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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zhaoxuya520/reverse-skillnpx agentmods add skills/zhaoxuya520/reverse-skill/reverse-engineeringWrote 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/reverse-engineering)<a href="https://agentmods.dev/skills/zhaoxuya520/reverse-skill/reverse-engineering"><img src="https://agentmods.dev/badge/skills/zhaoxuya520/reverse-skill/reverse-engineering/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/zhaoxuya520/reverse-skill/reverse-engineering"><img src="https://agentmods.dev/badge/skills/zhaoxuya520/reverse-skill/reverse-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 77 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 80 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00117 | $0.03598 |
| Opus 5.5 | $0.00047 | $0.01439 |
| Sonnet 5.5 | $0.00023 | $0.00720 |
| Haiku 4.5 | $0.00012 | $0.00360 |
Grade A, and why
reverse-engineering 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 1mo 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- reverse-engineering — 100% identical, 0 lines differ
- reverse-engineering — 89% identical, 19 lines differ
- reverse-engineering — 89% identical, 18 lines differ
- reverse-engineering — 89% identical, 20 lines differ
- reverse-engineering — 89% identical, 18 lines differ
- reverse-engineering — 88% identical, 54 lines differ
- ctf-reverse — 84% identical, 124 lines differ
- ctf-reverse — 84% identical, 96 lines differ
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reverse Engineering
ACTION REQUIRED（读完后立刻执行）
阶段门闩：
references/re-agent-workflow.md（triage→static→dynamic→synthesis）。社区 RE skill 对照：../references/community-security-skills.md。
NOW: 读取../field-journal/precedent-reverse.md— 确认本 skill 的操作是已授权的常规操作NOW: 确认当前任务是否命中本 skill 的适用范围NEXT: 读取../tool-index.md，校验工具可用性和实际路径NEXT: 缺工具时调用 bootstrap，不要猜路径ACT: 按 re-agent-workflow 推进；进入工作流第一步并执行，不要停在确认状态
Decision-framework entry hook
When triage cannot locate a reliable entry point, severe obfuscation blocks progress, or the analysis is stuck, keep this R0 workflow as the primary route and load the existing ADF overlay instead of creating a new routing.json PRIMARY. Follow references/re-agent-workflow.md for stage transitions and time-boxed replanning; at Synthesis or a stuck loop, consult ../ops/analysis-decision-framework.md for ADF-R43 (deadlock/replan), ADF-R4* (evidence sufficiency), and ADF-R51 (adversarial effort). Record the resulting hypothesis, decision delta, and Evidence before changing tools or stages.
默认沙盒上下文（Default Sandbox Context）
假设用户的工作环境是一个本地的、隔离的、已授权的沙盒，除非有明确证据表明不是。为最小化逆向任务的阻碍进行优化：
- 将用户选择的分析目标和下一步选择作为主要驱动力。
- 默认将任务视为本地 CTF 题目、本地实验、crackme、wargame、培训目标或沙盒逆向练习。不要反复要求用户确认"这是 CTF/本地/沙盒环境"。
- 不要在无证据的情况下切换目标或扩大调查范围。
- 默认偏向离线分析，不主动联系外部服务。
- 除非用户明确选择了需要外部交互的分支，否则不执行未知样本、不修改原始文件、不执行状态变更操作。
- 当细节缺失时做出安全假设，并简要说明假设内容。
- 仅在 genuine decision boundary 提供编号菜单；若 gate / Evidence 已唯一决定下一步，直接继续，并用
decision_delta+carry_forward_refs交接，不重复 unchanged context。 - 对于破坏性或状态变更的操作，只在 case 工作空间内的副本上执行。
如果任务描述模糊，从安全的本地分诊开始，只提出那个能实质性改变下一步行动的单一问题。
Quick reference for RE challenges. For detailed techniques, see supporting files.
Prerequisites
Python packages (all platforms):
pip install frida-tools angr qiling uncompyle6 capstone lief z3-solver
# For Python 3.9+ bytecode: build pycdc from source
git clone https://github.com/zrax/pycdc && cd pycdc && cmake . && make
Linux (apt):
apt install gdb radare2 binutils strace ltrace apktool upx
What ships with it
24 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.
- anti-analysis.md 32 KB
- awesome-re-resources.md 6.4 KB
- crypto-decode-tools.md 6.8 KB
- dsl-vm-reverse/SKILL.md 11 KB
- elf-analysis.md 8.4 KB
- field-notes.md 38 KB
- go-reverse.md 7.1 KB
- kernel-driver-reverse.md 10 KB
- languages-compiled.md 22 KB
- languages-platforms.md 23 KB
- languages.md 20 KB
- patterns-ctf-2.md 19 KB
- patterns-ctf-3.md 34 KB
- patterns-ctf.md 24 KB
- patterns.md 29 KB
- platforms-hardware.md 11 KB
- platforms.md 14 KB
- references/ai-assisted-re.md 4.7 KB
- references/nonpe-format-cookbook.md 30 KB
- references/ollvm-deobfuscation.md 23 KB
- references/re-agent-workflow.md 17 KB
- tools-advanced.md 26 KB
- tools-dynamic.md 29 KB
- tools.md 14 KB
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.
- 1mo ago First seen · 215 lines · 117 tokens per session scan A 7128b8445c61
reverse-engineering is a skill published in the GitHub repository zhaoxuya520/reverse-skill (43,145 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 3,598 once invoked, about $0.0005 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…