idfkit-mcp: Instructions file for Claude Code

CLAUDE.md

idfkit-mcp CLAUDE.md is an instructions file for Claude Code from idfkit/idfkit-mcp. It costs 756 tokens per session, scanned A, original, MIT.

Project instructions for Claude Code in the idfkit-mcp repository. They list setup commands, quality checks, tests, documentation, Docker tasks, and rules for handling automated dependency updates.

In plain words
What is it for?
Installing dependencies, running formatting and static checks, running all or individual tests, building Docker containers, serving documentation, and preparing small compatibility fixes.
Why use it?
They give the coding agent the repository's expected checks and limits, reducing the chance of proposing untested or unrelated changes.

Instructions file for Claude Code

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

This is idfkit/idfkit-mcp's own configuration. It tells Claude Code how to work on idfkit-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 idfkit-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to idfkit/idfkit-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/idfkit/idfkit-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/idfkit/idfkit-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 idfkit-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/idfkit/idfkit-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/idfkit/idfkit-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/idfkit/idfkit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/idfkit/idfkit-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 idfkit-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/idfkit/idfkit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/idfkit/idfkit-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 756 This file is loaded in full into every session.
When invoked 756 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 $0.00756 $0.00756
Opus 5.5 $0.00302 $0.00302
Sonnet 5.5 $0.00151 $0.00151
Haiku 4.5 $0.00076 $0.00076

Measured 1mo ago against content hash 15bedd824e17, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

idfkit-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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Common Commands

# Install dependencies
uv sync

# Run all quality checks (lint, format, type check, deptry)
make check

# Run tests
make test

# Run a single test
uv run pytest tests/test_file.py::test_function -v

# Serve documentation locally
make docs

# Build and run Docker container
make docker-build && make docker-run

Before Committing

Always run the full quality gate before proposing changes:

make check && make test

This runs: lock file validation, pre-commit hooks (ruff format/lint), pyright, deptry, and pytest.

The consumer register

This repository is idfkit-mcp in the consumer register, governance/consumers.toml in idfkit-conformance, read at the governance tag pinned in .github/workflows/main.yml. The register records where the idfkit level is declared and never the level itself.

  • Where the level lives: the exact idfkit==X pin in project.dependencies of pyproject.toml, and nowhere else. Bumping it needs no register change.
  • Self-check: the consumer-register job in main.yml calls check-consumer.yml at that tag. It fails when the level moves to a file the register does not point at, or when a new dependency on either library appears that the register does not name. It does not care whether the level is current. Moving where the level is declared is a change to the register, in idfkit-conformance, reviewed by both languages.
  • Rehearsal: .github/workflows/rehearse-candidate.yml builds a wheel from any idfkit ref and runs uv run pyright, then the tests, against it, without touching pyproject.toml or uv.lock. Run it before an idfkit release, not after one. pyright is the instrument that sees write_idf(doc, path) in tools/write.py stop meaning "save".
  • Version: idfkit-mcp --version prints this server's version and the idfkit it runs against. The plugin and the hosted deployment both deliver this server to people, and each must be able to say which level it runs.

Read the full file on GitHub · 81 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 · +30 lines · +490 tokens per session 15bedd824e17
  2. 2mo ago First seen · 51 lines · 266 tokens per session scan A a8bf896534b5

Subscribe to this mod's changes

idfkit-mcp CLAUDE.md is an instructions file published in the GitHub repository idfkit/idfkit-mcp (14 stars, last pushed yesterday), licensed MIT. It adds 756 tokens to every session, about $0.0030 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

idfkit-mcp CLAUDE.md compared with instructions from other repositories

idfkit-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
idfkit-mcp CLAUDE.mdidfkit/idfkit-mcpInstructions file14yesterdayMITA756Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode