Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/cyberkaida/reverse-engineering-assistant/claude-mdgit clone --depth 1 https://github.com/cyberkaida/reverse-engineering-assistantWrote 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/cyberkaida/reverse-engineering-assistant/claude-md)<a href="https://agentmods.dev/instructions/cyberkaida/reverse-engineering-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/cyberkaida/reverse-engineering-assistant/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 | $0.03603 | $0.03603 |
| Opus 5 | $0.01801 | $0.01801 |
| Sonnet 5 | $0.00721 | $0.00721 |
| Haiku 4.5 | $0.00360 | $0.00360 |
Grade A, and why
reverse-engineering-assistant 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 5d 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 — 330 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
ReVa (Reverse Engineering Assistant) is a Ghidra extension that provides a Model Context Protocol (MCP) server for AI-assisted reverse engineering. It supports both GUI and headless modes, with streamable HTTP transport for direct connections and stdio transport for Claude CLI integration.
Build and Test Commands
Java Extension (Ghidra Plugin)
# Set Ghidra installation directory first
export GHIDRA_INSTALL_DIR=/path/to/ghidra
# Build the extension
gradle
# Install directly to Ghidra's extension directory
gradle install
# Java unit tests (no Ghidra environment)
gradle test --info
# Integration tests (require GUI/headed environment, fork=1)
gradle integrationTest --info
# Run specific test class
gradle integrationTest --tests "*DecompilerToolProviderIntegrationTest" --info
# Run specific test method
gradle test --tests "*AddressUtilTest.testFormatAddress" --info
Important: Use gradle directly, NOT gradle wrapper (./gradlew)
Python CLI and Tests
# Setup Python environment with uv
uv sync
# Run all Python tests
uv run pytest
# Run specific test file
uv run pytest tests/test_cli.py -v
# Run tests by marker
uv run pytest -m unit # Fast unit tests with mocks
uv run pytest -m integration # Integration tests with PyGhidra
uv run pytest -m e2e # End-to-end subprocess tests
# Run CLI locally
uv run mcp-reva --verbose
# Install CLI for development
uv pip install -e .
Running the Complete Test Suite
Run all Java unit tests:
gradle test
Run all Java integration tests:
gradle integrationTest
Run all Python tests (unit, integration, and e2e):
uv run pytest
Run specific Python test categories:
uv run pytest -m unit # Unit tests only
uv run pytest -m integration # Integration tests only
uv run pytest -m e2e # End-to-end tests only
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.
- 5d ago First seen · 330 lines · 3,603 tokens per session scan A 3f537e0bcf5f
reverse-engineering-assistant CLAUDE.md is an instructions file published in the GitHub repository cyberkaida/reverse-engineering-assistant (822 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,603 tokens to every session, about $0.0180 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.
Other instructions, from other repositories
GhidrAssistMCP CLAUDE.md
Claude Code instructions for symgraph/GhidrAssistMCP, covering claude.md, build and development commands, building the extension, set ghidrainstalldir environment variable first and build the extension.
Reversecore_MCP AGENTS.md
AGENTS.md instructions for sjkim1127/Reversecore_MCP, covering agent customizations for reversecoremcp, project overview, quick commands, development setup and create virtual environment.
bg3se-macos CLAUDE.md
Instructions for tdimino/bg3se-macos, covering bg3se-macos, stack, structure, modding toolkit and core pipeline.
CodeCartographer CLAUDE.md
Claude Code instructions for HuginnIndustries/CodeCartographer, covering claude.md, commands, run a single test file, architecture and surface priority (for user-facing docs).
vikshana-graft-app CLAUDE.md
Claude Code instructions for vikshana/vikshana-graft-app, covering claude.md, project overview, build commands, frontend and backend.
Multimodal-voice-assistant CLAUDE.md
Instructions for tristan-mcinnis/Multimodal-voice-assistant, covering claude.md, project overview, running the assistant, or: pip install -e '.[dev]' and configure via .env (recommended).