Borrowing it
Nothing to install: this file belongs to mauriziomocci/deep-reasoning-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/mauriziomocci/deep-reasoning-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/mauriziomocci/deep-reasoning-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/mauriziomocci/deep-reasoning-mcp/claude-md)<a href="https://agentmods.dev/instructions/mauriziomocci/deep-reasoning-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mauriziomocci/deep-reasoning-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.
<a href="https://agentmods.dev/instructions/mauriziomocci/deep-reasoning-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mauriziomocci/deep-reasoning-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01529 | $0.01529 |
| Opus 5 | $0.00764 | $0.00764 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
deep-reasoning-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 10d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guide for Claude Code - deep-reasoning-mcp: recursive analysis engine for structured what-if reasoning.
Quick Reference
# Install dependencies
uv sync
# Run the server locally
uv run deep-reasoning-mcp
# Run tests
uv run pytest
# Type checking
uv run mypy deep_reasoning_mcp/
# Format
uv run ruff format deep_reasoning_mcp/
# Lint
uv run ruff check deep_reasoning_mcp/
Architecture
Stack: Python 3.10+ | FastMCP (mcp SDK) | Pydantic 2.x | httpx (async HTTP) | asyncio
Package: deep_reasoning_mcp/
deep_reasoning_mcp/
__init__.py # Package entry point, exports `mcp`
server.py # MCP tool handlers (7 tools)
models.py # Pydantic input models, enums (AnalysisType, ExecutionMode, etc.)
tree.py # Reasoning tree construction and navigation helpers
session.py # Session persistence to ~/.claude/deep-reasoning/
prompts.py # Analysis-type-specific prompt engineering
llm.py # Anthropic API client with rate limiting (semaphore + cooldown)
Execution modes:
orchestrator(default without API key): server manages tree state and prompt structure, Claude Code performs the reasoning. Zero extra cost.autonomous(default with API key): server calls the Anthropic API directly. RequiresANTHROPIC_API_KEY.
Tool workflow: deep_scan -> deep_explore (repeat) -> deep_synthesize
Session persistence: JSON files in ~/.claude/deep-reasoning/sessions/ with an index at ~/.claude/deep-reasoning/index.json.
Agent Rules
CRITICAL: Understand Before Implementing
Before writing any code, invest time in understanding the full context: how the existing system works, why it works that way, and what already exists. Read the affected files thoroughly. Never assume — verify in source code.
CRITICAL: Verify Before Asserting
Never present assumptions or hypotheses as verified facts. If something has not been verified in source code, say so explicitly. Unverified statements undermine credibility.
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.
- 10d ago First seen · 171 lines · 1,529 tokens per session scan A d2228eb8e9e5
deep-reasoning-mcp CLAUDE.md is an instructions file published in the GitHub repository mauriziomocci/deep-reasoning-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,529 tokens to every session, about $0.0076 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.
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).
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.
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.
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).