mcp: Instructions file for Claude Code

CLAUDE.md

mcp CLAUDE.md is an instructions file for Claude Code from tabnas/mcp. It costs 774 tokens per session, scanned A, original, MIT.

A set of instructions for working on the tabnas/mcp repository, including its architecture, generated data, security rules, and build and test process.

In plain words
What is it for?
Navigating the repository, changing its shared core or front ends, updating generated data, handling untrusted input, and running builds and tests.
Why use it?
It explains the repository's required design and checks, including keeping two user interfaces on one core and preserving exact output where required.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions AGENTS.md.

This is tabnas/mcp's own configuration. It tells Claude Code how to work on mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp configures →

View source ↗ tabnas/mcp
Reuse

Borrowing it

Nothing to install: this file belongs to tabnas/mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tabnas/mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tabnas/mcp

Made for: Claude Code.

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 mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tabnas/mcp/claude-md/github.svg)](https://agentmods.dev/instructions/tabnas/mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tabnas/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tabnas/mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tabnas/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tabnas/mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 774 This file is loaded in full into every session.
When invoked 774 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00774 $0.00774
Opus 5.5 $0.00310 $0.00310
Sonnet 5.5 $0.00155 $0.00155
Haiku 4.5 $0.00077 $0.00077

Measured 1mo ago against content hash 61a0dc77270d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp 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 1mo 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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

See AGENTS.md for the full guide to working in this repository: the one-core/two-front-ends rule and the golden byte-parity contract, the repository map, the bundled generated data and its staleness gates, the ADR-10 grammar security rule, build & test commands, and how to treat untrusted input.

Core principle: dependencies change only on explicit instruction

Dependencies may only be changed by explicit instruction from the maintainer. This covers every dependency this repository declares, in every runtime and every manifest:

  • package.json dependencies, peerDependencies and devDependencies, and their lockfiles;
  • go.mod require and replace lines, their versions, and go.sum;
  • Cargo.toml dependency tables and Cargo.lock;
  • any other manifest here, nested test modules included.

Adding, removing, re-pointing or re-versioning any of them is a dependency change.

  • A dependency never arrives as a side effect. Watch for an import, go mod tidy, npm install, cargo update, a stamped template, or a fix for something else. If a change would alter a dependency, stop and ask before making it. Do not make it and explain afterwards.
  • An explicit instruction names the change, for example "bump the parser requirement in X to 0.12" or "cascade the parser release". A goal is not an instruction for its means. "Make CI green", "ship the C library" or "fix the build" does not authorise a dependency change, however direct the route through one looks.
  • This repository's own version sites are not dependencies. They include the root entry of its own lockfile. A release bump moves them.
  • Versions track the latest release. Every dependency is kept at its latest published version, and none is held on an older one. That is the maintainer's standing instruction, so moving a dependency to its latest version needs no further one. Holding a dependency back, or adding, removing or re-pointing one, still does.

Read the full file on GitHub · 61 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. 1mo ago Changed · +55 lines · +697 tokens per session 61a0dc77270d
  2. 2mo ago First seen · 6 lines · 77 tokens per session scan A bd12400a40e2

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository tabnas/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 774 tokens to every session, about $0.0031 per session on Opus 5.5. 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

mcp CLAUDE.md compared with instructions from other repositories

mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp CLAUDE.mdtabnas/mcpInstructions file01mo agoMITA774Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot