CCG is a command-line workflow engine that coordinates Claude, Codex, Gemini, and other models as specialized collaborators on coding tasks. It is used to analyze requests, choose a strategy, delegate work to model-specific roles, and combine their results. The catalogue entries provide the skills, commands, agents, and plugin that implement this workflow.
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/fengshao1227/ccg-workflow/scraplingnpx skills add fengshao1227/ccg-workflow --skill scraplinggit clone --depth 1 https://github.com/fengshao1227/ccg-workflowWrote 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/fengshao1227/ccg-workflow/scrapling)<a href="https://agentmods.dev/skills/fengshao1227/ccg-workflow/scrapling"><img src="https://agentmods.dev/badge/skills/fengshao1227/ccg-workflow/scrapling.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 5.1 | $0.00074 | $0.01083 |
| Opus 5 | $0.00037 | $0.00541 |
| Sonnet 5 | $0.00015 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
scrapling 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 2d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scrapling 网页抓取 Skill
步骤 0：检查版本
pip show scrapling
- 未安装 → 执行
pip install "scrapling[fetchers]"+scrapling install - 有新版 → 执行
pip install --upgrade "scrapling[fetchers]"→ 查 changelog 告知用户 - 已最新 → 继续
步骤 1：选择 Fetcher
目标网站 →
│
├─ 已有 HTML 字符串/文件，只需解析?
│ → Selector（纯解析，无网络请求）
│ → 模板: templates/parse_only.py
│
├─ 静态页面，无 JS 渲染，无反爬?
│ → Fetcher（最快，基于 curl_cffi）
│ → 模板: templates/basic_fetch.py
│
├─ 需要登录（HTTP 表单，非 JS 登录）?
│ → FetcherSession（保持会话 cookie）
│ → 模板: templates/session_login.py
│
├─ 有 Cloudflare / WAF 保护?
│ → StealthyFetcher（Camoufox 浏览器，自动过 CF）
│ → 模板: templates/stealth_cloudflare.py
│
├─ SPA 应用（React/Vue），需要 JS 渲染?
│ → DynamicFetcher（Playwright 浏览器）
│ → 基于模板即时生成
│
└─ 不确定?
→ 先用 Fetcher 试，403/空内容 → 升级到 StealthyFetcher
步骤 2：执行工作流
1. 检查版本（步骤 0）
2. 查阅 references/site-patterns.md — 匹配已有模式则直接复用
3. 无匹配 → 用决策树选择 Fetcher
4. 读取对应模板 → 替换参数 → 生成完整脚本
5. 执行脚本 → 返回结果
6. **沉淀经验（必做）**:
- 新站点 → 追加到 site-patterns.md
- 新 cookie / 用户提供了 cookie → 保存到 cookie-vault.md
- **完成抓取后必须检查**：是否有新的 cookie 或 site pattern 需要保存
Cookie 格式速查
| Fetcher 类型 | Cookie 格式 | 示例 |
|---|---|---|
| Fetcher / FetcherSession | dict |
{'name': 'value', 'token': 'abc'} |
| StealthyFetcher / DynamicFetcher | list[dict] |
[{'name': 'n', 'value': 'v', 'domain': '.site.com', 'path': '/'}] |
浏览器 Fetcher cookie 必填字段: name, value, domain, path
超时单位速查
| Fetcher 类型 | 超时单位 | 示例 |
|---|---|---|
| Fetcher / FetcherSession | 秒 | timeout=30 |
| StealthyFetcher / DynamicFetcher | 毫秒 | timeout=60000 |
模板索引
| 模板 | 文件 | 何时读取 |
|---|---|---|
| 基础 HTTP 抓取 | templates/basic_fetch.py |
目标为静态页面，无反爬 |
| Cloudflare 绕过 | templates/stealth_cloudflare.py |
目标有 CF/WAF 保护 |
| Session 登录 | templates/session_login.py |
需 HTTP 表单登录后抓取 |
| 纯 HTML 解析 | templates/parse_only.py |
已有 HTML 字符串，只需提取数据 |
References 索引
| 文件 | 何时读取 |
|---|---|
references/site-patterns.md |
每次抓取前先查阅 — 检查目标站点是否有已记录的模式 |
references/api-quick-ref.md |
生成脚本时查阅 — Fetcher/Selector 方法签名和参数 |
references/troubleshooting.md |
执行报错时查阅 — 按错误信息查找原因和解决方案 |
references/cookie-vault.md |
需要登录 cookie 时查阅 — 检查是否有历史记录可复用 |
references/maintenance.md |
安装/升级/依赖问题时查阅 — 安装层级和验证命令 |
What ships with it
9 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.
- references/api-quick-ref.md 3.4 KB
- references/cookie-vault.md 1.4 KB
- references/maintenance.md 2.4 KB
- references/site-patterns.md 3.3 KB
- references/troubleshooting.md 3.1 KB
- templates/basic_fetch.py 527 B runs code
- templates/parse_only.py 488 B runs code
- templates/session_login.py 717 B runs code
- templates/stealth_cloudflare.py 677 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.
- 2d ago First seen · 99 lines · 74 tokens per session scan A e369e2cd5f31
scrapling is a skill published in the GitHub repository fengshao1227/ccg-workflow (5,874 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 1,083 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 2026-09-03.
Other skills, from other repositories
browser
Browser automation — setup the bsession environment, fetch info from a website (one-shot), create scripted automations (one-shot or recurring), or debug existing sessions. Works from any repo.
agent-browser
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection.
playwright-cli
官方Microsoft Playwright CLI网页自动化工具，支持所有主流浏览器的无头/有头自动化操作，包括页面导航、元素交互、截图、录制、测试等功能。当用户提到网页自动化、浏览器操作、爬虫、截图、录制用户操作、E2E测试时触发。.
browser
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
credential-setup-with-computer-use
Guides n8n credential setup through Computer Use browser tools. Use when a user needs OAuth apps, API keys, client IDs, client secrets, or other credential values from an external service console.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.