agentleFS
Sign inStart free
LuisoteeLuisotee/agent-mesh/skills/delegate-claude/SKILL.md

delegate-claude

Skill0 starsChanged 16 days agoMITView on GitHub

agent-mesh, mode `claude`: hands each repo's part of a change, a task list, or a question about another repo to Claude agents working inside those repos, and supervises them; large tasks get their plan reviewed first, and each PR gets its reviewers by its size, from the CLIs installed (this machine's policy: `mesh routing`), in one round (one root wake), except a tiny PR of a trivial or small task or group, which the root reviews itself. Also asks the registered peer projects a question. Use it, typed or not, when the user wants work or a question handed to agents, in this repo or others ("have Claude do it", "delegate this", "ask the shop-api agent"), or when you judge workers would do it better (several repos, a task list, parallel work, a long job you would otherwise do inline), and names no other CLI (agy, Gemini, Argon, Flash); with none named, use it when you are Claude Code. Not for a PR review the user asks for (/delegate-review), a research round by the peers (/harvest-peers), or a mesh worker (your task came by a `📬 [mesh]` doorbell).

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. epicenter-md/epicenter★ 4.8ksame name
    2. EpicenterHQ/epicenter★ 4.8ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository7 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run an agent-mesh in mode claude for the user's request: $ARGUMENTS when the user typed the command, otherwise the request that brought you …

    line 18
  2. Very specific:

    Read ~/.config/agent-mesh/ORCHESTRATE.md and ~/.config/agent-mesh/PROTOCOL.md in full.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/delegate-claude

Run an agent-mesh in mode claude for the user's request: $ARGUMENTS when the user typed the command, otherwise the request that brought you here.

  1. Read ~/.config/agent-mesh/ORCHESTRATE.md and ~/.config/agent-mesh/PROTOCOL.md in full.
  2. You are the root. Follow the "Root" section with mesh init --mode claude. Its address is how your Claude workers' reports reach your session as cross-session messages.
    • Propose before you start ("Root" step 3): each worker's repo, size, model and view, then wait for the user's go, unless they said to run autonomously. A question, a review or a peer ask they asked for needs none.
    • Size every task ("Sizes") and pass --size to every mesh spawn and mesh ask. --kind claude is the default CLI; propose agy only as "Routing" describes.
    • Pass --model / --effort only if the request names them. Pass --plan-review user only if the user wants to approve a large plan themselves.
    • Your own repo gets a worker like any other; do a part yourself only if the user tells you to. Work they gave you before delegating stays yours.
    • A question about another repo that changes nothing: use mesh ask --kind claude ("Questions and reviews"). A question for the registered peer projects goes to mesh ask --peers <group|all>, run in the background; read the one answers file it prints. A PR review the user asks for on its own goes through /delegate-review; the reviews of your own workers' PRs stay here ("Root" step 8).
    • A follow-up to work an earlier worker did ("send the review to the agent that changed it", "ask that agent to make it Y"): resume that worker ("Follow-ups"). It keeps its own CLI and model (a change it must plan first plans on its plan chain), and it's compacted first if its conversation is large.
    • Decide small things yourself and ask the user only where their input adds value; fix review findings and the follow-ups they turn up in the PR they came from, on its branch, by the worker that made it, never in a new PR ("Rules for everyone"); give new small work to the worker that already knows that code, not a fresh agent; put other follow-ups on the repo's list of open work.
    • A list of tasks: follow "Task lists". Triage it into a few themed groups (no size cap: a worker can take a whole batch), each one worker with one PR, sized by its combined work (independent small tasks: small, no plan; one plan for a large group); get the user's one go on the board, then supervise without writing code yourself.
    • Whenever mesh prints a send_message, pass it on with the SendMessage tool, exactly as printed.
  3. Once the user says go (at once, when they said to run autonomously), start the work and tell the user in one line what you started: run id, and each worker's repo, size, model and whether it's in a pane or in the background. Then supervise until every worker reports back. For a question, give the user the answer and the name of the worker that gave it, so they can ask it again.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free