What is web-verify-patcher?

A skill for analysing website verification checks such as image tests, slider puzzles, WAF challenges, and login verification. It uses supplied page evidence to identify the type and likely provider, with authorised testing steps.

Use it to inspect HTML, scripts, URLs, screenshots, labels, and network names; classify the verification; and choose an analysis approach. It can also help establish whether authorised verification tests have produced enough evidence.

It helps determine what kind of verification a website uses without guessing from a name or isolated error. It also sets boundaries for handling live pages, user-completed checks, and evidence collection.

web-verify-patcher — Skill for Codex by lwjjike

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.

Any agent

npx skills add lwjjike/xbsReverseSkill --skill web-verify-patcher

Clone the repo

git clone --depth 1 https://github.com/lwjjike/xbsReverseSkill

Made for: 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/lwjjike/xbsreverseskill/web-verify-patcher/github.svg)](https://agentmods.dev/skills/lwjjike/xbsreverseskill/web-verify-patcher)

Your own site

<a href="https://agentmods.dev/skills/lwjjike/xbsreverseskill/web-verify-patcher"><img src="https://agentmods.dev/badge/skills/lwjjike/xbsreverseskill/web-verify-patcher/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lwjjike/xbsreverseskill/web-verify-patcher"><img src="https://agentmods.dev/badge/skills/lwjjike/xbsreverseskill/web-verify-patcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 361 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,226 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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 5.1	$0.00361	$0.03226
Opus 5	$0.00180	$0.01613
Sonnet 5	$0.00072	$0.00645
Haiku 4.5	$0.00036	$0.00323

Measured 10d ago against content hash 80b8188db9fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

web-verify-patcher 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 10d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/analyze_tile_restore.py, scripts/classify_verify.py, scripts/eval_triggers.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.

web-verify-patcher/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Verify Patcher（网页验证码识别与验证方案分析）

使用这个技能分析网页验证码或网页验证材料，输出安全、可落地的“识别 + 厂商判断 + 验证分析方案 + 授权验证流程”。第一阶段做类型/厂商识别和方案选择；真实网页取证时先建立用户手动成功样本基线；第二阶段只在用户明确选择方案并确认授权后，编排离线求解、坐标/轨迹生成、平台请求模板、失败复盘、方案切换或授权验证测试。

工作流程

优先基于用户已提供的离线证据分析：HTML 片段、脚本 URL、iframe URL、页面可见提示文案、截图元信息、厂商参数名、网络接口名。
如果必须打开真实网页取证，先读取 references/browser-acquisition.md，并按其中的取证模式执行。启动任何浏览器前先让用户确认模式：ruyiPage + RuyiTrace、仅 ruyiPage、Camoufox + camoufox-reverse-mcp、仅 Camoufox、CloakBrowser、用户手动取证或 AI 自行决定。用户未确认前，不要打开页面、截图、抓包、注入 Hook、读取 Cookie/Storage 或启动任何浏览器工具。
打开网页时不要直接使用普通 Playwright、Puppeteer、系统浏览器或 CDP 路线；已选模式不可用时，暂停并让用户确认安装、提供路径、降级或切换，不要静默 fallback。验证码、登录、MFA 或设备验证出现时暂停，让用户手动完成或改为离线分析；授权取证时让用户多次手动完成验证码成功样本，用 scripts/evaluate_success_baseline.py 判断成功基线是否足够。
用现有证据运行离线分类脚本：
- python scripts/classify_verify.py --html page.html --url "https://example.test/login" --text "拖动滑块完成拼图" --pretty
- --html、--text、--screenshot-meta 既可以传文件路径，也可以直接传字符串。
得到初步分类后，再按需读取参考文件：
- 需要判断厂商/产品特征时读 references/provider-products.md。
- 需要判断验证码形态和证据要求时读 references/captcha-types.md。
- 需要按类型给方案时读 references/solution-playbooks.md。
- 需要打开真实网页、截图、抓包或采集页面证据时读 references/browser-acquisition.md。
- 如果 image-restore 命中 captcha_variant: tile-scramble，先用 scripts/analyze_tile_restore.py 判断是否是切片/分块乱序图，再分析 tileOrder、pieceOrder、background-position、drawImage 或纯图片边缘连续性。
用户从 solution_options 中选择方案并明确确认后，进入第二阶段：
- 总流程必须读 references/verification-workflow.md。
- 使用开源/本地方案时读 references/open-source-recipes.md。
- 使用打码平台时读 references/solver-platform-recipes.md。
- 需要坐标换算、滑块/拖放/刮刮卡/轨迹绘制时读 references/motion-and-coordinate.md，优先用 scripts/map_coordinates.py 和 scripts/generate_motion_track.py 生成离线结果。
- 需要厂商执行注意点时读 references/provider-execution-notes.md。
- 进入真实网页验证前，先评估用户手动成功样本基线：默认同一授权目标至少 5 次成功样本；若观察到新的验证码类型，该类型至少 2 次成功样本。基线不足时输出强提示，但用户确认后仍可继续离线分析或受控验证。
- 同一授权目标、同一验证码类型、同一用户选择方案出现连续失败时，用 scripts/evaluate_verification_attempts.py 复盘 attempts JSON；连续 5 次失败且图片/坐标/轨迹/切片还原/补环境/challenge 新鲜度均无明显异常时，主动建议 recommended_next_route: platform-control。
- 真实页面点击、拖动、提交或抓取 Cookie/Storage 前必须再次让用户确认授权目标、执行模式和浏览器取证模式。
输出报告时必须包含：
- captcha_type
- provider
- 置信度和命中的信号
- 为什么判断为该类型/厂商
- 推荐方案：先给开源/本地方案，再给低通过率时的打码平台或人工/厂商备选，最后说明切换条件
- 关键风险和缺失证据
- 第二阶段执行时还必须包含：用户选择的方案、执行前检查结果、是否需要真实网页操作、需要用户确认的动作、产物路径或 JSON 结果
- 真实网页取证或第二阶段执行前还必须包含：success_baseline_status、success_baseline_summary、missing_success_samples
- 第二阶段失败复盘时还必须包含：attempt_summary、diagnosis_status、switch_triggered、recommended_next_route、platform_control_plan、requires_user_confirmation

Read the full file on GitHub · 136 lines

Files

What ships with it

20 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.

10d ago First seen · 136 lines · 361 tokens per session scan A 80b8188db9fd

Subscribe to this mod's changes

web-verify-patcher is a skill published in the GitHub repository lwjjike/xbsReverseSkill (362 stars, last pushed 1mo ago), licensed MIT. It adds 361 tokens to every session and 3,226 once invoked, about $0.0018 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.

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens