mstack CLAUDE.md

A project guide for mstack, a plugin that manages development work through a durable queue, verification gates, and defined workflows.

In plain words
What is it for?
Use it to start and manage mstack work, run its checks, follow its development rules, and avoid accidentally using an older installed version.
Why use it?
It keeps work tracked and requires checks to pass before a session closes, while helping developers run the intended local copy.

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/romerma/mstack/claude-md
Clone the repo
git clone --depth 1 https://github.com/romerma/mstack
Per session 284 This file is loaded in full into every session.
When invoked 284 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 $0.00284 $0.00284
Opus 5 $0.00142 $0.00142
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured yesterday against content hash 0917d9cb2a74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mstack 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 yesterday.

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 · 25 lines

What it actually says

mstack

This repository is the mstack plugin, and it uses mstack on itself: .mstack/ is the real work queue for real work on the plugin, which is the only way an unused workflow gets found out.

Workflow

Start work with /mstack. Durable state is in .mstack/; mstack gate must be green before a session closes. One item active at a time, a verdict from a pass that did not write the code to close it, and product forks answered through mstack decide --resolves.

Development

The dev loop, the runtime rules (no build step, no runtime dependencies, both runtimes green), and the docs discipline (pasted output from real runs) are in CONTRIBUTING.md. Run the plugin from this checkout with claude --plugin-dir ., with the marketplace-installed copy disabled — otherwise the hooks load twice and, worse, subagents run the cached agent and skill definitions rather than this checkout's.

Every CLI call in this repository is ./bin/mstack, never bare mstack: the copy on PATH is the installed plugin, which can be older than this checkout and reports green on checks it does not contain. ./bin/mstack version prints which copy is running.

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. yesterday First seen · 25 lines · 284 tokens per session scan A 0917d9cb2a74

Subscribe to this mod's changes

mstack CLAUDE.md is an instructions file published in the GitHub repository romerma/mstack (1 stars, last pushed 8d ago), licensed MIT. It adds 284 tokens to every session, about $0.0014 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 2026-08-31.