agentmods.dev

web-reverse-algorithm

A skill for tracing browser JavaScript computations back from an outgoing request, cookie, header, verification result, or WebSocket message to the code that produced it. It covers ordinary signing and encryption as well as heavily obfuscated code, WebAssembly, proof-of-work, and binary data.

In plain words
What is it for?
Use it to classify a reverse-engineering problem, find the relevant entry point, capture intermediate values, align browser and local results, and turn a confirmed computation into reusable code or a documented workflow.
Why use it?
It helps replace guesswork about an unknown value with a trace of its inputs, intermediate values, and final writer. It also helps decide whether to instrument the code, simplify it, add a small browser environment, or keep execution in a browser.

Skill for Claude CodeCodex

359 +2 1mo ago A scan 226 tokens original MIT
View the source file lwjjike/xbsReverseSkill
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/lwjjike/xbsreverseskill/web-reverse-algorithm
Any agent
npx skills add lwjjike/xbsReverseSkill --skill web-reverse-algorithm
Clone the repo
git clone --depth 1 https://github.com/lwjjike/xbsReverseSkill

Made for: Claude Code, Codex.

Per session 226 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,238 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00226 $0.02238
Opus 5 $0.00113 $0.01119
Sonnet 5 $0.00045 $0.00448
Haiku 4.5 $0.00023 $0.00224

Measured 2d ago against content hash 366e236853bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-reverse-algorithm 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/new_case_scaffold.py), 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

web-reverse-algorithm/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web 逆向纯算

这项技能不是“给一个固定公式”，而是把资料库里的方法层、题型层、训练层、工程化层压成一套总入口。

先把任务压缩成这条闭环，再决定读哪份 references、走哪条路径、写哪种落地代码：

最终请求 / 最终 cookie / 最终 verify / 最终 WS 帧
-> writer
-> builder
-> entry
-> source

核心原则

  1. 先找最终写出点，不先读混淆大文件。
  2. 先存中间值，不先猜算法名。
  3. 先缩小执行范围，再补环境。
  4. 先证明输入输出边界，再决定是否整体迁移。
  5. 先把结果整理成可复用结构，再继续做版本适配。

使用顺序

1. 先判题型

把目标先归到下面之一：

  • 标准签名 / 标准摘要题
  • 混合加密 / 密钥包装题
  • Cookie / Header / 多参数联动题
  • JSVMP / VMP / 强混淆纯算题
  • Wasm / Protobuf / WebSocket / 二进制协议题
  • 验证码 / 风控 / challenge 题

如果还没分清，先读 references/01-decision-tree.md。

2. 再判当前阻塞点

优先判断你卡在下面哪一类：

  • 入口没找对
  • 原始串或原始 payload 没对齐
  • 中间数组 / 中间对象没采到
  • 运行时依赖没补齐
  • 图像线和参数线没拆开
  • 协议边界没证明

遇到这一步拿不准时，优先读 references/04-debug-env-playbook.md。

3. 按题型选路线

标准签名 / 混合加密 / Cookie / Header / 国密

适用信号：

  • 输出长度规整
  • md5/sha1/hmac/aes/rsa/sm3/sm4
  • token&t&appKey&data
  • params + encSecKey
  • document.cookie 或 header 明显可追

优先读取 references/02-algorithm-families.md。

JSVMP / VMP / 小红书 / a_bogus / 多参数复杂纯算

适用信号：

  • 大数组、解释器、for(;;)+switch
  • 位运算密集、状态数组、寄存器式写法
  • window._webmsxyw、__TENCENT_CHAOS_VM、byted_acrawler 一类入口

优先读取 references/02-algorithm-families.md 和 references/04-debug-env-playbook.md。

Wasm / Protobuf / WebSocket / challenge 协议

适用信号：

  • WebAssembly.instantiate
  • application/x-protobuf
  • 二进制响应、导出函数、首包/验证包分段

优先读取 references/02-algorithm-families.md 和 references/03-captcha-families.md。

验证码 / 风控 / challenge / verify

永远先拆 5 条线：

  1. 初始化 / challenge 线
  2. 图像或题面识别线
  3. 参数 builder 线
  4. 环境 / 指纹 / collect 线
  5. 最终 verify 线

优先读取 references/03-captcha-families.md。

统一工作流

1. 锁定最终写出点

优先从这些位置切：

  • fetch
  • XMLHttpRequest.send
  • setRequestHeader
  • document.cookie
  • JSON.stringify
  • verify 提交点
  • WebSocket 首包或验证包发送点

Read the full file on GitHub · 218 lines

Files

What ships with it

13 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. 2d ago First seen · 218 lines · 226 tokens per session scan A 366e236853bc

Subscribe to this mod's changes

web-reverse-algorithm is a skill published in the GitHub repository lwjjike/xbsReverseSkill (359 stars, last pushed 1mo ago), licensed MIT. It adds 226 tokens to every session and 2,238 once invoked, about $0.0011 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.

Debugging
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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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