Borrowing it
Nothing to install: this file belongs to JoshuaOliphant/scratchpad_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.
curl -O https://raw.githubusercontent.com/JoshuaOliphant/scratchpad_mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/JoshuaOliphant/scratchpad_mcpWrote 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.
[](https://agentmods.dev/instructions/joshuaoliphant/scratchpad_mcp/claude-md)<a href="https://agentmods.dev/instructions/joshuaoliphant/scratchpad_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/joshuaoliphant/scratchpad_mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00703 | $0.00703 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00141 | $0.00141 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
scratchpad_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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 91 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.
Overview
This is an MCP (Model Context Protocol) server that implements a "think" tool for structured reasoning, based on the Anthropic blog post about improving Claude's problem-solving capabilities through dedicated thinking steps.
Project Structure
scratchpad_mcp/
├── src/
│ └── mcp_server_scratchpad/
│ ├── __init__.py # Entry point with main() function
│ ├── __main__.py # Module runner
│ └── server.py # Core server implementation
├── pyproject.toml # Package configuration and dependencies
├── README.md # User documentation
└── LICENSE # MIT license
Development Commands
# Install dependencies
uv sync
# Run the server directly
uv run mcp-server-scratchpad
# Run development server with MCP Inspector
uv run mcp dev src/mcp_server_scratchpad/server.py
# Run tests (when added)
uv run pytest
# Format code
uv run ruff format
# Check code style
uv run ruff check
Package Distribution
This package is designed to be distributed via PyPI and run with uvx:
# Run without installation (recommended)
uvx mcp-server-scratchpad
# Or install globally
pip install mcp-server-scratchpad
Architecture
The codebase uses the low-level MCP server API:
src/mcp_server_scratchpad/server.py: Main server implementation- Uses in-memory storage for thoughts (list:
thoughts_log) - Implements three MCP primitives:
- Tools:
think()for logging thoughts,clear_thoughts()for resetting - Resources:
read_resource()exposes thoughts atlog://thoughts - Prompts:
get_prompt()provides structured thinking template
- Tools:
- Uses stdio transport for communication
- Uses in-memory storage for thoughts (list:
Key Implementation Details
- Server Type: Uses the low-level
mcp.server.ServerAPI (not FastMCP) for maximum control and compatibility with packaging standards.
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.
- 7d ago First seen · 91 lines · 703 tokens per session scan A 0424bc6e203d
scratchpad_mcp CLAUDE.md is an instructions file published in the GitHub repository JoshuaOliphant/scratchpad_mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 703 tokens to every session, about $0.0035 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 2026-09-01.
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.
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.
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).
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).
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.
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.