re-mcp: Instructions file for Claude Code

CLAUDE.md

re-mcp CLAUDE.md is an instructions file for Claude Code from jtsylve/re-mcp. It costs 1,499 tokens per session, scanned A, original, Apache-2.0.

A project instruction document for a reverse-engineering server that supports IDA Pro and Ghidra, tools for examining compiled programs.

In plain words
What is it for?
It explains how to run the server, where its three packages live, and how to lint, format, and test the code.
Why use it?
It gives contributors the project's package layout, commands, architecture references, and required checks in one place.

Instructions file for Claude Code

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

This is jtsylve/re-mcp's own configuration. It tells Claude Code how to work on re-mcp 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 re-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jtsylve/re-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.

Copy the file
curl -O https://raw.githubusercontent.com/jtsylve/re-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jtsylve/re-mcp

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 re-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jtsylve/re-mcp/claude-md.svg)](https://agentmods.dev/instructions/jtsylve/re-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jtsylve/re-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jtsylve/re-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,499 This file is loaded in full into every session.
When invoked 1,499 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 $0.01499 $0.01499
Opus 5 $0.00749 $0.00749
Sonnet 5 $0.00300 $0.00300
Haiku 4.5 $0.00150 $0.00150

Measured 8d ago against content hash 651d016fcd36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

re-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 8d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 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

Multi-backend reverse-engineering MCP server. Python + FastMCP, stdio and streamable HTTP transports. Backends: IDA Pro (idalib) and Ghidra (pyghidra).

Commands

uv sync                              # Install dependencies
uv run re-mcp-ida                    # Run IDA backend (direct stdio mode)
uv run re-mcp-ghidra                 # Run Ghidra backend (direct stdio mode)
uv run ruff check packages/          # Lint
uv run ruff format packages/         # Format
uv run ruff check --fix packages/    # Lint with auto-fix

Pre-commit hooks run REUSE compliance checks, ruff lint (with --fix --exit-non-zero-on-fix), ruff format, idalib threading lint (scripts/lint_ida_threading.py), and pytest on commit.

Architecture

See docs/architecture.md for full details. The project is a monorepo with three packages:

  • re-mcp-core (packages/re-mcp-core/src/re_mcp/): generic MCP supervisor infrastructure — supervisor.py, daemon.py, proxy.py, worker_provider.py, backend.py, server.py, context.py, exceptions.py, helpers.py, models.py, sandbox.py, transforms.py, _process.py
  • re-mcp-ida (packages/re-mcp-ida/src/re_mcp_ida/): IDA-specific backend — backend.py, server.py, session.py, helpers.py, exceptions.py, models.py, transforms.py, _cli.py, tools/, resources.py, prompts/
  • re-mcp-ghidra (packages/re-mcp-ghidra/src/re_mcp_ghidra/): Ghidra-specific backend — backend.py, server.py, session.py, helpers.py, exceptions.py, models.py, transforms.py, _cli.py, tools/, resources.py, prompts/

Key points for editing:

  • Supervisor (re_mcp.supervisor): entry point, ProxyMCP(FastMCP) + WorkerPoolProvider. Registers generic management tools (close_database, save_database, list_databases, wait_for_analysis, list_targets); each backend registers open_database via backend.py. Management tools use try_get_session_id() (from re_mcp.context). Most omit ctx from their signature; save_database is the exception (it accepts ctx for heartbeat progress notifications, but FastMCP strips it from the JSON schema).
  • Backends (re_mcp_ida.backend, re_mcp_ghidra.backend): implement the Backend protocol — register open_database, prompts, backend-specific instructions, and target listing. Discovered via re_mcp.backends entry points.
  • Worker provider (re_mcp.worker_provider): WorkerPoolProvider(Provider), RoutingTool(Tool), RoutingTemplate(ResourceTemplate), Worker dataclass. Session-scoped ownership under _lockclose_for_session() and detach_all() are atomic. ensure_session_cleanup() registers a disconnect callback on the MCP session's exit stack.
  • Workers (re_mcp_ida.server, re_mcp_ghidra.server): one per database, stdio transport. Entry points: re-mcp-ida-worker, re-mcp-ghidra-worker.
  • Bootstrap-safe modules (importable without bootstrap()): all re_mcp modules, plus <backend>.exceptions, <backend>.models, <backend>.transforms, <backend>.prompts/. The supervisor never imports backend-engine-required modules.
  • Engine-required modules: <backend>.helpers, <backend>.session, <backend>.tools/, <backend>.resources. Backend-specific imports — only loaded in worker processes.
  • @session.require_open (no parens) — decorator on nearly every tool
  • All tools return Pydantic models on success; raise BackendError subclass on failure (IDAError / GhidraError)

Read the full file on GitHub · 64 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. 8d ago First seen · 64 lines · 1,499 tokens per session scan A 651d016fcd36

Subscribe to this mod's changes

re-mcp CLAUDE.md is an instructions file published in the GitHub repository jtsylve/re-mcp (151 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,499 tokens to every session, about $0.0075 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 2026-08-30.

Related

Other instructions, from other repositories

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

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

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

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