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/guccig4366/xbsreverseskill/web-reverse-envnpx skills add guccig4366/xbsReverseSkill --skill web-reverse-envgit clone --depth 1 https://github.com/guccig4366/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/guccig4366/xbsreverseskill/web-reverse-env)<a href="https://agentmods.dev/skills/guccig4366/xbsreverseskill/web-reverse-env"><img src="https://agentmods.dev/badge/skills/guccig4366/xbsreverseskill/web-reverse-env.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 | $0.00121 | $0.02149 |
| Opus 5 | $0.00060 | $0.01074 |
| Sonnet 5 | $0.00024 | $0.00430 |
| Haiku 4.5 | $0.00012 | $0.00215 |
Grade A, and why
web-reverse-env 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 4d 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.
This is a copy
100% identical to web-reverse-env — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web逆向补环境
概览
使用这个技能时，不要把“补环境”理解成给 window/document/navigator 随便补几个值。
先把任务视为四类问题之一：
- 缺对象或缺属性，代码直接报
undefined - 对象存在，但原型链、描述符、getter/setter、
toString暴露 - 基础对象能跑，但被指纹、栈、异步对象、通信对象继续检测
- 补环境成本过高，应切换到浏览器内执行或
JsRpc/WebSocket替代路线
默认优先走“诊断驱动”的补环境路线，而不是一次性补全浏览器。
快速分流
根据任务特点，优先读取对应参考文档：
- 用户要先理解整体流程或不知道从哪里下手：读 01-workflow.md
- 用户要模块化设计、生成补丁或定义模块边界：读 02-module-contracts.md
- 用户卡在
document.all、nativetoString、堆栈、反检测、WebRTC/AudioContext/Worker：读 03-special-cases.md - 用户想知道当前草稿还缺什么：读 04-missing-points.md
- 用户要继续扩展外部阅读池或找更多非大站来源：读 05-diversified-reading.md
- 用户要做回归验证、模块验收或判断补丁是否够稳：读 06-validation.md
- 用户要了解现有 GitHub 框架、来源映射和代码级模式：读 07-source-map.md
标准工作流
1. 先判断目标路线
优先判断当前任务属于哪一类：
- 只需要最小补丁让样本跑通
- 需要做成可复用模块
- 需要沉淀为 skill / 框架
- 需要高强度检测点补齐
- 需要切换到浏览器内执行或
JsRpc
如果是最后一种，不要硬补到底。
2. 先采集，再诊断
如果用户还没有真实浏览器样本：
- 优先使用 collect-browser-env.js
- 采集
navigator、document、location、history、screen - 采集
cookie、localStorage、sessionStorage - 采集基础
canvas/webgl指纹
如果用户已经有运行日志或报错：
- 优先使用 observe-runtime.js
- 让缺失路径、描述符探测、原型链探测、调用错误先浮出来
不要在没有诊断信息的前提下大面积硬补对象。
3. 按模块补，而不是按页面乱补
补环境时，优先按模块推进：
prototype-builderdescriptor-guardnative-protector- 浏览器对象模块
performance-modulecrypto-modulefingerprint-moduleaudio-fingerprint-modulewebrtc-moduleworker-moduleproxy-observermath-precision-modulestack-clean-moduledocument-all-module
如果站点一开始就死在 document.all，把特殊对象优先级前置。
4. 先补“能继续执行”的缺口
补丁优先级默认如下：
undefined或缺对象导致主流程中断- getter / setter / 方法的
Illegal invocation - 原型链和描述符不一致
- native
toString暴露 - 指纹异常
- 异步对象、通信对象、高强度检测点
5. 把高强度检测点单独看
遇到下面这些对象时，不要按“普通 BOM/DOM 补值”处理：
What ships with it
35 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 262 B
- assets/crypto-sample.example.json 417 B
- assets/document-sample.example.json 965 B
- assets/fingerprint-seed.example.json 1.1 KB
- assets/navigator-sample.example.json 375 B
- assets/performance-sample.example.json 898 B
- assets/plugin-graph.example.json 511 B
- assets/storage-state.example.json 221 B
- assets/webrtc-sample.example.json 584 B
- assets/worker-sample.example.json 424 B
- references/01-workflow.md 20 KB
- references/02-module-contracts.md 7.5 KB
- references/03-github-code-level-notes.md 22 KB
- references/03-special-cases.md 1.8 KB
- references/04-missing-points.md 7.0 KB
- references/05-diversified-reading.md 6.9 KB
- references/06-validation.md 880 B
- references/07-source-map.md 964 B
- references/reading-round2.md 6.8 KB
- references/reading-round3.md 5.1 KB
- scripts/analyze-gap-log.js 5.2 KB runs code
- scripts/build-crypto-module.js 5.6 KB runs code
- scripts/build-document-module.js 12 KB runs code
- scripts/build-fingerprint-module.js 7.6 KB runs code
- scripts/build-navigator-module.js 8.8 KB runs code
- scripts/build-performance-module.js 5.9 KB runs code
- scripts/build-plugin-graph.js 1.1 KB runs code
- scripts/build-storage-module.js 5.3 KB runs code
- scripts/build-webrtc-module.js 7.7 KB runs code
- scripts/build-worker-module.js 6.7 KB runs code
- scripts/collect-browser-env.js 5.4 KB runs code
- scripts/merge-storage-state.js 726 B runs code
- scripts/observe-runtime.js 4.3 KB runs code
- scripts/protect-native.js 2.3 KB runs code
- scripts/scaffold-module.js 203 B 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.
- 4d ago First seen · 214 lines · 121 tokens per session scan A 811eec62eacf
web-reverse-env is a skill published in the GitHub repository guccig4366/xbsReverseSkill (5 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 2,149 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to web-reverse-env, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
wiki-knowledge-agent
Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base. When a user pastes a link or text (in ANY channel — Discord, Slack, CLI, etc.), fetch+verify it, classify it (useful vs ad), translate+summarize it into the target language, save it to the wiki, and optionally alert on…
geo-effect-kit-release
Use when preparing, versioning, tagging, publishing, or verifying npm releases for the cesiumDesign geo-effect-kit workspace, including @ztgkzhaohao/geo-effect-kit and @ztgkzhaohao/geo-effect-kit-mcp.
ai-ppt-powerpoint-generator
AI PPT PowerPoint Presentation Generator Skills to Generate Multi-Page Image Carousels from Templates of AI PPT PowerPoint, Sota Models Nano Banana, Nano Banana-2 ,Imagen-2 and more are available.
Calcul de chemin d'escalade 3D sur mesh
Génère un algorithme en C# pour Unity permettant de calculer un chemin d'escalade sur un mesh 3D (montagne/falaise) entre deux points, en utilisant une projection sur plan et des raycasts pour assurer un chemin droit et praticable.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…