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 lwjjike/xbsReverseSkill --skill web-reverse-algorithmgit clone --depth 1 https://github.com/lwjjike/xbsReverseSkillWrote 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/lwjjike/xbsreverseskill/web-reverse-algorithm)<a href="https://agentmods.dev/skills/lwjjike/xbsreverseskill/web-reverse-algorithm"><img src="https://agentmods.dev/badge/skills/lwjjike/xbsreverseskill/web-reverse-algorithm/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/lwjjike/xbsreverseskill/web-reverse-algorithm"><img src="https://agentmods.dev/badge/skills/lwjjike/xbsreverseskill/web-reverse-algorithm.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 | $0.00226 | $0.02238 |
| Opus 5.5 | $0.00090 | $0.00895 |
| Sonnet 5.5 | $0.00045 | $0.00448 |
| Haiku 4.5 | $0.00023 | $0.00224 |
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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- web-reverse-algorithm — 100% identical, 0 lines differ
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
- 先找最终写出点，不先读混淆大文件。
- 先存中间值，不先猜算法名。
- 先缩小执行范围，再补环境。
- 先证明输入输出边界，再决定是否整体迁移。
- 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/sm4token&t&appKey&dataparams + encSecKeydocument.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.instantiateapplication/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：
- 初始化 / challenge 线
- 图像或题面识别线
- 参数 builder 线
- 环境 / 指纹 / collect 线
- 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：
fetchXMLHttpRequest.sendsetRequestHeaderdocument.cookieJSON.stringify- verify 提交点
- WebSocket 首包或验证包发送点
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.
- agents/openai.yaml 302 B
- references/01-decision-tree.md 3.9 KB
- references/02-algorithm-families.md 3.9 KB
- references/03-captcha-families.md 2.8 KB
- references/04-debug-env-playbook.md 2.9 KB
- references/05-training-routes.md 2.4 KB
- references/06-engineering-maintenance.md 2.3 KB
- references/captcha-patterns.md 2.8 KB
- references/debug-env-checkpoints.md 2.5 KB
- references/purecalc-patterns.md 2.6 KB
- references/route-map.md 3.9 KB
- scripts/__pycache__/new_case_scaffold.cpython-312.pyc 12 KB
- scripts/new_case_scaffold.py 11 KB runs code
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.
- 1mo ago First seen · 218 lines · 226 tokens per session scan A 366e236853bc
web-reverse-algorithm is a skill published in the GitHub repository lwjjike/xbsReverseSkill (379 stars, last pushed 3mo ago), licensed MIT. It adds 226 tokens to every session and 2,238 once invoked, about $0.0009 per session on Opus 5.5. 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.