leanrea
One 8 KB skill that replaces REA (Reverse Engineer Anything): plain CLI tools, no MCP. Benchmarked: 38% faster, 35% cheaper.
The Lens
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
Updated Oct 2026
leanrea is one 8 KB instruction file that teaches your coding agent to reverse engineer shipped software: Electron apps, native binaries, Go builds, APKs, databases and websites. It replaces REA (Reverse Engineer Anything), an MCP server (a plugin that hands the agent extra commands) with 207 tools. leanrea skips the wrapper and tells the agent which real command to run. Free, MIT licensed.
Install is npx skills add aicodeking/leanrea, for Claude Code, Codex, Cursor and others. Nothing to host, but the underlying tools must be on your machine. In the author's 36-run benchmark, leanrea finished 38% faster and 35% cheaper than REA, scoring 74 of 75 against REA's 75. The totals match the raw results file. Solo, small teams and larger teams: free. You pay only for model tokens.
The catch: it's the author's own test, three reps on one Mac, and REA has shipped newer versions since. The README admits the bare model already handles most of this. Nine Router commands break when an agent copies them raw, and the fix is still an open pull request. You're also giving an agent shell access to untrusted binaries, so work on a copy, ideally in a VM.
Free vs Self-Hosted vs Paid
fully freeFree: The whole product is one MIT-licensed SKILL.md (about 8 KB). No account, no paid tier, no telemetry.
Self-hosted: Nothing to run. Install with npx skills add aicodeking/leanrea (Vercel's skills CLI, which asks which agents to install for) or copy the leanrea/ folder into ~/.claude/skills. Agents without skills support can take the file pasted into their rules. It calls the real tools, so install what your target needs: asar, otool, nm, go version -m, jadx, apktool, Ghidra, tshark, binwalk, sqlite3.
Paid: No paid tier. The only cost is your agent's model usage. In the author's benchmark the 12-task leanrea arm cost $2.17 in Sonnet tokens versus $3.36 for REA, and rerunning the full 36-run benchmark costs about $8 on Sonnet.
Free and MIT. The only bill is your agent's model usage, which the author's benchmark put about a third below REA for the same four tasks.
What to do by team size
- Solo
- free; one npx command, you pay only for model tokens
- Small team
- free; install per developer with the skills CLI
- Medium team
- free; standardize it in a shared skills folder and run agents on copies of targets
- Large team
- free, but have security review the shell permissions before agents touch untrusted binaries
Get tools like this every Wednesday
One featured tool, three on the radar. No fluff.
A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores
Trust Signals
About
- Owner
- AICodeKing (User)
- Stars
- 4,034
- Forks
- 614
Also by AICodeKing
Explore Further
More tools in the directory
rea
Reverse engineer anything with agents, from app behavior down to native binaries.
435.8k ★openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
394.0k ★everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
298.1k ★