delegate-skills is a toolkit for assigning coding tasks to separate agent command-line tools while keeping control of review and commits. It is for developers who want to organize installed implementers into lanes for work such as features, tests, or UI, then delegate tasks by lane or directly. The catalogue entries define the setup and delegation workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add amElnagdy/delegate-skills --skill muse-delegategit clone --depth 1 https://github.com/amElnagdy/delegate-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/amelnagdy/delegate-skills/muse-delegate)<a href="https://agentmods.dev/skills/amelnagdy/delegate-skills/muse-delegate"><img src="https://agentmods.dev/badge/skills/amelnagdy/delegate-skills/muse-delegate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/amelnagdy/delegate-skills/muse-delegate"><img src="https://agentmods.dev/badge/skills/amelnagdy/delegate-skills/muse-delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00157 | $0.02325 |
| Opus 5.5 | $0.00063 | $0.00930 |
| Sonnet 5.5 | $0.00031 | $0.00465 |
| Haiku 4.5 | $0.00016 | $0.00232 |
Grade A, and why
muse-delegate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Muse Delegate
You are the orchestrator. This skill lets you hand a bounded coding task to a separate
implementer — Muse Code (muse) — then review what it produced and land it yourself. You write
the brief and own the judgment; Muse does the typing in its own exec run; you verify and commit.
Nothing here is specific to one orchestrating agent. The loop needs only the ability to run a shell command and read a file, so any agent with those two capabilities can drive it. The full delegate → review → commit loop has been run with Claude Code as the orchestrator. Other orchestrators remain unproven.
When NOT to use this
- The task is small enough to just do inline — delegation overhead is not worth it.
- The
museCLI is not installed or not authenticated (runmuse login, or setMETA_API_KEY). - You want to write the code yourself.
- You are on native Windows and need a supported launcher. Upstream's
muselauncher is Darwin/Linux only; this skill still ships in the Windows contract matrix, but a live Windows dispatch is not a supported Muse install.
Read this before the first dispatch: the autonomy model
Headless Muse is muse exec only. muse resume is the interactive TUI and is never invoked.
--resume-last is rejected; continue a run with --session <id> (Muse's --session-id).
Write runs keep Muse's sandbox on and pass --disable-approval so a headless run cannot hang on a
tool-approval prompt. They also pass --trust-workspace and --user-input-auto-resolve. That is not
--yolo and not --full-access — do not invent either as the default. --trust-workspace loads the
target repo's rules and skills into the implementer run, and nothing in the relay narrows the
implementer's tool set inside the sandbox; the brief is what bounds it to the task.
--read-only adds --disable-write (non-shell filesystem writes) and --disable-shell. Approval
stays disabled so the review cannot block on a prompt either.
--provider echo|meta is a relay-only flag for tests and explicit probes. It is not a fleet dial.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 163 lines · 157 tokens per session scan A 0faaa4ed2979
muse-delegate is a skill published in the GitHub repository amElnagdy/delegate-skills (2,400 stars, last pushed yesterday), licensed MIT. It adds 157 tokens to every session and 2,325 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.
Other skills, from other repositories
claude-md-improver
Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.
claude-md-revision
Record durable, project-specific learnings from the current session in CLAUDE.md, .claude.local.md, or AGENTS.md—not general documentation, session summaries, or repo-wide audits.
commit
A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.
review
Review a change for correctness, security, and missing tests.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.