agentleFS
Sign inStart free
StoicEnsoStoicEnso/openclaw-claude-delegate/SKILL.md

claude-delegate

Skill0 starsChanged 7 months agoMITView on GitHub

Give Claude back to OpenClaw through a local Claude Code delegation lane with dispatch, poll, result, resume, and an optional non-root bypassPermissions runner. Use when: you want Claude subscription access available to OpenClaw agents through a stable local worker lane, need resume/monitoring in a bounded workspace, or need Claude auth separate from OpenClaw providers. Don't use when: the user explicitly wants an ACP chat harness or thread, use acp-router plus sessions_spawn(runtime: \"acp\"); the task is a simple edit or shell command, use edit/exec directly; or the local Claude runner is not set up yet, read references/setup.md first.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. amElnagdy/delegate-skills★ 2.6ksame name
    2. ricardodeazambuja/tui-driver★ 1same name
    3. fergus/claude-kimi-delegate★ 0same name
    4. lnopy96/claude-skills★ 0same 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.

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when Claude Code should run as a local delegated worker, not as an ACP chat harness.

    line 10
  2. Very specific:

    Read references/setup.md the first time you install or port this skill.

    line 23
  3. Very specific:

    Keep local delegate instructions in the nearest CLAUDE.delegate.md files.

    line 25
  4. Very specific:

    Use resume to continue the same Claude session instead of starting over.

    line 28
  5. Distinctive:

    Prefer this skill when you want:

    line 32
  6. Distinctive:

    Prefer ACP when the user explicitly asked for Claude Code as a chat/thread runtime.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Claude Delegate

Give Claude back to OpenClaw.

Use this skill when Claude Code should run as a local delegated worker, not as an ACP chat harness.

The whole point is simple: third-party harnesses do not reliably get Claude subscription access, but OpenClaw operators still want Claude-quality work inside their agent system.

Stable entrypoints

  • Wrapper: scripts/claude-delegate.sh
  • Profile wrapper: scripts/cc-profile.sh
  • Orchestrator: scripts/cc-orchestrator.sh
  • Low-level runner: scripts/run-task.sh

Default flow

  1. Read references/setup.md the first time you install or port this skill.
  2. Configure profiles.json, or point CLAUDE_DELEGATE_PROFILES at a host-local profiles file.
  3. Keep local delegate instructions in the nearest CLAUDE.delegate.md files. The wrapper now tells Claude to discover/read those plus nearby AGENTS.md, TOOLS.md, and README.md docs before substantive work.
  4. Dispatch work through scripts/claude-delegate.sh dispatch <profile> <budget> <model> <label> "<task>".
  5. Monitor with poll, result, list, or doctor.
  6. Use resume to continue the same Claude session instead of starting over.

When to prefer this over ACP

Prefer this skill when you want:

  • a boring local wrapper around Claude CLI
  • a non-root runner user with synced auth/binary state
  • bounded filesystem access through a chosen workdir
  • cheap monitoring and resume without a chat-thread harness

Prefer ACP when the user explicitly asked for Claude Code as a chat/thread runtime.

Files to load when needed

  • Setup, auth, env knobs, and profile customization: references/setup.md
  • Delegate bootstrap guidance for this repo: CLAUDE.delegate.md

Notes

  • scripts/cc-profile.sh supports CLAUDE_DELEGATE_PROFILES=/abs/path/to/profiles.json.
  • Profile paths support ~ and environment variable expansion.
  • scripts/ensure-nonroot-delegation.sh supports env overrides for source paths if your Claude or acpx installs live somewhere else.
  • Delegate bootstrap is on by default. Disable with CLAUDE_DELEGATE_BOOTSTRAP=0 or change the instruction filename with CLAUDE_DELEGATE_DOC_BASENAME.

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