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 agentmods add skills/schuettc/muster/muster-coordinationnpx skills add schuettc/muster --skill muster-coordinationgit clone --depth 1 https://github.com/schuettc/musterWrote 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/schuettc/muster/muster-coordination)<a href="https://agentmods.dev/skills/schuettc/muster/muster-coordination"><img src="https://agentmods.dev/badge/skills/schuettc/muster/muster-coordination.svg" alt="Measured on agentmods" 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 | $0.00096 | $0.02182 |
| Opus 5 | $0.00048 | $0.01091 |
| Sonnet 5 | $0.00019 | $0.00436 |
| Haiku 4.5 | $0.00010 | $0.00218 |
Grade A, and why
muster-coordination 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 4d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordinating over the muster bus
muster lets independent agent sessions (each in its own tmux tab) message and hand tasks to each other with no copy/paste. If your session has the muster MCP tools, you're a potential peer on the bus. This skill is the etiquette.
Register at the start — and on resume
Call register_agent(alias, role, model_type) once when your session begins.
The bus captures your tmux pane automatically; your alias is how peers
address you (seeded from your tmux session name by default). If a launch hook
already ran muster register, you're already on the bus — don't
double-register.
Your alias is your durable identity: your inbox, threads, and read-state live under it in the bus's store, and they survive tmux sessions, terminal restarts, and reboots. If this conversation registered an alias earlier and the session was resumed — even in a brand-new tmux session — re-register the SAME alias: the bus revives the identity with its mail intact, and the register response tells you whether it was revived and how many threads are unread. (Under Claude Code the SessionStart hook does this reclaim for you and tells you your alias and backlog; re-registering by name is the fallback every harness has.)
Underneath the alias, the bus actually tracks conversations by transcript
path — if you register under a name other than the one your transcript
already owns a row for, the daemon adopts that existing row onto your
current tuple instead of creating a second one; the response's outcome
comes back adopted and carries the row's real alias, which may differ from
the name you asked for.
Codex peers register on their first turn, not at launch: a freshly opened
Codex session is not addressable until someone says something to it ("hi" is
enough). If a Codex peer you expect is missing from list_agents, that is the
usual reason.
Your seed alias (your tmux session's name) is a placeholder, not your
identity. When the work has a real name, claim it:
register_agent(alias: "<real-name>", become: true) — the new alias
inherits this session's identity and inbox, the seed retires, and peers
address you by a name that means something.
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.
- 4d ago First seen · 150 lines · 96 tokens per session scan A 625217ee26dc
muster-coordination is a skill published in the GitHub repository schuettc/muster (12 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 2,182 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…