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 luochang212/cc-enhance --skill web-fetch-ccegit clone --depth 1 https://github.com/luochang212/cc-enhanceWrote 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/luochang212/cc-enhance/web-fetch-cce)<a href="https://agentmods.dev/skills/luochang212/cc-enhance/web-fetch-cce"><img src="https://agentmods.dev/badge/skills/luochang212/cc-enhance/web-fetch-cce/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/luochang212/cc-enhance/web-fetch-cce"><img src="https://agentmods.dev/badge/skills/luochang212/cc-enhance/web-fetch-cce.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00084 | $0.01084 |
| Opus 5 | $0.00042 | $0.00542 |
| Sonnet 5 | $0.00017 | $0.00217 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
web-fetch-cce 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.
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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
来自 cc-enhance。
-cce后缀表示此技能由 cc-enhance 项目安装，避免与本地同名技能冲突。
Web Fetch
搜索拿到 URL 之后，把页面内容提取为 Claude 可读的格式。
工具选择
| 工具 | 适用场景 | 格式 |
|---|---|---|
WebFetch |
静态页面、文档、博客 | HTML → Markdown |
| Crawl4AI | JS 渲染、反爬、结构化提取 | Playwright → Markdown / JSON |
| 原生 Playwright | Crawl4AI 超时/被检测时的降级 | inner_text 纯文本 |
策略
- 优先
WebFetch。内置、<1s、零依赖。覆盖 90% 的页面。 - Crawl4AI 处理 JS 重/反爬页。Markdown 质量好，
magic=True解微信。 - 原生 Playwright 兜底。当 Crawl4AI 超时（阮一峰）或被检测时，手动控制
wait_until策略。
对比
| WebFetch | Crawl4AI | 原生 Playwright | |
|---|---|---|---|
| 速度 | <1s | 2-4s | 1-5s |
| JS 渲染 | 否 | 是 | 是 |
| 输出质量 | 可用 | 丰富 Markdown | 纯文本 |
| 反爬 | 否 | magic/undetected | 手动注入 |
| 灵活性 | 无 | 中 | 高（wait_until、stealth） |
| 适合 | 90% 日常 | JS 重/反爬页 | Crawl4AI 搞不定时 |
参考
- references/crawl4ai.md — Crawl4AI 部署与使用、中国站点实测矩阵
- references/playwright.md — 原生 Playwright 降级方案
环境依赖
| 依赖 | 用途 | 安装方式 | 磁盘 | 必需 |
|---|---|---|---|---|
| Python 环境 + Crawl4AI | JS 渲染、反爬绕过 | 见下方「Python 环境检测」 | ~300MB | 否 |
| 无（WebFetch 内置） | 静态页面首选，零依赖 | — | 0 | 否 |
Python 环境检测
按以下顺序检查，任一项满足即可跳过安装：
conda --version→ 已有 conda，直接用 conda 创建环境uv --version→ 已有 uv，用uv venv && uv pip installpython3 --version→ 已有 python3，用venv + pip
若都没有，按优先级推荐安装：
安装后执行：
中国大陆使用镜像加速（腾讯云 / 阿里云二选一）：
# conda
conda create -n crawl4ai python=3.13 -y && conda activate crawl4ai
pip install -i https://mirrors.cloud.tencent.com/pypi/simple/ crawl4ai # 腾讯云
pip install -i https://mirrors.aliyun.com/pypi/simple/ crawl4ai # 阿里云
playwright install chromium
# uv
uv venv && source .venv/bin/activate
uv pip install -i https://mirrors.cloud.tencent.com/pypi/simple/ crawl4ai # 腾讯云
uv pip install -i https://mirrors.aliyun.com/pypi/simple/ crawl4ai # 阿里云
playwright install chromium
# venv
python3 -m venv venv && source venv/bin/activate
pip install -i https://mirrors.cloud.tencent.com/pypi/simple/ crawl4ai # 腾讯云
pip install -i https://mirrors.aliyun.com/pypi/simple/ crawl4ai # 阿里云
playwright install chromium
What ships with it
2 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.
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 · 86 lines · 84 tokens per session scan A 021c05b3dc86
web-fetch-cce is a skill published in the GitHub repository luochang212/cc-enhance (7 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 1,084 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
playwright
Browser automation, web testing, dynamic scraping, and visual verification using Playwright and agent-browser CLI. Supports DOM snapshots with @eN element references, form interactions, and screenshot validations.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
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…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.