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 dslsdzc/rev-skills --skill re-analyzegit clone --depth 1 https://github.com/dslsdzc/rev-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/dslsdzc/rev-skills/re-analyze)<a href="https://agentmods.dev/skills/dslsdzc/rev-skills/re-analyze"><img src="https://agentmods.dev/badge/skills/dslsdzc/rev-skills/re-analyze/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/dslsdzc/rev-skills/re-analyze"><img src="https://agentmods.dev/badge/skills/dslsdzc/rev-skills/re-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00114 | $0.02717 |
| Opus 5 | $0.00057 | $0.01358 |
| Sonnet 5 | $0.00023 | $0.00543 |
| Haiku 4.5 | $0.00011 | $0.00272 |
Grade A, and why
re-analyze 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 10d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
逆向分析入口
第〇步：输入类型判定与环境探测
输入类型 → probe 判定：
| 输入类型 | probe |
|---|---|
| 文件/样本（可执行、固件、压缩包、文档、APK 等） | 必须 |
| 二进制/固件分析请求（目标在磁盘上） | 必须 |
| 代码片段（用户直接粘贴的 C/汇编/伪代码） | 跳过 |
| 反编译截图/反汇编文本（无文件可分析） | 跳过 |
| 协议描述/逻辑问答（无二进制目标） | 跳过 |
- probe 必须时：运行
references/probe.sh（或本机手动执行等价命令），记录：RE_OS/RE_ARCH/RE_CORES/RE_MEM_GB（探测失败→询问用户）RE_TOOLS：HAVE 列表（已装，优先使用）与 MISS 列表（未装，不中断流程，用到的技能会引导安装）- 参考 [[platform-tips]] 中本平台分支的经验
- probe 跳过时：无 OS/ARCH/MEM 需求——
RE_OS/RE_ARCH/RE_CORES/RE_MEM_GB/RE_TOOLS置unknown，后续步骤/技能用到时按需询问，不阻塞入口
第一步：偏好询问（分级）
按 references/preferences.md 分级规则处理（不默认逐项询问）：
- Level 0 快速入口（默认）：目标为初步分析或未明确 → 直接采用默认值（目标=初步分析、Ghidra、standard、报告要、平台 auto），进入第二步
- Level 1 深度任务：目标明确属于深度任务（脱壳 / 漏洞 / 协议逆向 / 恶意深度分析 / 破解 / 取证等）或用户主动要求 → 完整询问 5 项：
- 分析目标（必答，第一项）——不明确就追问
- 反编译器：Ghidra(默认) / IDA / radare2
- 深度：快速结论 / 标准分析 / 深度报告
- 报告：要 / 不要
- 平台确认：自动 / 手动
结果存入会话变量（RE_GOAL、RE_DECOMPILER、RE_DEPTH、RE_REPORT、RE_TARGET_PLATFORM），本次分析全程有效，被调用技能读取。
安全底线：目标涉及运行样本 → 提醒默认沙箱原则（见 [[platform-tips]] 最高原则）。
第二步：任务识别
按 references/triage.md 决策表，把 RE_GOAL + 输入文件映射到一条编排路径。复合目标按依赖顺序串联多个大类。
先判授权上下文：按 triage 第 0 步判定 RE_AUTH（owned / ctf / research / unknown）——补丁/绕过/动态执行等敏感路径受其约束（与 [[re-cracking]] 授权边界一致）。
第三步：路由引擎（状态机）
技能不是调用链，是状态转移：每个技能执行后产出新证据，证据驱动下一跳。
triage → route → skill execution → evidence → route（循环）
调用对应大类网关技能（[[re-binary-core]] [[re-malware]] [[re-firmware]] [[re-protocol]] [[re-mobile]] [[re-anti-analysis]] [[re-cracking]] [[re-vuln]] [[re-ctf]] [[re-managed]] [[re-forensics]]），网关内部自行选择原子技能。
Route State（循环防护）：
visited：已进入技能列表（会话变量RE_VISITED）max revisit：1- 规则：同技能第二次进入必须携带新证据（相对上次进入时的证据增量——新字符串/新行为/新结构特征）；无新证据禁止重入，回到当前技能的备选分支或按 [[rerouting]] B 表收束（防 binary-core ↔ crypto ↔ anti-analysis 类循环）
双轨再路由（强制，见 [[rerouting]]）：
- 轨 1（网关完成必查）：每网关完成后，对照 [[rerouting]] 的 A/B 表检查新证据；命中 → 调用对应技能，完成后回到轨 1 继续
- 轨 2（证据出现即查）：分析中每产出新证据类型（字符串内容如密钥/C2/壳名、节表、行为、加密特征），立即对照 A 表；命中 → 调用技能
- 未命中任何表项 → 按 B 表约束行动（换思路/回退/交付部分结论），禁止自行硬琢磨
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.
- 10d ago First seen · 111 lines · 114 tokens per session scan A 8b691c234b33
re-analyze is a skill published in the GitHub repository dslsdzc/rev-skills (52 stars, last pushed 11d ago), licensed Apache-2.0. It adds 114 tokens to every session and 2,717 once invoked, about $0.0006 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
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
deobfuscating-powershell-obfuscated-malware
Systematically deobfuscates multi-layer PowerShell malware using AST analysis, dynamic tracing, and tools like PSDecode and PowerDecode to reveal hidden payloads and C2 infrastructure. Use during incident response or malware analysis when a PowerShell script is obfuscated with encoding, string manipulation, or…
conducting-malware-incident-response
Respond to malware infections across enterprise endpoints by identifying the malware family, determining infection vectors, assessing spread, and executing containment, analysis, eradication, and recovery procedures aligned to MITRE ATT&CK. Use when responding to a confirmed or suspected malware infection, including…
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…
analyzing-network-covert-channels-in-malware
Detect and analyze covert communication channels used by malware, including DNS tunneling, ICMP exfiltration, steganographic HTTP, and other protocol abuse used for C2 and data exfiltration. Use when investigating suspicious DNS/ICMP/HTTP traffic patterns, hunting for hidden C2 channels in network captures, or…
analyzing-golang-malware-with-ghidra
Reverse engineer Go-compiled malware using Ghidra with specialized scripts for function recovery, string extraction, and type reconstruction in stripped Go binaries.