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/tha23rd/recaf-mcp/agents-mdgit clone --depth 1 https://github.com/tha23rd/recaf-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/tha23rd/recaf-mcp/agents-md)<a href="https://agentmods.dev/instructions/tha23rd/recaf-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tha23rd/recaf-mcp/agents-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 | $0.01133 | $0.01133 |
| Opus 5 | $0.00566 | $0.00566 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
recaf-mcp 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 4d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Overview
MCP (Model Context Protocol) server plugin for Recaf, enabling AI agents to perform Java reverse engineering tasks. 68 tools across 13 categories.
- Repo: https://github.com/tha23rd/recaf-mcp (private)
- Recaf: https://github.com/Col-E/Recaf
- Recaf docs: https://recaf.coley.software/dev/index.html
Architecture
- recaf-mcp-plugin/ — Java Recaf plugin with embedded Jetty HTTP server + MCP SDK
- recaf-mcp-bridge/ — Python stdio-to-HTTP bridge for tools needing stdin/stdout
- Plugin runs inside Recaf's JVM, exposes Streamable HTTP endpoint at
localhost:8085/mcp - Shadow JAR shades Jetty, MCP SDK, and TOON into the plugin JAR
Build & Test
cd recaf-mcp-plugin
./gradlew test # Run unit tests
./gradlew shadowJar # Build plugin JAR
./gradlew runRecaf # Build, deploy to ~/.config/Recaf/plugins/, launch Recaf
Plugin JAR output: recaf-mcp-plugin/build/libs/recaf-mcp-plugin-<version>.jar
Release Flow
- Bump version in
recaf-mcp-plugin/build.gradle(version = 'x.y.z') - Commit and push
- Tag:
git tag vx.y.z && git push origin vx.y.z - GitHub Actions builds the JAR and creates a release with the artifact attached
CI runs on every push to master/main and on PRs.
Key Conventions
- Tool providers extend
AbstractToolProviderinrecaf-mcp-plugin/src/main/java/dev/recafmcp/providers/ - Resource providers in
recaf-mcp-plugin/src/main/java/dev/recafmcp/resources/ - Recaf dependencies are
compileOnly(provided at runtime by Recaf) - Response format: TOON by default (
-Drecaf.mcp.format=jsonfor JSON) - Port/host configurable via
RECAF_MCP_PORT/RECAF_MCP_HOSTenv vars
Issue Tracking with bd (beads)
IMPORTANT: This project uses bd (beads) for ALL issue tracking. Do NOT use markdown TODOs, task lists, or other tracking methods.
Why bd?
- Dependency-aware: Track blockers and relationships between issues
- Git-friendly: Auto-syncs to JSONL for version control
- Agent-optimized: JSON output, ready work detection, discovered-from links
- Prevents duplicate tracking systems and confusion
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.
- 4d ago First seen · 130 lines · 1,133 tokens per session scan A 1f79dbbdc154
recaf-mcp AGENTS.md is an instructions file published in the GitHub repository tha23rd/recaf-mcp (11 stars, last pushed 3mo ago), licensed MIT. It adds 1,133 tokens to every session, about $0.0057 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
questdb CLAUDE.md
Claude Code instructions for questdb/questdb, covering claude.md, project overview, coding guidelines, tests and questdb's sql dialect.
liteflow CLAUDE.md
Instructions for dromara/liteflow, covering claude.md, 概述, 命令, 构建 and 构建整个项目（模块集由 jdk 版本自动选择 —— 见下方说明）.
BitcoinAddressFinder CLAUDE.md
Claude Code instructions for bernardladenthin/BitcoinAddressFinder, covering claude.md — bitcoinaddressfinder, project overview, build system, common commands and compile only.
imgui-java CLAUDE.md
Claude Code instructions for SpaiR/imgui-java: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
langchain4j-cdi copilot-instructions.md
Copilot instructions for langchain4j/langchain4j-cdi, covering langchain4j cdi integration, working effectively, prerequisites, bootstrap and build and essential commands.
leyden-perf-test AGENTS.md
Instructions for quintesse/leyden-perf-test, covering agents.md - leyden performance test harness, project overview, purpose, primary goals and current state.