muster CLAUDE.md

muster CLAUDE.md is an instructions file for coding agents from schuettc/muster. It costs 2,606 tokens per session, scanned A, original, MIT.

Project instructions for muster, a local message bus that lets independent coding-agent sessions pass tasks and messages to one another. The project is a Go program with a server, command-line interface, MCP server, and optional hosted-backend mode.

In plain words
What is it for?
Use it when developing muster, especially before commits, when running verification checks, or when changing its storage and coordination code.
Why use it?
It gives agents and developers a shared set of build, test, branch, and architecture rules for working in the repository.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/schuettc/muster/claude-md
Clone the repo
git clone --depth 1 https://github.com/schuettc/muster

Wrote 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.

agentmods badge for muster CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/schuettc/muster/claude-md.svg)](https://agentmods.dev/instructions/schuettc/muster/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/schuettc/muster/claude-md"><img src="https://agentmods.dev/badge/instructions/schuettc/muster/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,606 This file is loaded in full into every session.
When invoked 2,606 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02606 $0.02606
Opus 5 $0.01303 $0.01303
Sonnet 5 $0.00521 $0.00521
Haiku 4.5 $0.00261 $0.00261

Measured 4d ago against content hash 5a213b81fa5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

muster CLAUDE.md 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.

CLAUDE.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — muster

Conventions for working in this repo (humans and agents).

What muster is

A local multi-agent coordination bus: independent coding-agent sessions (Claude Code + OpenAI Codex, each in its own tmux tab) hand tasks/messages to each other — no copy/paste, subscription-only (the bus never calls a model; it routes between agents already running on their own plans). One static Go binary, multi-mode (serve daemon · mcp stdio server · human CLI · lambda handler for the optional hosted backend).

Build / test / run

  • just verify — the gate: gofmt, golangci-lint, go test -race, build, cross (all four release targets plus the -tags lambda build). Run it before every commit; CI runs the same recipe, so local and CI can't drift.
  • just verify-dynamo — the second gate, deliberately NOT part of verify because it needs Docker. Runs internal/dynamostore and the DynamoDB half of the cross-backend conformance suite against DynamoDB Local. Without an endpoint those tests skip, so verify compiles and vets them but proves nothing about DynamoDB semantics — run this after touching internal/dynamostore. The dynamo job in CI runs the same two packages against a service container.
  • cgo-free — the binary builds under CGO_ENABLED=0 (pure-Go SQLite via modernc.org/sqlite). Don't add cgo dependencies.
  • macOS tests use internal/mustertest.ShortHome() for unix-socket paths (the sun_path ~104-char limit; t.TempDir() is too long and breaks the socket).
  • Build + run: go build -o ~/.local/bin/muster ./cmd/muster, then muster serve | mcp | agents | send | inbox | tasks | nudge | register | ….

Branch model

feat/* → dev → main. CI (just verify) is required on dev and main; main is the release line. Never develop on main — do feature work in a git worktree off dev, merged via PR.

Releases are automated. The VERSION file is the knob: bump it on dev, and when the promotion PR merges to main, the release workflow tags v<VERSION>, creates the GitHub release with generated notes, and attaches cross-compiled binaries (darwin/linux × arm64/amd64) with checksums. A merge to main that doesn't bump VERSION releases nothing. The darwin binaries are signed and notarized by the release job itself, which is why that job runs on a macOS runner, and it fails rather than publishing anything unsigned — so a green release needs no manual signing step. contrib/release-sign.sh v<VERSION> remains only for repairing an already-published release by hand.

Read the full file on GitHub · 174 lines

Changes

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.

  1. 4d ago First seen · 174 lines · 2,606 tokens per session scan A 5a213b81fa5a

Subscribe to this mod's changes

muster CLAUDE.md is an instructions file published in the GitHub repository schuettc/muster (12 stars, last pushed today), licensed MIT. It adds 2,606 tokens to every session, about $0.0130 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens