One 8 KB skill that replaces REA (Reverse Engineer Anything): plain CLI tools, no MCP. Benchmarked: 38% faster, 35% cheaper.
Python
docs: drop target app name and feature details from README
AICodeKing91c75b13ea00
diff --git a/README.md b/README.mdindex d22abe3..cfc2271 100644--- a/README.md+++ b/README.md@@ -21,11 +21,11 @@ Claude Code headless (`claude -p`), Sonnet 5.5, macOS arm64. 4 reverse-engineeri| no skill | 479 s | $2.21 | 81 | 3.11 M | 67/75 (one refusal) || REA (MCP + its skill) | 627 s | $3.36 | 124 | 5.93 M | 75/75 |-Against REA, leanrea had **38% less wall time, 35% lower cost, 56% fewer turns and 60% fewer tokens, at the same accuracy**. Its one partial miss named Notion's older change channel instead of the v2 one (both channels exist).+Against REA, leanrea had **38% less wall time, 35% lower cost, 56% fewer turns and 60% fewer tokens, at the same accuracy**. Its one partial miss named an older IPC channel instead of the v2 one (both channels exist).The tasks:-- **electron**: trace Notion's meeting/mic detection through its app.asar (native function → main-process class → IPC channels).-- **native**: inventory the exports, TCC permission check and single-instance lock of Notion's `mac_utils.node`.+- **electron**: trace a feature through a real Electron app's app.asar (native function → main-process class → IPC channels).+- **native**: inventory the exports, a TCC permission check and the single-instance lock of that app's native addon (`.node`).- **go**: toolchain and dependency versions of a stripped `gh` binary.- **deep**: from disassembly alone, the exact socket path format, wire protocol and peer authentication of that lock.@@ -35,7 +35,7 @@ The same operation run through REA's CLI vs the raw command:|---|---|---|| Go build info | 0.56 s | `go version -m`: 0.06 s || Mach-O overview | 3.32 s | otool + dyld_info + nm: 0.04 s |-| Electron app analysis (Notion) | fails on asar integrity until you pass a flag, then **47.9 s and 140 MB of JSON** | asar extract + `rg -uu`: 4.8 s, 24 KB |+| Electron app analysis (real desktop app) | fails on asar integrity until you pass a flag, then **47.9 s and 140 MB of JSON** | asar extract + `rg -uu`: 4.8 s, 24 KB |Full tables, the context-overhead runs and caveats: [bench/BENCHMARK.md](bench/BENCHMARK.md). Raw per-run metrics: [bench/results/final.jsonl](bench/results/final.jsonl).@@ -96,7 +96,7 @@ Use it:## Reproduce the benchmark-Needs macOS with Notion.app, `gh` from Homebrew, Node, and Claude Code logged in.+Needs macOS with the target Electron app installed (see `bench/setup.sh`), `gh` from Homebrew, Node, and Claude Code logged in.```shcd bench./setup.sh # installs [email protected], copies the targets into bench/work (gitignored)@@ -104,7 +104,7 @@ cd bench./ctx.sh # context-overhead probepython3 mcp_list.py node work/rea-install/node_modules/rea-agents/scripts/rea.mjs --mcp # REA tool count + size```-The answer keys in `tasks.json` match Notion 7.35.1 and a `gh` built with go1.27.1. Other versions need new keys.+The answer keys in `tasks.json` match the app versions used here and a `gh` built with go1.27.1. Other versions need new keys.## Credit