ultrathink: Instructions file for Claude Code

CLAUDE.md

ultrathink CLAUDE.md is an instructions file for Claude Code from husniadil/ultrathink. It costs 2,854 tokens per session, scanned A, original, MIT.

A project instruction file for UltraThink, a server that lets compatible AI clients call software tools through the Model Context Protocol (MCP), a standard way for AI applications to use external tools.

In plain words
What is it for?
It helps developers install dependencies, run the server and test client, run tests with or without coverage, format and check code, and clean cached files.
Why use it?
It gathers the project’s setup, testing, formatting, linting, and type-checking commands in one place, reducing guesswork when developing or maintaining the server.

Instructions file for Claude Code

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

This is husniadil/ultrathink's own configuration. It tells Claude Code how to work on ultrathink 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 ultrathink configures →

Reuse

Borrowing it

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

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 ultrathink CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/husniadil/ultrathink/claude-md"><img src="https://agentmods.dev/badge/instructions/husniadil/ultrathink/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,854 This file is loaded in full into every session.
When invoked 2,854 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 $0.02854 $0.02854
Opus 5.5 $0.01142 $0.01142
Sonnet 5.5 $0.00571 $0.00571
Haiku 4.5 $0.00285 $0.00285

Measured 2mo ago against content hash d2099dffbbe1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ultrathink 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 2mo 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 · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 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.

Project Overview

UltraThink is an MCP (Model Context Protocol) server built with FastMCP framework. The project provides tools that can be consumed by MCP clients.

Development Commands

Setup & Dependencies

# Install dependencies (managed by uv)
uv sync

Task Commands (npm-like)

# List all tasks
uv run task --list

# Run server
uv run task run

# Run tests with coverage
uv run task test

# Quick tests (no coverage)
uv run task test-quick

# Run test client
uv run task client

# Format code (ruff + prettier)
uv run task format

# Lint code
uv run task lint

# Type check with mypy
uv run task typecheck

# Clean cache
uv run task clean

Direct Commands (Alternative)

Prefer using uv run task commands above. For direct execution:

# Run the server directly
uv run ultrathink

# Run the test client directly (connects to server via in-memory transport)
uv run task client
# Or: uv run python examples/client.py

This will test all available tools by connecting to the MCP server and calling each tool with sample inputs.

Architecture

Project Structure

src/ultrathink/                    # Main package
├── models/                        # DATA MODELS
│   ├── thought.py                 # Thought, ThoughtRequest, ThoughtResponse models
│   └── session.py                 # ThinkingSession model
├── services/                      # BUSINESS LOGIC
│   └── thinking_service.py        # UltraThinkService
├── interface/                     # EXTERNAL INTERFACE
│   └── mcp_server.py              # FastMCP server & tool registration
├── __init__.py                    # Package exports
└── __main__.py                    # CLI entry point

tests/                             # Test files (100% coverage, mirroring source structure)
├── models/
│   ├── test_thought.py            # Thought model tests
│   └── test_session.py            # Session logging tests
├── services/
│   └── test_thinking_service.py   # Service validation, functionality, branching, multi-session
├── interface/
│   └── test_mcp_server.py         # MCP tool function tests
└── test_cli.py                    # CLI entry point tests

examples/                          # Example/demo scripts
└── client.py                      # Test harness for the MCP server

Read the full file on GitHub · 369 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. 2mo ago First seen · 369 lines · 2,854 tokens per session scan A d2099dffbbe1

Subscribe to this mod's changes

ultrathink CLAUDE.md is an instructions file published in the GitHub repository husniadil/ultrathink (21 stars, last pushed 6mo ago), licensed MIT. It adds 2,854 tokens to every session, about $0.0114 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 2026-08-30.

Related

ultrathink CLAUDE.md compared with instructions from other repositories

ultrathink CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ultrathink CLAUDE.mdhusniadil/ultrathinkInstructions file216mo agoMITA2,854Claude 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