More room for your next idea. Membership from $9.99/month.Take a look

REA — Reverse Engineer Anythingv1.0.0

Investigate packaged software with REA: inspect JavaScript and Electron modules, IPC bridges and source evidence, then explain how a feature works. Free official open-source skill by morluto, with a tested static-analysis example and a clear MCP setup guide.

No reviews yetFeatured

See what you can make

Skip the interactive example

Loading the working example…

Open example
Interact with the sample. Scroll inside to explore.
Made with this SkillA traceable software investigation with original evidence

Actual REA 6.4.0 analysis · source locations · owned fixture

Open full example

What you get

A traceable software investigation with original evidence

What you can make

  • Investigate shipped software with module, process and source-location evidence.
  • Trace Electron IPC bridges in a real static-analysis notebook and download complete REA JSON.
  • Install the official skill and review MCP setup for Codex, Claude Code or Cursor.
Explore delivered files6 groups
  • Original SKILL.md + six reference guides
  • MIT license + pinned source hashes
  • Owned Desk Notes practice artifact
  • MCP setup guide for three agents
  • Actual analysis JSON + browsable notebook
  • Input hashes + delivery-manifest.json

Good fit

Developers and researchers inspecting software they own or are authorized to analyze.

Know the limits

REA by morluto, MIT licensed. This release tests a small static JavaScript artifact only; inferred relationships do not prove runtime behavior. Native engines and agent/model access are separate.

About this skill

REA by morluto, distributed free under MIT. The official rea-agents 6.4.0 skill and all six reference guides are preserved byte-for-byte. Skillrove adds an owned fictional Desk Notes artifact, a first-run helper and a browsable notebook built from actual REA output.

Investigate shipped applications and binaries with evidence, rather than guessing from the interface. Supported workflows include JavaScript/Electron, native binaries, managed assemblies, packaged resources and requested runtime observation. Available formats and tools depend on your installed REA version and analysis engines.

Read the full workflow

First run: install the skill, then run node scripts/analyze-example.mjs --output ./sample-rea from its folder. This downloads the pinned official runtime when needed, analyzes only the supplied fixture without executing it, and delivers analysis.json, input hashes, a browsable evidence notebook and a SHA-256 delivery manifest. It leaves existing output folders intact.

Agent setup: a skill ZIP supplies instructions; it does not register MCP. Preview npx rea-agents@6.4.0 setup --client codex --dry-run --json, review the proposed paths and backups, then use the interactive setup and restart your agent. Claude Code and Cursor are also supported. Requirements: Node.js 22.19+ within 22.x, 24.11+ within 24.x, or 26+, with npm. Static JavaScript needs no native analysis engine.

Source: https://github.com/morluto/rea at a56f7bb668ab23fec8d33f7af353ac7ed2fe1895; published npm package rea-agents 6.4.0. Copyright (c) 2026 morluto and original notices are included. Platform 1.0.0 is a distribution snapshot. The runtime is acquired separately from npm; it is not bundled in the skill ZIP.

Limits: this release was tested on the included small static JavaScript/Electron artifact. Static observations and inferred IPC pairings do not establish runtime reachability, security or correctness. Native decompilation requires an appropriate Hopper, Ghidra or IDA installation; commercial tools and agent/model access are separate. Only inspect software you own or are authorized to analyze. Tool results sent to your agent follow its model provider's data policy.

Read skill facts →Choose a skill by task →
DeveloperResearcherReverse engineeringSoftware analysis

FROM PACKAGE TO FIRST RESULT

Your first evidence-led investigation.

Follow a search request through a small fictional Electron package, inspect actual REA evidence, then connect its tools to your agent.

View example result

Open-source skill by morluto · MIT · Original repository · Pinned source snapshot

Free · MIT licenseNode.js 22.19+ (22.x), 24.11+ (24.x) or 26+ · npmStatic example: no paid analysis engine. Agent/model access is separate.
  1. 01

    Choose your agent

    These steps use a project folder. Open the project in your agent and run terminal commands from its root.

    Codex directory guide

    Package folder .agents/skills/reverse-engineer-anything

  2. 02

    Add the package

    Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.

    Downloads require a verified account. Choose a new folder if this Skill is already installed.

  3. 03

    Connect REA and inspect a small artifact

    The ZIP installs workflow instructions. To use REA through your agent, preview its MCP setup, review the proposed paths and backups, then run the interactive setup and restart the selected agent. The CLI sample below works without MCP registration.

    npx rea-agents@6.4.0 setup --client codex --dry-run --json
    npx rea-agents@6.4.0 setup --client codex

    Setup may replace this curated skill folder; keep sample files in a separate project if needed. Native analysis engines are optional for this static example.

    Manual sample commands and technical details

    Read SKILL.md, review the generator and check its runtime requirements before running:

    cd .agents/skills/reverse-engineer-anything
node scripts/analyze-example.mjs --output ./sample-rea
python3 -m http.server 8080 --bind 127.0.0.1 --directory sample-rea
    Your first result

    Open http://127.0.0.1:8080/. Filter IPC & bridge, search preload.cjs, expand original nodes and download the complete analysis JSON. Compare the input and delivery hashes. This is static inspection; the target app is never executed.

    The first run downloads official rea-agents 6.4.0 from npm when needed. Node.js 22.19+ in 22.x, 24.11+ in 24.x, or 26+ is required. Python 3 only serves the preview. Agent/model access and optional native engines are separate. Platform 1.0.0 identifies this distribution snapshot.

    If sample-rea already exists, change the output to ./sample-rea-2. Existing files are never overwritten.

    Prefer to ask your agent?

    Use reverse-engineer-anything. Read SKILL.md and SKILLROVE-SETUP.md. First inspect the MCP setup dry-run and explain its proposed configuration changes; wait for my approval before changing agent configuration. Then statically inspect the included Desk Notes fixture. Explain the notes:search request with source locations, distinguish observed facts from inferred IPC pairing, and list coverage limits. Do not execute the target application.

Ready to use your own facts?

For your own investigation, give the agent an absolute path to software you own or are authorized to inspect, one concrete question and whether runtime observation is permitted. Review what evidence may be sent to your model provider.

Reviews0

Share your first result

Tried this workflow? Help others decide with an honest review.

Before you choose this Skill

How do I get REA — Reverse Engineer Anything?

The package is free to download with a verified Skillrove account. Your agent subscription, model access and external provider credits are separate.

Compare access and pricing
Which agents can use this skill?

This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.

Codex setupClaude Code setupCursor setup
What files can this workflow generate?

The documented 1.0.0 workflow lists: Original SKILL.md + six reference guides; MIT license + pinned source hashes; Owned Desk Notes practice artifact; MCP setup guide for three agents; Actual analysis JSON + browsable notebook; Input hashes + delivery-manifest.json. Some files or exports are optional; follow the package’s setup and inspect the delivered result.

Review all deliverablesInspect the working example
What should I check before using the result?

The first run downloads official rea-agents 6.4.0 from npm when needed. Node.js 22.19+ in 22.x, 24.11+ in 24.x, or 26+ is required. Python 3 only serves the preview. Agent/model access and optional native engines are separate. Platform 1.0.0 identifies this distribution snapshot.

Read the installation guideReview third-party notices

More skills to explore

View all skills
FreeFree package