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/naptila/recaf-mcp/agents-mdgit clone --depth 1 https://github.com/Naptila/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/naptila/recaf-mcp/agents-md)<a href="https://agentmods.dev/instructions/naptila/recaf-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/naptila/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 5.1 | $0.00887 | $0.00887 |
| Opus 5 | $0.00443 | $0.00443 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00089 | $0.00089 |
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 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Scope and Sources of Truth
This repository integrates with Recaf 4 but does not vendor Recaf source or documentation.
recaf-mcp-plugin/build.gradlepinsrecafVersion; it is the compile-time compatibility baseline.- The generic JAR selected by
RECAF_JARis the runtime compatibility target. - Recaf's developer documentation is a rolling upstream reference. Verify version-sensitive APIs against the pinned dependency, source for that revision, and the build.
tmp/is ignored local scratch space. Never depend on its contents or commit copied Recaf documentation, sample targets, generated output, or model notes.
Project Structure
recaf-mcp-plugin/contains the Java Recaf plugin and Worker implementation. Production code is undersrc/main/java/me/naptila/recafmcp/, resources are undersrc/main/resources/, and matching JUnit tests are undersrc/test/java/.recaf-mcp-bridge/contains the Python MCP stdio bridge and Worker session supervisor. Production modules are undersrc/; pytest tests are undertests/.README.mdandREADME-ZH.mdare the public user documentation.
Build and Test Commands
Run commands from the relevant module directory.
For the plugin:
./gradlew buildcompiles the plugin, runs all JUnit tests, and creates the plugin JAR inbuild/libs/../gradlew testruns the Java test suite../gradlew runRecafHeadlesslaunches the pinned headless development runtime../gradlew -q javaToolchainslists detected JDK installations.
The Gradle wrapper is authoritative. The build uses a JDK 25 toolchain and emits Java 22-compatible bytecode.
For the bridge:
uv sync --frozeninstalls the locked Python environment.uv run pytest -qruns the Python test suite.uv run recaf-mcp-bridge --stdiostarts the development stdio server.
Python 3.11 or newer is required. Do not hand-edit uv.lock; update it through
uv.
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 · 97 lines · 887 tokens per session scan A 966f4413fcae
recaf-mcp AGENTS.md is an instructions file published in the GitHub repository Naptila/recaf-mcp (12 stars, last pushed 13d ago), licensed MIT. It adds 887 tokens to every session, about $0.0044 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
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.
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.
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).