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 skills add vichhka-git/renef-skills --skill renefgit clone --depth 1 https://github.com/vichhka-git/renef-skillsWrote 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/skills/vichhka-git/renef-skills/renef)<a href="https://agentmods.dev/skills/vichhka-git/renef-skills/renef"><img src="https://agentmods.dev/badge/skills/vichhka-git/renef-skills/renef/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vichhka-git/renef-skills/renef"><img src="https://agentmods.dev/badge/skills/vichhka-git/renef-skills/renef.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00167 | $0.03778 |
| Opus 5 | $0.00084 | $0.01889 |
| Sonnet 5 | $0.00033 | $0.00756 |
| Haiku 4.5 | $0.00017 | $0.00378 |
Grade A, and why
renef 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 9d 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Renef
You are driving renef — a dynamic instrumentation engine for Android ARM64. Your job is to emit renef Lua/CLI that runs correctly the first time. If you've written Frida hooks, GameGuardian cheats, or game-hacking Lua, the concepts already transfer — you only need renef's syntax and workflow, which this skill makes exact. Do not guess API names; use the Syntax Contract below as ground truth, and run the Self-Lint before presenting any script.
For authorized security testing, app-hardening review, CTFs, and reverse-engineering of software you own or are permitted to analyze.
Start here for any real target: run probe.lua (bundled with this skill) to ground-truth the
actual API/behavior of this renef build, then follow the investigation loop in
references/methodology.md. Attempt and measure on-device — don't pre-decide what's possible —
and report status honestly: not attempted → installed but unverified → verified working. The
human drives the device/app/proxy and decides the goal; you do the enumeration, scripting,
error-parsing, and verification. Recipes below are worked examples of the loop, not a menu to
copy blindly (offsets/signatures are target-specific).
What you're driving
- Topology — read this before anything.
renefis a host client (your macOS/Linux shell) that drivesrenef_serverrunning on the Android device over an ADB-forwarded socket. You do not runrenefon the device, and you do notadb push hook.lua+adb shell renef …. That on-device pattern is only--localmode (Termux/SSH on a rooted phone). Default and assumed-here = host client → remote device. Lua scripts stay on the host and are sent over the wire by-l; device-side paths apply only under--local. - Your Lua runs inside the target process (injected
libagent.so, embedded Lua 5.4, memfd injection, no ptrace).Module.*,Memory.*, hook callbacks all execute in the app's address space — paths, PIDs, fds are the target's. - You drive it from the CLI REPL (
renef>) or one-shot via-l script.lua. - Hook/trace output is asynchronous — you must
watch(or launch with-w) or you see nothing.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 223 lines · 167 tokens per session scan A 1163a1de7157
renef is a skill published in the GitHub repository vichhka-git/renef-skills (15 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 167 tokens to every session and 3,778 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.