Reverse Skill is a routing package for AI coding agents that selects appropriate reverse-engineering, penetration-testing, and security-research methods and tools for a given target. It is used for tasks involving APKs, binaries, frontend JavaScript, packet captures, CTF challenges, and authorized penetration testing. Its catalogue add-ons provide the skills and instructions that guide these workflows.
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 zhaoxuya520/reverse-skill --skill binary-ninja-reversegit clone --depth 1 https://github.com/zhaoxuya520/reverse-skillWrote 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/zhaoxuya520/reverse-skill/binary-ninja-reverse)<a href="https://agentmods.dev/skills/zhaoxuya520/reverse-skill/binary-ninja-reverse"><img src="https://agentmods.dev/badge/skills/zhaoxuya520/reverse-skill/binary-ninja-reverse.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00766 |
| Opus 5 | $0.00028 | $0.00383 |
| Sonnet 5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
binary-ninja-reverse 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 3d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Binary Ninja reverse engineering
Use Binary Ninja when the user explicitly selects it, when its ILs materially help data-flow analysis, or when IDA/Ghidra/radare2 results need an independent cross-check.
Start safely
- Confirm the repository case scope is ready before acting on a target.
- Check
skills/tool-index.mdforbinaryninja; Binary Ninja is commercial software and must be installed manually with a valid Vector 35 license. - Work on a copy when applying patches or saving database changes.
- Record imports/exports, entry points, architecture, and file hash before promoting findings.
Choose the integration
- GUI or Python API: preferred when Binary Ninja is already open or the user wants direct interactive analysis.
- Community MCP bridge: use only when explicitly requested and after reviewing the third-party plugin boundary. Keep the Binary Ninja HTTP listener on
127.0.0.1:9009; do not enable network exposure by default. - Fallback: use
ghidra-reverse,ida-reverse, orradare2when Binary Ninja is unavailable or its license/API cannot open the target.
The reviewed community integration is fosdickio/binary_ninja_mcp, GPL-3.0, plugin metadata version 1.1.0, minimum Binary Ninja build 4000. The repository is not an official Vector 35 component. This skill was checked against commit 8c5134ee46e2bf44f9a4d846bd971c3e39b3e306 on 2026-09-03.
Install the Binary Ninja side through its Plugin Manager or from the reviewed source. For the MCP stdio bridge, pin the published bridge version rather than using an unbounded package:
npx -y [email protected] --host 127.0.0.1 --port 9009
Register that command only in the MCP client the user selected. The bridge is not ready until Binary Ninja is running, a binary is open, and the localhost plugin endpoint responds.
Analysis workflow
- Enumerate open binaries and select the intended view.
- Capture binary status, entry points, segments, imports, exports, and representative strings.
- Follow call sites and cross-references before interpreting a function in isolation.
- Use HLIL for readable logic, MLIL SSA for data flow, and LLIL/disassembly when lifting loses instruction-level behavior.
- Apply names, comments, and types incrementally; keep the original addresses in evidence.
- Treat byte patches, prototype changes, and saved-file writes as mutations. Perform them only when requested and preserve the original artifact.
- Cross-check high-impact conclusions with a second evidence source or another disassembler.
What ships with it
1 file 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.
- 3d ago First seen · 48 lines · 55 tokens per session scan A 257823a0e25b
binary-ninja-reverse is a skill published in the GitHub repository zhaoxuya520/reverse-skill (34,719 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 766 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.