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 5.5 | $0.00034 | $0.00434 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 5mo ago), licensed MIT. It adds 84 tokens to every session and 1,084 once invoked, about $0.0003 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 2026-08-31.
web-fetch-cce compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| web-fetch-cceluochang212/cc-enhance | Skill | 7 | 5mo ago | MIT | A | 84 | Claude Code, Codex |
| playwrightSdinzsh/PowerHou53 | Skill | 5 | 1mo ago | none | A | 40 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |