int:
    parser = argparse.ArgumentParser()
    parser.add_argument("--goal", required=True)
    parser.add_argument("--worker", action="append", default=[])
    parser.add_argument("--format", choices=["json", "markdown"], default="json")
    args = parser.parse_args()

    workers = args.worker or ["research", "synthesis", "implementation", "verification"]
    board = {
        "goal": args.goal,
        "phases": [
            {"phase": "research", "owner": workers[0] if len(workers) > 0 else None, "deliverable": "facts and evidence"},
            {"phase": "synthesis", "owner": workers[1] if len(workers) > 1 else None, "deliverable": "conclusions and plan"},
            {"phase": "implementation", "owner": workers[2] if len(workers) > 2 else None, "deliverable": "bounded code changes"},
            {"phase": "verification", "owner": workers[3] if len(workers) > 3 else None, "deliverable": "findings and gate decision"},
        ],
    }

    if args.format == "json":
        print(json.dumps(board, indent=2, ensure_ascii=False))
        return 0

    print(f"# Goal\n\n{board['goal']}\n")
    print("## Phases")
    for phase in board["phases"]:
        print(f"- {phase['phase']}: owner={phase['owner'] or '-'}; deliverable={phase['deliverable']}")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())