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/jacksontai2007/cc-unlock/win-reversenpx skills add JacksonTai2007/cc-unlock --skill win-reversegit clone --depth 1 https://github.com/JacksonTai2007/cc-unlockWrote 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/jacksontai2007/cc-unlock/win-reverse)<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>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 | $0.00492 | $0.08153 |
| Opus 5 | $0.00246 | $0.04077 |
| Sonnet 5 | $0.00098 | $0.01631 |
| Haiku 4.5 | $0.00049 | $0.00815 |
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.
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。 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/xxx、state/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:- 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”。 - 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。 - 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。
- SHA256哈希物理核对:必须在终端计算当前受损文件与
- 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。
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.
- agents/openai.yaml 982 B
- artifacts/tasks/_TEMPLATE/core/core-task.json 2.1 KB
- artifacts/tasks/_TEMPLATE/core/env/entry.js 123 B runs code
- artifacts/tasks/_TEMPLATE/core/report.md 1.3 KB
- artifacts/tasks/_TEMPLATE/core/run/closeout.mjs 919 B runs code
- artifacts/tasks/_TEMPLATE/core/run/fixtures.json 130 B
- artifacts/tasks/_TEMPLATE/core/run/local-repro-example.js 123 B runs code
- artifacts/tasks/_TEMPLATE/core/run/protocol-replay-example.js 133 B runs code
- artifacts/tasks/_TEMPLATE/core/run/run-local.mjs 177 B runs code
- artifacts/tasks/_TEMPLATE/core/run/validate-fixture.mjs 202 B runs code
- artifacts/tasks/_TEMPLATE/core/run/verify-once.mjs 1.6 KB runs code
- artifacts/tasks/_TEMPLATE/core/state/clues.md 354 B
- artifacts/tasks/_TEMPLATE/core/state/progress.md 877 B
- artifacts/tasks/_TEMPLATE/core/state/route-plan.md 4.0 KB
- artifacts/tasks/_TEMPLATE/core/state/route-state.json 2.7 KB
- artifacts/tasks/_TEMPLATE/core/task.json 2.1 KB
- artifacts/tasks/_TEMPLATE/extensions/anti-analysis.json 295 B
- artifacts/tasks/_TEMPLATE/extensions/config-recovery.json 284 B
- artifacts/tasks/_TEMPLATE/extensions/dotnet.json 242 B
- artifacts/tasks/_TEMPLATE/extensions/driver.json 251 B
- artifacts/tasks/_TEMPLATE/extensions/exception-runtime.json 276 B
- artifacts/tasks/_TEMPLATE/extensions/frida-hooking.json 247 B
- artifacts/tasks/_TEMPLATE/extensions/ipc-persistence.json 325 B
- artifacts/tasks/_TEMPLATE/extensions/loader-injection.json 373 B
- artifacts/tasks/_TEMPLATE/extensions/memory-forensics.json 268 B
- artifacts/tasks/_TEMPLATE/extensions/mixed-mode-interop.json 364 B
- artifacts/tasks/_TEMPLATE/extensions/packer-unpack.json 243 B
- artifacts/tasks/_TEMPLATE/extensions/protection-bypass.json 344 B
- artifacts/tasks/_TEMPLATE/extensions/static-triage.json 247 B
- artifacts/tasks/_TEMPLATE/extensions/tls-network.json 282 B
- artifacts/tasks/_TEMPLATE/extensions/ui-runtime.json 239 B
- artifacts/tasks/_TEMPLATE/extensions/web-shell-triage.json 448 B
- artifacts/tasks/_TEMPLATE/run/anti-analysis-bypass-report.md 189 B
- artifacts/tasks/_TEMPLATE/run/anti-analysis-hook.js 112 B runs code
- artifacts/tasks/_TEMPLATE/run/anti-analysis-notes.md 90 B
- artifacts/tasks/_TEMPLATE/run/blob-decode-notes.md 99 B
- artifacts/tasks/_TEMPLATE/run/bridge-map.md 80 B
- artifacts/tasks/_TEMPLATE/run/config-recovery-notes.md 165 B
- artifacts/tasks/_TEMPLATE/run/config-schema.md 90 B
- artifacts/tasks/_TEMPLATE/run/dotnet-notes.md 122 B
- artifacts/tasks/_TEMPLATE/run/driver-dispatch-map.md 92 B
- artifacts/tasks/_TEMPLATE/run/dump-plan.md 60 B
- artifacts/tasks/_TEMPLATE/run/exception-runtime-notes.md 99 B
- artifacts/tasks/_TEMPLATE/run/frida-hook-template.js 100 B runs code
- artifacts/tasks/_TEMPLATE/run/hook-events.jsonl 0 B
- artifacts/tasks/_TEMPLATE/run/iat-rebuild-notes.md 97 B
- artifacts/tasks/_TEMPLATE/run/il-patch-notes.md 88 B
- artifacts/tasks/_TEMPLATE/run/import-surface.md 80 B
- artifacts/tasks/_TEMPLATE/run/interop-bridge-report.md 157 B
- artifacts/tasks/_TEMPLATE/run/interop-hook-template.js 25 B runs code
- artifacts/tasks/_TEMPLATE/run/ipc-persistence-notes.md 96 B
- artifacts/tasks/_TEMPLATE/run/ipc-surface.md 101 B
- artifacts/tasks/_TEMPLATE/run/kernel-ioctl-map.md 100 B
- artifacts/tasks/_TEMPLATE/run/loader-hook-template.js 89 B runs code
- artifacts/tasks/_TEMPLATE/run/loader-injection-notes.md 151 B
- artifacts/tasks/_TEMPLATE/run/loader-technique-report.md 121 B
- artifacts/tasks/_TEMPLATE/run/memory-layout.md 102 B
- artifacts/tasks/_TEMPLATE/run/message-flow.md 98 B
- artifacts/tasks/_TEMPLATE/run/mixed-mode-notes.md 104 B
- artifacts/tasks/_TEMPLATE/run/persistence-map.md 110 B
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.
- 5d ago First seen · 544 lines · 492 tokens per session scan A f85da2c00ce3
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…