MyMCP CLAUDE.md

MyMCP CLAUDE.md is an instructions file for coding agents from flyset/MyMCP. It costs 189 tokens per session, scanned A, original, Apache-2.0.

A contributor instruction file for MyMCP, a local-first host for narrowly scoped integrations with built-in memory. It defines how work is approved and how project changes should be handled.

In plain words
What is it for?
Use it to guide work on MyMCP plans, approval boundaries, open questions, commits, pushes, and releases.
Why use it?
It prevents an agent from taking unauthorised steps, especially when a decision could change a public interface, compatibility, or data storage.

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/flyset/mymcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/flyset/MyMCP

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 MyMCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/flyset/mymcp/claude-md.svg)](https://agentmods.dev/instructions/flyset/mymcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/flyset/mymcp/claude-md"><img src="https://agentmods.dev/badge/instructions/flyset/mymcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 189 This file is loaded in full into every session.
When invoked 189 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 $0.00189 $0.00189
Opus 5 $0.00095 $0.00095
Sonnet 5 $0.00038 $0.00038
Haiku 4.5 $0.00019 $0.00019

Measured 2d ago against content hash 876efc78e259, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

MyMCP 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 2d 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 · 18 lines

What it actually says

@AGENTS.md

Approval Granularity (Claude-specific)

  • An instruction to work on a Track authorizes only its next unchecked plan step. Execute that step, update the Track, report back, and wait for an explicit go before starting the next step.
  • Run multiple plan steps in one pass only when the user explicitly says so, for example "run the whole track without stopping".
  • Resolving an Open Question whose answer changes a public contract, Tool schema, compatibility version, or storage layout always requires a fresh explicit yes, even inside an authorized step.
  • Commits, pushes, and releases always require an explicit user request.
  • Treat tentative phrasing — "maybe", "it may make sense", "we could", "perhaps", thinking out loud — as discussion, not authorization. Respond with a proposal and wait for an explicit instruction before changing anything.
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. 2d ago First seen · 18 lines · 189 tokens per session scan A 876efc78e259

Subscribe to this mod's changes

MyMCP CLAUDE.md is an instructions file published in the GitHub repository flyset/MyMCP (0 stars, last pushed 29d ago), licensed Apache-2.0. It adds 189 tokens to every session, about $0.0009 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.