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/agents-mdgit clone --depth 1 https://github.com/cyberkaida/reverse-engineering-assistantWhat 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 | $0.00853 | $0.00853 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
reverse-engineering-assistant AGENTS.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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
ReVa (Reverse Engineering Assistant) is a Ghidra extension that provides a Model Context Protocol (MCP) server for AI‑assisted reverse engineering. It offers a collection of tool providers that expose Ghidra functionality (decompiler, strings, symbols, etc.) via a JSON‑based MCP interface.
Build & Test Commands
Building the extension
# Set the Ghidra installation directory first
export GHIDRA_INSTALL_DIR=/path/to/ghidra
gradle # no wrapper – use the system `gradle` command
Testing
- Unit tests:
gradle test --info - Integration tests (require a headed GUI environment):
gradle integrationTest --info - Run a single unit test:
gradle test --tests "*MyTestClass.testMethod" --info - Run a single integration test:
gradle integrationTest --tests "*MyIntegrationTest" --info - Check (includes lint & both test suites):
gradle check
Project Structure
src/main/java/reva/– Core source codeutil/– Foundational utilities (AddressUtil,ProgramLookupUtil, etc.)plugin/– Ghidra plugin infrastructure and configurationserver/– Embedded Jetty server and MCP transporttools/– Tool providers (decompiler, functions, strings, symbols, …)resources/– Read‑only MCP resourcesservices/– Service‑layer abstractionsui/– Optional UI components
src/test/– Unit tests (no Ghidra runtime required)src/test.slow/– Integration tests (require Ghidra environment)
Development Guidelines
Code Style
- Java version: Target Java 21.
- Formatting: 4‑space indentation, no trailing whitespace. Imports sorted alphabetically, static imports after regular imports.
- Naming: Classes & enums
PascalCase; methods & variablescamelCase; constantsUPPER_SNAKE_CASE. - Types: Prefer concrete generic types (
List<>,Map<>) over raw collections; useOptionalfor nullable returns. - Documentation: Every public class and method must have a Javadoc comment describing purpose, parameters, and return values.
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.
- 2d ago First seen · 86 lines · 853 tokens per session scan A c68467a8b1a3
reverse-engineering-assistant AGENTS.md is an instructions file published in the GitHub repository cyberkaida/reverse-engineering-assistant (821 stars, last pushed 8d ago), licensed Apache-2.0. It adds 853 tokens to every session, about $0.0043 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
Reversecore_MCP 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.
ida-pro-mcp CLAUDE.md
Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.
Gladys AGENTS.md
AGENTS.md instructions for GladysAssistant/Gladys, covering agents.md, cursor cloud specific instructions, running the app (dev mode), non-obvious caveats and feature specs (spec-first process).
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.
openclaw CLAUDE.md
Claude Code instructions for openclaw/openclaw, a project described as: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞.