A workflow for investigating how web front ends work internally, including request signatures, encrypted parameters, cookies, browser checks, and obfuscated JavaScript. It can also guide reproducing observed behavior outside the browser.

Use it to analyze request authentication, anti-bot fields, encrypted data, workers, WebAssembly, browser hooks, source maps, and JavaScript behavior that needs to be reproduced.

It helps turn difficult-to-read browser code and network behavior into testable findings instead of relying on guesses or incomplete clues.

web-reverse — Skill for Claude Code and Codex by JacksonTai2007: A workflow for investigating how web front ends work…

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/web-reverse

Any agent

npx skills add JacksonTai2007/cc-unlock --skill web-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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/web-reverse.svg)](https://agentmods.dev/skills/jacksontai2007/cc-unlock/web-reverse)

Your own site

<a href="https://agentmods.dev/skills/jacksontai2007/cc-unlock/web-reverse"><img src="https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/web-reverse.svg" alt="Measured on agentmods" height="20"></a>

Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,622 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.

Model	Per session	Once invoked
Fable 5	$0.00138	$0.07622
Opus 5	$0.00069	$0.03811
Sonnet 5	$0.00028	$0.01524
Haiku 4.5	$0.00014	$0.00762

Measured 5d ago against content hash 8b24c7743d5c, 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 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 5d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (artifacts/tasks/_TEMPLATE/core/run/closeout.mjs, artifacts/tasks/_TEMPLATE/core/run/run-local.mjs, artifacts/tasks/_TEMPLATE/core/run/validate-fixture.mjs, …), 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.

cc-unlock-files/skill-bundle/web-reverse/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Reverse

这是一个任务契约驱动的总控 + 路由系统，不是知识清单。本文件只做三件事：锁定验收目标、约束执行节奏、把任务路由到正确的 reference / workflow。细则一律按需读 references/ 与 docs/reference/（见末尾路由表）。

约束力来自机制而非文字篇幅，要优先消灭三种失效模式：

目标漂移：用户要 A，执行中偷偷降成 B，还把 B 说成完成。
虚假完成：没过最终验证就说"已完成 / 已交付"。局部样本、单点成功、容器可读、浏览器偶发成功都不算验收。
线索不落盘：发现了线索只放在脑子里 → 任务一中断就得重新分析，白烧 token。

何时使用

还原签名/认证参数/挑战链/风控字段；分析混淆 JS、动态代码、source map、反调试、反篡改；分析 Worker/iframe/多上下文、JSVMP/自定义 VM/WASM/媒体解密；基于浏览器证据做 Node/Python 复现、纯算法迁移、浏览器内可控复用；或继续已有 task-local 任务。

不适用：普通前端开发、密码学教学、漏洞利用 / 渗透或其它非 Web 前端逆向。

北极星：以验收为唯一目标

目标不是持续汇报新发现，而是在任务契约下尽快逼近用户验收目标。每个动作前先自问：① 用户最终交付是什么；② 这个动作是否直接缩短到该交付；③ 当前路线是否还值得再走一轮。研究型收敛 ≠ 交付型推进。

逆向中你通常不知道哪条路最短，直到走通。所以发现线索的第一反应是「记录」而不是「立刻写脚本验证」——验证可能失败、可能被打断，只有落盘的线索能跨轮复用（见下文「记录与搜索」）。

三条红线（其余都是指引，唯这三条不可退让）

先初始化再动手：任何分析 / 浏览器操作 / 写文件前，先在当前项目目录执行 node $TOOL_DIR/task-boot.mjs <task-id>（幂等：有任务则续跑，无则新建）。 $TOOL_DIR = 本 skill 包内 tools/task/ 的绝对路径，首次操作前先解析一次（解析细则见 docs/reference/tooling-degradation.md Step 0），本文件后续所有 node $TOOL_DIR/... 调用都复用此次解析结果。task-boot.mjs 是唯一开机入口，内部已串起 task-init（新建）/ resume → task-sync → task-advance，无需再逐个手调。 每个 workspace 只在首个动作前 boot 一次：续跑时直接按 task-advance 输出的 nextExecutableAction 执行，不要每轮重复 boot。boot 的 ready 输出会打印产物写入锚点的绝对路径（run/ / state/ / report.md），照它写。跳过它产物会散落根目录、状态无法跨轮恢复。Windows 路径用正斜杠。细则见 docs/reference/startup-gate-procedures.md。
产物落 task 目录：本任务产生的每个文件（脚本/样本/中间数据/报告）都落在 cwd 下 artifacts/tasks/<task-id>/（脚本与样本进 run/，状态进 state/，报告就是 report.md）。 cwd 根只允许项目元文件（SKILL.md / README.md / .gitignore / package.json / package-lock.json 等，以及 tsconfig.json / vite.config.* / requirements.txt 等常见构建配置；完整白名单真源 = tools/task/common.mjs 的 WORKSPACE_ROOT_ALLOWLIST，门禁与本表共用），其余逆向脚本/数据一律进 artifacts/tasks/。 这条红线有机械门禁：task-close / verify-once 会扫描 workspace 根目录，凡是本任务 boot 之后新增的非白名单 .js/.mjs/.cjs/.ts/.py/.json/.jsonl 文件一律 BLOCK（rule=move-stray-artifacts-into-task-run-dir）；task-close 还会自动把它们 [relocate] 进 run/。不要靠"我觉得放根目录也行"——门禁不认。
完成必须可验证："已完成 / 已成功 / 已交付"只能在 run/verify-once.mjs 真跑通、 run/fixtures.json 存在、acceptanceGap 为空后才能说。交付物 = 验证脚本跑通的副产品，不是口头宣称。 assert-can-reply 返回 BLOCKED（exit≠0）就等于「未完成」：此时禁止任何用户可见的交付性回复（包括"已完成/已闭环/已实现"的总结、表头标"已验证"、贴成功结论），只能继续执行它打印的 nextExecutableAction；复述 BLOCKED 原因、或把 BLOCKED 包装成"基本完成/已基本跑通"都不算交付，仍属违规。 挑战链 / 验证码 / 滑块类任务（模式 A）的验收 = 端到端服务端返回成功（如求解器实际通过、error==0 且业务校验通过），不是「格式被接受 / JSON 字段齐全 / validate-fixture 通过」——validate-fixture.mjs 只校验 JSON 字段存在，绝不能冒充验收；这类成功必须由 run/verify-once.mjs 复现，未复现前 claimLevel 最高只能停在 provisional。

Read the full file on GitHub · 227 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.

5d ago First seen · 227 lines · 138 tokens per session scan A 8b24c7743d5c

Subscribe to this mod's changes

web-reverse is a skill published in the GitHub repository JacksonTai2007/cc-unlock (137 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 7,622 once invoked, about $0.0007 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 Security

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

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens