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-search-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-search-cce)<a href="https://agentmods.dev/skills/luochang212/cc-enhance/web-search-cce"><img src="https://agentmods.dev/badge/skills/luochang212/cc-enhance/web-search-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-search-cce"><img src="https://agentmods.dev/badge/skills/luochang212/cc-enhance/web-search-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 | $0.00055 | $0.00950 |
| Opus 5 | $0.00028 | $0.00475 |
| Sonnet 5 | $0.00011 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
web-search-cce scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
├─ Tavily curl (Bash) ──失败──┐ What it actually says
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。
网络搜索
核心原则
- 先读注册表。
~/.claude/tool-registry.json记录了每个工具的实测状态。 - 同层并发。独立通道同时发起，谁先返回用谁。
- 失败即降级，不重试。一个工具失败一次就跳到下一层。
优先级链
Tier 0 — 直接 URL
用户给了 URL 或你知道目标地址 → 不搜索，直接提取页面内容。优先用内置 WebFetch（<1s，覆盖 90% 页面）；JS 渲染/反爬页面用 Crawl4AI（需 Python 环境）；Crawl4AI 超时或被检测时降级到原生 Playwright 拿 inner_text。
Tier 1 — WebSearch（内置，零配置）
WebSearch 是 Claude Code 内置工具，零依赖、零成本、结构化返回。始终最先尝试。失败（如当前模型不支持）则立即降级到 Tier 2。
Tier 2 — Tavily / SearXNG（并列）
Tavily — ~0.6s 响应，JSON 结构化返回，不限频，英中文均可。1000 次/月。
SearXNG — 自部署 Docker，零额度限制，~3s 响应，中文 18 条/Tavily 5 条。
Tier 3 — web_search_prime MCP
域名过滤、时效性、内容长度控制优于 Tavily。有月额度，备选。
→ references/web-search-prime.md
Tier 4 — DuckDuckGo（兜底）
纯免费但 ~2s、HTML 需解析、限频。仅在前三层全部不可用时使用，降级前告知用户。
降级流程
需要搜索
├─ WebSearch (内置) ──失败──┐
│ ▼
├─ Tavily curl (Bash) ──失败──┐
├─ SearXNG (本地 Docker) ──失败──┤
│ ▼
├─ web_search_prime MCP ──失败──┐
│ ▼
└─ DuckDuckGo curl ── 兜底
搜索拿到 URL 后，提取页面内容：优先 WebFetch（内置，<1s）→ JS 重/反爬页用 Crawl4AI（magic=True 解微信）→ 超时或被检测时降级到原生 Playwright（wait_until=commit）。
结果展示
每条搜索结果必须附带链接，让用户能直接点开看原文。格式：
1. **标题** — 来源
🔗 https://...
维护
工具状态变更时更新 ~/.claude/tool-registry.json。
环境依赖
| 依赖 | 用途 | 安装方式 | 磁盘 | 必需 |
|---|---|---|---|---|
| Tavily API Key | 首选搜索，~0.6s，1000次/月 | 注册 tavily.com → export TAVILY_API_KEY=xxx |
0 | 否 |
| ddgs | 兜底搜索，防 CAPTCHA | pip install ddgs |
~1MB | 否 |
What ships with it
4 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 · 83 lines · 55 tokens per session scan A d2425cfc79a9
web-search-cce is a skill published in the GitHub repository luochang212/cc-enhance (7 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 950 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
scaffold
Use when starting hyperflow in a new project, refreshing the .hyperflow/ cache, or installing auto-detection shims (AGENTS.md, CLAUDE.md). One-shot project setup; does not start the spec → scope → dispatch chain. Trigger with /hyperflow:scaffold, "init hyperflow", "set up hyperflow", "refresh hyperflow", "install…
review
Rigorous code review of all uncommitted changes. Analyzes architecture, code quality, security, and engineering best practices. Embeds questions and assumptions inline, then summarizes all proposed changes as a plan for user approval before any edits are made.
capability-evolver
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
fastapi
FastAPI best practices and conventions. Use when working with FastAPI APIs and Pydantic models for them. Keeps FastAPI code clean and up to date with the latest features and patterns, updated with new versions. Write new code or refactor and update old code.
commit
Git commit workflow with precommit hook handling, lint/type checking, README updates, and API reference updates. Use when the user wants to commit changes. Handles precommit hooks that modify files (formatting, linting) by re-staging and retrying. Runs ruff lint and pyright type checks on staged Python files, and…
check-and-test
Run lint checks (ruff for Python, Biome for TS/JS), type checks (pyright for Python, tsc for TS/JS), and the standard pytest tiers (unit + e2e + tests skipped during pre-commit). Investigates failures to determine if they are application bugs or test issues, and fixes application bugs rather than weakening tests. Does…