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 agentmods add skills/asaiuta/reverse-workbench-skill/reverse-workbench-skillnpx skills add Asaiuta/reverse-workbench-skill --skill reverse-workbench-skillgit clone --depth 1 https://github.com/Asaiuta/reverse-workbench-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/asaiuta/reverse-workbench-skill/reverse-workbench-skill)<a href="https://agentmods.dev/skills/asaiuta/reverse-workbench-skill/reverse-workbench-skill"><img src="https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/reverse-workbench-skill.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 | $0.00051 | $0.01519 |
| Opus 5 | $0.00026 | $0.00759 |
| Sonnet 5 | $0.00010 | $0.00304 |
| Haiku 4.5 | $0.00005 | $0.00152 |
Grade A, and why
reverse-workbench-skill 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reverse-workbench-skill（跨 Agent 全局入口）
安装根目录：本文件所在目录（标准 Agent Skills 位置 ~/.agents/skills/reverse-workbench-skill，pi / Codex CLI / DSH 共用；Claude Code 用 ~/.claude/skills/）。
立即路由（MUST）
- 读
RULES_zh.md（规则与全局行为；英文环境可读RULES.md）。 - 读
skills/MASTER-ROUTING.md（或运行skills/scripts/master-route.ps1）确定 PRIMARY；需要完整三轴匹配时再读skills/routing_zh.md（或skills/routing.md）。 - 进入对应子目录的
SKILL.md执行；本机工具路径以skills/tool-index.md为准（不存在则先运行索引刷新脚本）。 - 子模块总览见
skills/SKILL.md；扩展包含archive-file-triage/、ghidra-headless/和pentest-tools/observer-ward/。
宿主入口（同一 bundle，多宿主共用）
| 宿主 | 调用方式 |
|---|---|
| pi | /skill:reverse-workbench-skill |
| Codex CLI | /skills 或 $reverse-workbench-skill |
| DSH | web 端 skill 目录 / skill 工具 |
| Claude Code | /skills |
工具索引（Windows，首次或换机后）
以下命令在技能根目录（本文件所在目录）执行：
powershell -ExecutionPolicy Bypass -File ".\skills\scripts\refresh-tool-index.ps1"
人类概览
docs/OVERVIEW_zh.md/README_zh.md
Pi 手动启用时的完整路由规则
逆向技能路由（pi 全局注入 · 精简版）
包根目录：本文件所在目录（Skill bundle 根，任意宿主安装位置） 触发后不要重新走首次配置；直接路由并执行。
触发关键词
- APK、Android 逆向、反编译、smali、jadx、apktool、Frida、Hook
- 二进制分析、IDA、radare2、r2、反汇编、逆向工程、RE、还原源码
- 前端签名、加密参数、JS 逆向、jshookmcp、CDP、SourceMap
- 抓包、HTTP 捕获、请求重放、anything-analyzer
- CTF、Pwn、Web 渗透、漏洞利用、提权
- 重打包、签名、证书校验、root 检测、反调试
- so 分析、native hook、JNI
- 渗透测试、红队、安全评估、蓝队、应急响应
- 端口扫描、Nmap、漏洞扫描、Nuclei、SQL 注入、SQLMap、目录爆破、FFUF、密码破解、Hashcat、Hydra、Metasploit、Impacket
- SRC、Bug Bounty、众测、漏洞赏金、HackerOne、WAF bypass、IDOR、越权
- 内网渗透、横向移动、域渗透、AD 攻击、BloodHound、权限提升、凭证提取
- Prompt 注入、AI 安全、Agent 安全、LLM 攻击、jailbreak、越狱
- EDR 绕过、免杀、AV bypass、direct syscall、unhook
- 固件、firmware、IoT、binwalk、嵌入式漏洞利用
- pwn、栈溢出、ROP、ret2libc、pwntools、GEF
- 写报告、writeup、技术文档、渗透报告、逆向报告
- 浏览器自动化、Playwright、agent-browser、桌面自动化
- N-day、补丁差分、patch diff、CVE 复现、1day
- 符号迁移、bindiff、跨版本、PDB 缺失
- API 安全测试、GraphQL 安全、JWT 攻击、供应链安全
- iOS 逆向、移动安全、MSTG、Objection、SSL Pinning
- YARA、恶意软件分析、IOC、沙箱
- Agent 不干活、AI 懒、跳过步骤、只读不干、Prompt 工程
- AI 反编译、LLM 逆向、神经反编译
- Claude Code、Bun 单二进制、遥测、geo restriction、补丁差分
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 · 113 lines · 51 tokens per session scan A a091200158f0
reverse-workbench-skill is a skill published in the GitHub repository Asaiuta/reverse-workbench-skill (2 stars, last pushed 20d ago), licensed MIT. It adds 51 tokens to every session and 1,519 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 2026-08-31.
Other skills, from other repositories
ctf-web
CTF Web攻击知识库 — PHP弱比较绕过、命令注入空格绕过、eval回显技巧、SSTI注入链、反序列化利用链、PHP代码审计checklist、常见flag位置.
osint-recon
OSINT 开源情报收集知识库 — 四维信息收集模型（服务器→网站→域名→人员），维度四（人员信息）条件触发.
crypto-toolkit
编码解码与加解密工具 — base64/URL/Hex/HTML实体编码解码，MD5/SHA哈希，AES/DES/RSA加解密，JWT解析，Caesar/ROT13密码，栅栏/Vigenere密码，Unicode转义，Morse电码等.
hackerone
HackerOne 赏金项目 scope-guard 流程 — 读取 program scope，强制 scope 与 program rules，再逐个把 in-scope asset 交给 pentest-flow.
redteam-cve-lookup
CVE lookup and applicability assessment domain card. Use after reconnaissance has identified products, versions, services, or fingerprints and red-team mode needs evidence-based CVE matching before deeper testing.
redteam-cve-validation
CVE validation domain card. Use after CVE lookup has produced applicable or candidate CVEs and red-team mode needs scoped evidence to decide whether to continue, pivot, or report.