win-reverse

win-reverse is a skill for Claude Code, Codex from JacksonTai2007/cc-unlock. It costs 492 tokens per session (8,153 once invoked), scanned A, original, MIT.

A structured workflow for investigating Windows programs and libraries, including EXE, DLL, driver, and .NET files. It covers static and runtime analysis, memory evidence, program protection, and communication between processes.

In plain words
What is it for?
Use it to examine how Windows software starts, loads code, communicates, stores configuration, handles errors, or behaves in memory.
Why use it?
It keeps reverse-engineering work organized and records evidence, reducing skipped analysis and unsupported claims.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/jacksontai2007/cc-unlock/win-reverse
Any agent
npx skills add JacksonTai2007/cc-unlock --skill win-reverse
Clone the repo
git clone --depth 1 https://github.com/JacksonTai2007/cc-unlock

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for win-reverse

README.md
[![agentmods](https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/win-reverse.svg)](https://agentmods.dev/skills/jacksontai2007/cc-unlock/win-reverse)
Your own site
<a href="https://agentmods.dev/skills/jacksontai2007/cc-unlock/win-reverse"><img src="https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/win-reverse.svg" alt="Measured on agentmods" height="20"></a>
Per session 492 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,153 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00492 $0.08153
Opus 5 $0.00246 $0.04077
Sonnet 5 $0.00098 $0.01631
Haiku 4.5 $0.00049 $0.00815

Measured 5d ago against content hash f85da2c00ce3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

win-reverse scanned grade A with 1 finding 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 5d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (artifacts/tasks/_TEMPLATE/core/env/entry.js, artifacts/tasks/_TEMPLATE/core/run/closeout.mjs, artifacts/tasks/_TEMPLATE/core/run/local-repro-example.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

`pure-algorithm` 禁止包含:`child_process.exec/spawn`、注册表操作、目标安装路径写入、二进制 patch。
cc-unlock-files/skill-bundle/win-reverse/SKILL.md · 544 lines

How it starts

The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Windows Reverse Framework

任务脚本与路径约定

当 Skill 工具被调用时,系统返回 skill 的 base directory(如 C:\Users\xxx\.claude\skills\win-reverse)。以下用 <SKILL_BASE> 代指该路径。

任务产物始终创建在当前项目目录,禁止在 skill 全局目录创建任务产物。

node <SKILL_BASE>/tools/task/task-start.mjs <task-id>
node <SKILL_BASE>/tools/task/task-init.mjs <task-id> [--topic=... --topics=...]
node <SKILL_BASE>/tools/task/task-sync.mjs <task-id>
node <SKILL_BASE>/tools/task/task-advance.mjs <task-id>
node <SKILL_BASE>/tools/task/task-close.mjs <task-id>

文档读取使用绝对路径:<SKILL_BASE>/docs/reference/reverse-bootstrap.md 等。

⚠️ 路径规则(硬约束)

本文档中所有 run/xxxstate/xxx 简写路径,均表示相对于 <PROJECT_DIR>/artifacts/tasks/<task-id>/ 的路径,而不是相对于项目根目录(cwd)。

  • 正确:将 investigation.md 写入 <PROJECT_DIR>/artifacts/tasks/<task-id>/run/investigation.md
  • 错误:将 investigation.md 写入 <PROJECT_DIR>/run/investigation.md(cwd 下的 run/ 目录)

每次写入产物文件前,必须确认路径以 artifacts/tasks/<task-id>/ 为根。task-init 脚本已创建了完整目录骨架,所有后续文件操作都必须在该目录内进行。


反捷径系统(Anti-Shortcut System)

本 SKILL 最核心的部分。解决的问题:LLM 在执行逆向任务时,会系统性地跳过复杂分析步骤,选择简单路线反复尝试,然后用容易获取的信号(脚本无报错、文件已修改)谎报进展。

⚠️ 核心硬约束:运行时物理合规检查与硬性诊断闸口协议(物理断路器)

为根治模型在面对失败时通过“语义合理化”进行违规越权或在“最低成本路线”上盲目死循环的通病,本技能工具链已物理集成了API合规审计与硬性退出码拦截。你必须无条件执行以下断路器协议,任何自我辩解或试图绕过的行为都将被系统物理锁死:

1. 闪退与静默失败的“物理断路器”(Crash State Hard Block)

一旦目标程序发生【静默闪退】、【无日志报错退出】或【声称还原备份后依旧崩溃】的现象:

  • 【物理挂起修改权限】:立即挂起并物理锁死一切对项目文件的 Write/Edit 动作。在此状态下,任何尝试直接修改 JS、C#、二进制代码的工具调用均被系统视为越权违规。
  • 【强制启动硬件级三步诊断】:你必须且只能依次执行以下诊断,将客观输出落盘至项目 run/crash_diagnostics.md (字数必须 >= 200 字符),通过只读脚本审计后方可解锁修改权限:
    1. SHA256哈希物理核对:必须在终端计算当前受损文件与 .clean.bak 的哈希值,确保还原 100% 成功,严禁口头声明“已完全恢复”。
    2. 操作系统级事件抓取:必须使用 PowerShell 或命令行抓取系统 Application Error 事件日志,提取明确的 ExceptionCode(如 0xc0000005 段错误)与崩溃模块。
    3. 挂载调试器提取堆栈:若本地提供调试工具,必须挂载调试器(或利用调试 MCP 服务)启动程序,捕获 Crash 瞬间的第一手寄存器(EIP/RIP)及堆栈调用流。
  • 未将包含上述硬件特征(如 eip、exception、0x...)的客观证据落盘前,思维中禁止提出任何假说推理。
2. SHA256 哈希一致性硬核交叉校验
  • 系统阶段推进工具(task-advance)和自测脚本在执行时,会自动物理扫描并核对项目所有 .clean.bak 备份文件与其物理原始文件的 SHA256 校验和。
  • 若哈希值不匹配,说明系统现场处于被盲改的受损/脏状态。工具将直接抛出退出码 1 并物理锁死任务推进
  • 【授权豁免】:若修改属于合理且受控的行为,你必须在项目 run/ 目录下物理生成 hash_mismatch_authorized.flag 豁免证书,否则系统绝不予放行。

Read the full file on GitHub · 544 lines

Files

What ships with it

60 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.

Changes

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.

  1. 5d ago First seen · 544 lines · 492 tokens per session scan A f85da2c00ce3

Subscribe to this mod's changes

win-reverse is a skill published in the GitHub repository JacksonTai2007/cc-unlock (137 stars, last pushed today), licensed MIT. It adds 492 tokens to every session and 8,153 once invoked, about $0.0025 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens