sweeppea-mcp-info: Instructions file for Claude Code

CLAUDE.md

sweeppea-mcp-info CLAUDE.md is an instructions file for Claude Code from Sweeppea-Development-Lab/sweeppea-mcp-info. It costs 1,699 tokens per session, scanned A, original, MIT.

Repository guidance for maintaining Sweeppea's public MCP server manifest. MCP is a standard way for AI assistants to use tools; this repository describes a remote server but does not contain its implementation.

In plain words
What is it for?
Use it when updating release information, comparing tool lists between repositories, checking the authoritative tool count, or reviewing the known index.js issue.
Why use it?
It helps keep the manifest's version, tool list, and counts aligned with the separate server repository, while documenting a known defect before changes are committed.

Instructions file for Claude Code

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

This is Sweeppea-Development-Lab/sweeppea-mcp-info's own configuration. It tells Claude Code how to work on sweeppea-mcp-info 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 sweeppea-mcp-info configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is grep -oE '^#### [a-z_]+' ../renaissance-mcp/README.md | sed 's/#### //' | sort -u > /tmp/up.txt.

Reuse

Borrowing it

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

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 sweeppea-mcp-info CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sweeppea-development-lab/sweeppea-mcp-info/claude-md.svg)](https://agentmods.dev/instructions/sweeppea-development-lab/sweeppea-mcp-info/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sweeppea-development-lab/sweeppea-mcp-info/claude-md"><img src="https://agentmods.dev/badge/instructions/sweeppea-development-lab/sweeppea-mcp-info/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,699 This file is loaded in full into every session.
When invoked 1,699 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01699 $0.01699
Opus 5 $0.00849 $0.00849
Sonnet 5 $0.00340 $0.00340
Haiku 4.5 $0.00170 $0.00170

Measured 6d ago against content hash bad4a289dcbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sweeppea-mcp-info CLAUDE.md scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=sweeppea"
CLAUDE.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 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.

What this repo is (and is not)

This is the public info / distribution manifest for the Sweeppea MCP Server — not the server itself.

The real server is remote and hosted: https://mcp.sweeppea.com/ (Streamable HTTP, Bearer auth, MCP protocol 2025-11-25). Its 83 tools proxy the Sweeppea API v3 and its implementation lives in a different repository (renaissance-mcp, sibling directory ../renaissance-mcp). Nothing you change here alters the behavior of those 83 tools.

To resync after an upstream release, read ../renaissance-mcp/CHANGELOG.md and package.json for the version and counts, then diff the tool names instead of trusting the changelog prose:

grep -oE '^#### [a-z_]+' ../renaissance-mcp/README.md | sed 's/#### //' | sort -u > /tmp/up.txt
grep -oE '^\| `[a-z_]+`' README.md | tr -d '|` ' | sort -u > /tmp/here.txt
comm -23 /tmp/up.txt /tmp/here.txt   # new upstream, missing here
comm -13 /tmp/up.txt /tmp/here.txt   # here but gone upstream — must be removed

The authoritative count is find ../renaissance-mcp/src/tools -name '*Tool.js' | wc -l minus one (BaseSweeppeaTool.js is not a tool).

What this repo actually ships:

  • README.md — the public catalog: tool tables, per-platform setup guides, protocol table, badges. This is the primary deliverable and what most changes touch.
  • index.js — a tiny stdio wrapper exposing a single local tool, sweeppea_connect, that just returns the remote endpoint + config JSON for a given client platform. It exists so registries (Glama, the official MCP registry) and docker run have something executable to list; it never calls the Sweeppea API.
  • server.json — manifest for the official MCP registry (mcp-publisher). Untracked in git.
  • glama.json, Dockerfile — registry/container metadata for index.js.

Consequence: "add a tool" here means documenting a tool that already exists upstream, never implementing one.

Read the full file on GitHub · 116 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. 6d ago First seen · 116 lines · 1,699 tokens per session scan A bad4a289dcbc

Subscribe to this mod's changes

sweeppea-mcp-info CLAUDE.md is an instructions file published in the GitHub repository Sweeppea-Development-Lab/sweeppea-mcp-info (2 stars, last pushed 29d ago), licensed MIT. It adds 1,699 tokens to every session, about $0.0085 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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 · 5,182 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

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

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

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