mcp-scribe: Instructions file for Claude Code

CLAUDE.md

mcp-scribe CLAUDE.md is an instructions file for Claude Code from The-Swarm-Corporation/mcp-scribe. It costs 2,113 tokens per session, scanned A, original, Apache-2.0.

Repository guidance for mcp-scribe, a tool that turns an OpenAPI description of web APIs into an MCP server. OpenAPI is a machine-readable document describing API endpoints, inputs, and outputs.

In plain words
What is it for?
Use it to install dependencies, run focused or complete tests, check types and style, format Python code with Black, and build the package.
Why use it?
It explains how the project converts API descriptions into usable tools and sets the required development checks and formatting rules.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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-scribe CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/the-swarm-corporation/mcp-scribe/claude-md"><img src="https://agentmods.dev/badge/instructions/the-swarm-corporation/mcp-scribe/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,113 This file is loaded in full into every session.
When invoked 2,113 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 $0.02113 $0.02113
Opus 5 $0.01056 $0.01056
Sonnet 5 $0.00423 $0.00423
Haiku 4.5 $0.00211 $0.00211

Measured 11d ago against content hash f403f3ece39d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-scribe 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 11d 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 · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in this repository.

What this is

mcp-scribe turns an OpenAPI schema into a production-grade MCP server. It is a compiler with a runtime attached: it lowers an OpenAPI document into MCP tools, then executes those tools as real HTTP requests with auth, retries, rate limiting, and response shaping already handled.

Package lives in src/mcp_scribe/ (src layout, Poetry, packages = [{include = "mcp_scribe", from = "src"}]).

Commands

poetry install --all-extras --with lint,test

poetry run pytest -q                        # 201 tests, ~1s
poetry run pytest tests/test_toolset.py -q  # one file
poetry run pytest -m remote                 # network tests (opt-in marker)

poetry run ruff check src tests             # lint
poetry run black src tests examples         # format  <-- see below
poetry run mypy src/mcp_scribe              # types
poetry build

Formatting: black only. Do not run ruff format.

black at line-length = 70 is the formatter of record. [tool.black] and [tool.ruff] both pin 70 in pyproject.toml, and they must stay identical — when they drift, each tool rewrites what the other just wrote and every file shows up as modified.

At 70 columns black and ruff format genuinely disagree (tuple-unpacking RHS, assert x, msg parenthesization). They agreed at 100; they do not at 70. So:

  • Format with black. Never run ruff format — it will fight black on ~2 files and reintroduce the churn loop.
  • Lint with ruff check. That is ruff's only job here.
  • E501 is in ruff's ignore list. At 70 the remaining long lines are URLs, OpenAPI keyword names, and string literals no formatter can split; enforcing it produces 400+ findings black cannot act on.

If a ruff check --fix result and black disagree, verify they reach a fixpoint (apply the fix, run black, confirm nothing changes) before committing.

README.md's Development section still lists ruff format --check src tests. That command now fails by design — it should be black --check.

Read the full file on GitHub · 159 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. 11d ago First seen · 159 lines · 2,113 tokens per session scan A f403f3ece39d

Subscribe to this mod's changes

mcp-scribe CLAUDE.md is an instructions file published in the GitHub repository The-Swarm-Corporation/mcp-scribe (7 stars, last pushed 19d ago), licensed Apache-2.0. It adds 2,113 tokens to every session, about $0.0106 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens