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 instructions/philipnee/mvmt/claude-mdgit clone --depth 1 https://github.com/philipnee/mvmtWrote 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/instructions/philipnee/mvmt/claude-md)<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>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 | $0.00712 | $0.00712 |
| Opus 5 | $0.00356 | $0.00356 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
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.
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:coverageto 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:
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 · 105 lines · 712 tokens per session scan A a3a630fc983a
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.
Other instructions, from other repositories
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
KKTerm AGENTS.md
AGENTS.md instructions for ryantsai/KKTerm, covering agent instructions, project shape, constitution, rule 1 — think before coding and rule 2 — simplicity first.
clawstash CLAUDE.md
Claude Code instructions for fo0/clawstash, covering claude.md -- project guide, session start -- read order, workflow triggers, output languages and performance / modes.
KKTerm CLAUDE.md
Claude Code instructions for ryantsai/KKTerm: Constitution, Repository workflow, domain language, source-area boundaries, i18n rules, and engineering defaults live in AGENTS.md. Product terminology lives in CONTEXT.md. Read both before changing behavior or terminology.
grounded-knowledge-engine copilot-instructions.md
Instructions for dimosgit/grounded-knowledge-engine: Follow AGENTS.md as the canonical repository contract.
grounded-knowledge-engine CLAUDE.md
Instructions for dimosgit/grounded-knowledge-engine: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.