JoasASantos/REA-Prompts

REAP - Prompts for you to use REA (Reverse Engineer Anything), get the most out of it, and clone or break down any program

REA Investigation Prompts (REAP) – Prompt library for the RE​A reverse‑engineering AI agent

What it is – A curated set of ready‑to‑paste prompts designed for the REA (Reverse Engineer Anything) toolchain. REA is an AI‑powered coding‑agent that can statically analyse binaries, firmware, Android APKs, Electron apps, kernels, games, etc. The repository does not contain any analysis code itself; it only provides the textual prompts that tell the agent what to look for and how to structure its answers.

Key ideas

  • Each prompt follows a strict template: replace the <angle brackets> with concrete values and ask the agent to focus on a single feature.
  • The prompts enforce evidence‑backed responses, separating confirmed facts, hypotheses, and unknowns, and they require citations such as file names, function addresses, or code snippets.
  • The collection is organized by target domain (native binaries, games, firmware, Android, kernel drivers, vulnerability research, etc.) and includes meta‑prompts for writing new prompts, installation, and next‑step guidance.

Typical workflow

  1. Install REA – npx rea‑agents@latest setup (the README shows a sample install‑verification prompt).
  2. Pick a prompt from the relevant section, fill in the placeholders, and feed it to the REA agent.
  3. The agent returns a structured report: entry points, data flow, strings, decompiled pseudocode, triage maps, or clean‑room specifications, all with explicit evidence references.

Who it’s for

  • Security researchers, CTF participants, and bug‑bounty hunters who want a systematic way to drive an AI reverse‑engineering assistant.
  • Developers needing clean‑room specifications for re‑implementing proprietary functionality.
  • Game modders, firmware analysts, and anyone performing static analysis of closed‑source software.

Installation / usage The repository itself needs no build step – just clone it and copy the desired prompt. The actual REA tool is installed separately via the npx rea‑agents@latest setup command shown in the Install & verify section.

License & attribution The README credits the original REA tools (https://rea.tools/), the official prompt gallery, and the community members who coined the REAP name. No explicit software license is listed, so users should treat the prompts as community‑shared content and respect the usage disclaimer that all analysis must be performed on software they own or have permission to test.

Why it matters Prompt engineering is a crucial part of getting reliable results from AI agents. By providing a disciplined, evidence‑oriented prompt library, REAP helps prevent vague or speculative AI answers and makes large‑scale reverse‑engineering projects more reproducible and legally compliant.

Related

  • Project
    microsoft/skills

    Microsoft / skills is a genuine open‑source toolbox that equips AI coding agents (e.g., GitHub Copilot) with ready‑made, Azure‑specific “skills” – code snippets, templates, and MCP server scaffolding – so the agents can generate correct Azure SDK calls, manage Foundry resources, and follow governance patterns. Install via `npx skills add microsoft/skills`, pick only the needed skills (≈175 across Python, .NET, TypeScript, Java, Rust), and use the provided `AGENTS.md` and MCP configs to build custom agents for backend, frontend, infrastructure, or planning tasks.

  • Project
    sopaco/deepwiki-rs

    Litho (deepwiki‑rs) is a Rust‑based tool that automatically generates C4‑style architecture documentation from a codebase using LLMs. It scans source files, extracts structure and comments, runs AI agents to infer architecture, creates Mermaid diagrams, and outputs a synced wiki. Supports many languages, can integrate external docs, and includes companion tools (Litho Book viewer, Mermaid Fixer). Designed for CI/CD integration and aims to eliminate manual documentation upkeep.

  • Project
    Chachamaru127/claude-code-harness

    A management framework for AI coding assistants that adds structured planning, safety guardrails, and mandatory review steps to ensure reliable code generation.

  • Project
    cloudflare/skills

    A plug‑in library that adds Cloudflare‑specific “Agent Skills” to AI coding assistants (Claude Code, Codex, Cursor, VS Code, etc.). Each skill teaches the agent how to work with a Cloudflare product—Workers, Wrangler, Durable Objects, Turnstile, Cloudflare One, and more—by providing up‑to‑date docs, CLI commands, and API calls via Cloudflare’s remote MCP server. Install via the native plugin marketplace of the target agent or manually copy the skill folders.