Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/athola/claude-night-marketnpx agentmods add skills/athola/claude-night-market/muse-delegationWrote 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/athola/claude-night-market/muse-delegation)<a href="https://agentmods.dev/skills/athola/claude-night-market/muse-delegation"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/muse-delegation/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/athola/claude-night-market/muse-delegation"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/muse-delegation.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 | $0.00041 | $0.01132 |
| Opus 5 | $0.00020 | $0.00566 |
| Sonnet 5 | $0.00008 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade C, and why
muse-delegation scanned grade C with 2 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://dev.meta.ai/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://dev.meta.ai/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Table of Contents
- Overview
- When To Use
- When NOT To Use
- Prerequisites
- Quick Start
- Smart Delegation
- Muse-Specific Details
- Exit Criteria
Muse Code Delegation
Overview
Muse Code is Meta's terminal coding agent, released August 2026 and built on Muse Spark 1.2. It runs either as an interactive TUI or as a one-shot headless command, and the headless form is what delegation uses.
The binary is muse. Meta publishes no npm or PyPI package for it:
the documented install is a script served from Meta's own domain.
When To Use
delegation-coreselectedmusefor the task- Repository-scale reading where Muse Spark 1.2's 1M-token context helps
- Work that should run unattended, since
muse execis designed for CI
When NOT To Use
META_API_KEYis unset and the run cannot be interactive- A specific model must be selected. Meta documents no
--modelflag forexec, so the CLI default stands - Structured output is required. No output-format flag is documented
for
exec
Prerequisites
Installation
curl -fsSL https://dev.meta.ai/install.sh | sh
This pipes a remote script into a shell. Read https://dev.meta.ai/docs/muse-code before running it. The guided installer offers the same command and shows its source first:
make -C plugins/conjure delegate-setup
Authentication
Meta documents the environment variable as the CI path:
export META_API_KEY="<your-key>"
muse exec "Run the test suite and summarize failures."
A bare muse prompts for browser sign-in on first run, which is not
usable unattended. There is no muse auth status command, so the
service declares an empty auth probe and verification checks
META_API_KEY instead.
Quick Start
Using the shared delegation executor
uv run python scripts/delegation_executor.py muse "Summarize this module" \
--files src/
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.
- 9d ago First seen · 160 lines · 41 tokens per session scan C a72c82dc2b4f
muse-delegation is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,132 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
author-skill
Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into references/, writing its evals, auditing it against the rubric. NOT building a product feature (that is specify) and NOT designing an agent loop…
continuous-learning
Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives…
orient
Always-on. The brújula: close every turn by situating the person — where they are, what just happened, why it mattered, and the next step as a question, never a dead end. Reads the accompaniment and technical dials from 02-DOCS and calibrates how much it explains, rewriting the dial when the user asks for more or…
skill-authoring
Creates and structures SKILL.md files for AI coding agents, including YAML frontmatter, trigger phrases, directive instructions, decision trees, code examples, and verification checklists. Use when the user asks to write a new skill, create a skill file, author agent capabilities, generate skill documentation, or…
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…
skill-navigator
A skill that recommends which already-installed local agent skill matches a described task. It uses the machine's skill catalogue and does not perform the task itself.