mvmt CLAUDE.md

mvmt CLAUDE.md is an instructions file for coding agents from philipnee/mvmt. It costs 712 tokens per session, scanned A, original, MIT.

Project instructions for coding agents working on mvmt, a local-first hub that collects data through the Model Context Protocol.

In plain words
What is it for?
Use them when making changes in mvmt to understand the project context, avoid unrelated edits, and run the required verification command.
Why use it?
They set boundaries for keeping code changes small and require checks before work is declared complete.

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/philipnee/mvmt/claude-md
Clone the repo
git clone --depth 1 https://github.com/philipnee/mvmt

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 mvmt CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/philipnee/mvmt/claude-md.svg)](https://agentmods.dev/instructions/philipnee/mvmt/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/philipnee/mvmt/claude-md"><img src="https://agentmods.dev/badge/instructions/philipnee/mvmt/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 712 This file is loaded in full into every session.
When invoked 712 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 $0.00712 $0.00712
Opus 5 $0.00356 $0.00356
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 4d ago against content hash a3a630fc983a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mvmt 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Rules

This file is the entry point for any AI coding agent working on mvmt. If you are Claude Code, Codex, Cursor, Copilot, or any other coding agent, read and follow these rules before making any changes.

Project context

mvmt is a local-first MCP data hub. Read README.md for what it does, docs/architecture.md for how it works, and CONTRIBUTING.md for development setup and the test matrix.

Rules

1. Keep diffs small and reviewable

  • One concern per commit. Do not bundle unrelated changes.
  • Prefer editing existing files over creating new ones.
  • Do not refactor, rename, reformat, or add comments to code you are not changing for the task at hand.
  • Do not add speculative features, abstractions, or configurability beyond what was requested.
  • If a change touches more than ~5 files or ~150 lines, stop and break it into smaller steps.

2. Run verification before declaring done

Run:

npm run verify

This is the PR gate. It runs the TypeScript build, full test suite, whitespace checks, package dry-run, and a runtime smoke test.

Coverage requirements:

  • 100% feature coverage: every behavior your change introduces or modifies must have a test that exercises it, including error/rejection paths.
  • 80% spatial coverage: at minimum 80% of the lines you added or changed must be hit by at least one test. Run npm run test:coverage to check.

Do not skip verification. Do not report a task as complete without showing that verification passed.

3. Security-sensitive changes need extra tests

If your change touches any of these areas, add focused tests for both the success and failure/rejection paths:

  • Token generation or validation
  • OAuth/PKCE flow
  • Origin checks
  • Write gates
  • Filesystem path validation (traversal, symlinks)
  • Environment scrubbing
  • Audit logging
  • Connector process spawning or shutdown

Default to less access. Require explicit user consent for writes.

4. PR description format

Every pull request must include:

Read the full file on GitHub · 105 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 · 105 lines · 712 tokens per session scan A a3a630fc983a

Subscribe to this mod's changes

mvmt CLAUDE.md is an instructions file published in the GitHub repository philipnee/mvmt (2 stars, last pushed 3mo ago), licensed MIT. It adds 712 tokens to every session, about $0.0036 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.

Related

Other instructions, from other repositories