Agent skill

Swarm Coordinator

by LearnPrompt in LearnPrompt/cc-harness-skills

Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw…

MITAuto-check passedAgent Workflows

Install Swarm Coordinator

skills CLI
$ npx skills add LearnPrompt/cc-harness-skills --skill swarm-coordinator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LearnPrompt/cc-harness-skills swarm-coordinator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LearnPrompt/cc-harness-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/swarm-coordinator .claude/skills/swarm-coordinator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
swarm-coordinator
GitHub stars
236
Token cost
~346 tokens
SKILL.md length
107 words
Files
5 (incl. scripts, references)
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw…

  • Tasks that involve User research
  • SKILL.md covers Use It For, Avoid It For, Quick Start and Core Rule, plus 1 more section
  • Runs Python scripts from its folder; calls python3

What it does

Swarm Coordinator is an agent skill from LearnPrompt/cc-harness-skills. Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw exploration.

Its SKILL.md is about 350 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `README.md`, `references/prompt-template.md` and `references/source-notes.md`).

It sits in Agent Workflows, covering User research. The repository describes itself as: Portable CC-inspired skills for memory, verification, multi-agent coordination, context compression, and proactive coding-agent workflows. The licence is MIT.

When your agent uses it

  • Tasks that involve User research

Example prompts

  • “/swarm-coordinator”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 3899650. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Swarm Coordinator loads about 346 tokens when it runs, and up to ~621 if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 107 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~346
With references · SKILL.md plus every file in references/, read only if the agent opens them
~621

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LearnPrompt/cc-harness-skills at commit 3899650, republished under its MIT licence (© LearnPrompt). 107 words, ~346 tokens.

Download SKILL.mdSave it as .claude/skills/swarm-coordinator/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
swarm-coordinator
description
Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw exploration.

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:

bash
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

© LearnPrompt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in skills/swarm-coordinator of LearnPrompt/cc-harness-skills.

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

Open the folder on GitHubat commit 3899650

Compare with similar skills

Swarm Coordinator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Swarm Coordinator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Swarm Coordinator this skillLearnPrompt/cc-harness-skills236—~346Automated safety check: PassMIT
Mom Testgetagentseal/founder-playbook724—~2.3kAutomated safety check: PassMIT
Build Afm Nightly Publishscouzi1966/maclocal-api345—~8.8kAutomated safety check: PassMIT
Looperksimback/looper710—~2.7kAutomated safety check: NotesMIT
User Testing ValidatorIntelligent-Internet/zenith334—~1.8kAutomated safety check: PassApache-2.0
Riffrec Feedback AnalysisEveryInc/compound-engineering-plugin25k—~695Automated safety check: PassMIT

Similar skills

  • Mom Test

    getagentseal/founder-playbook

    Validates business ideas through customer conversations using Rob Fitzpatrick's Mom Test framework.

    724 GitHub stars~2.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Build Afm Nightly Publish

    scouzi1966/maclocal-api

    Build, test, and publish an afm-next nightly release — full from-scratch build, user testing pause, GitHub release, and Homebrew tap update.

    345 GitHub stars~8.8k tokensUpdated 3 days ago
    MobileAuto-check passed
  • Looper

    ksimback/looper

    Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.

    710 GitHub stars~2.7k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check: notes
  • User Testing Validator

    Intelligent-Internet/zenith

    Real-surface validation coordinator for engineering validation assignments.

    334 GitHub stars~1.8k tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed
  • Riffrec Feedback Analysis

    EveryInc/compound-engineering-plugin

    Turns Riffrec screen, voice and event recordings into evidence for bug reports and requirements, and helps set up Riffrec when no recording exists yet.

    25k GitHub stars~695 tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Foundation Meeting Recap

    product-on-purpose/pm-skills

    Produces a topic-segmented post-meeting summary for attendees with decisions highlighted and actions captured inline per topic (plus a consolidated action view at the end).

    715 GitHub stars~2.6k tokensUpdated 3 days ago
    Productivity & AutomationAuto-check passed

More from LearnPrompt/cc-harness-skills

  • Dream Memory

    LearnPrompt/cc-harness-skills

    Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.

    236 GitHub stars~477 tokensUpdated 3 mo ago
    Auto-check passed
  • Kairos Lite

    LearnPrompt/cc-harness-skills

    Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.

    236 GitHub stars~334 tokensUpdated 3 mo ago
    Auto-check passed
  • Memory Extractor

    LearnPrompt/cc-harness-skills

    Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.

    236 GitHub stars~347 tokensUpdated 3 mo ago
    Auto-check passed
  • Structured Context Compressor

    LearnPrompt/cc-harness-skills

    Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.

    236 GitHub stars~327 tokensUpdated 3 mo ago
    Auto-check passed
  • Verification Gate

    LearnPrompt/cc-harness-skills

    Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed.

    236 GitHub stars~302 tokensUpdated 3 mo ago
    Auto-check passed

Questions about Swarm Coordinator

What does Swarm Coordinator do?

Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw…. Swarm Coordinator is an agent skill from LearnPrompt/cc-harness-skills. Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw exploration.

When should I use Swarm Coordinator?

Swarm Coordinator fits situations like: tasks that involve User research.

How do I install Swarm Coordinator in Claude Code?

Run `npx skills add LearnPrompt/cc-harness-skills --skill swarm-coordinator -a claude-code`. Or copy the skill folder (skills/swarm-coordinator in LearnPrompt/cc-harness-skills) into .claude/skills/swarm-coordinator in your project. Claude Code loads it when a task matches its description.

How do I install Swarm Coordinator in Codex?

Run `npx skills add LearnPrompt/cc-harness-skills --skill swarm-coordinator -a codex`. Or copy the skill folder (skills/swarm-coordinator in LearnPrompt/cc-harness-skills) into .agents/skills/swarm-coordinator in your project. Codex loads it when a task matches its description.

Can I use Swarm Coordinator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LearnPrompt/cc-harness-skills --skill swarm-coordinator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/swarm-coordinator, .gemini/skills/swarm-coordinator, .github/skills/swarm-coordinator and .opencode/skills/swarm-coordinator in your project.

What does Swarm Coordinator need to run?

Going by SKILL.md and its folder, Swarm Coordinator needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Swarm Coordinator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Swarm Coordinator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Swarm Coordinator use?

Swarm Coordinator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Swarm Coordinator use?

About 346 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 275 tokens, read only when the agent opens those files.

What are the alternatives to Swarm Coordinator?

Skills that share tags, products or a category with Swarm Coordinator: Mom Test (getagentseal/founder-playbook, 724 stars), Build Afm Nightly Publish (scouzi1966/maclocal-api, 345 stars), Looper (ksimback/looper, 710 stars) and User Testing Validator (Intelligent-Internet/zenith, 334 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Swarm Coordinator?

LearnPrompt (a GitHub user) maintains it in LearnPrompt/cc-harness-skills, which has 236 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on July 10, 2026.

Source: LearnPrompt/cc-harness-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.