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 xiaobei930/cc-best --skill search-firstgit clone --depth 1 https://github.com/xiaobei930/cc-bestWrote 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/xiaobei930/cc-best/search-first)<a href="https://agentmods.dev/skills/xiaobei930/cc-best/search-first"><img src="https://agentmods.dev/badge/skills/xiaobei930/cc-best/search-first.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 | $0.00030 | $0.01149 |
| Opus 5 | $0.00015 | $0.00575 |
| Sonnet 5 | $0.00006 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
search-first 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 4d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究优先工作流
编码前系统化搜索现有方案，做出 Adopt/Extend/Compose/Build 决策。
核心原则：不重复造轮子，但也不盲目引入依赖。
触发条件 | Trigger Conditions
/cc-best:lead技术方案设计阶段- 需要引入新库/工具/框架时
- 遇到"需要 X 功能"的需求时
- 解决不熟悉的技术问题时
搜索流程 | Search Process
1. 并行搜索（限时 5-10 分钟）
├─ 包管理器（npm/PyPI/Maven 等，根据项目技术栈）
├─ MCP 服务器（如适用）
├─ GitHub/社区方案
└─ 官方文档/API 参考
2. 方案评估
├─ 功能匹配度
├─ 维护活跃度（最近提交、issue 响应）
├─ 许可证兼容性
└─ 依赖复杂度
3. 决策 + 记录
├─ 输出 Adopt/Extend/Compose/Build 决策
├─ 记录到 progress.md 决策表
└─ 标注置信度
评估矩阵 | Decision Matrix
| 条件 | 决策 | 行动 |
|---|---|---|
| 精确匹配 + 活跃维护 + 兼容许可 | 采用 (Adopt) | 直接安装使用 |
| 部分匹配 + 良好基础 | 扩展 (Extend) | 安装 + 薄包装器适配 |
| 多个弱匹配 | 组合 (Compose) | 组合 2-3 个小包 |
| 无合适方案 | 构建 (Build) | 自研，但带着搜索知识 |
评估检查清单
- [ ] 功能是否满足核心需求（≥80%）
- [ ] 最近 6 个月内有提交
- [ ] 许可证与项目兼容（MIT/Apache/ISC 优先）
- [ ] 依赖数量合理（<20 direct deps）
- [ ] 有测试覆盖和文档
- [ ] 无已知安全漏洞
与角色工作流的集成 | Pipeline Integration
在 /cc-best:lead 工作流中，技术栈选型前自动触发：
PM(需求) → Lead(search-first → 方案设计) → Dev(实现)
集成方式
- Lead 角色：技术方案设计时，对每个新依赖执行 search-first
- Dev 角色：遇到"需要引入新工具"时，暂停编码执行 search-first
- Architect agent：架构决策中自动引用 search-first 结果
搜索策略 | Search Strategy
按场景选择搜索深度
| 场景 | 搜索深度 | 时间上限 |
|---|---|---|
| 已知成熟方案 | 浅搜索 | 2 分钟 |
| 常见功能需求 | 标准搜索 | 5 分钟 |
| 创新/罕见需求 | 深度搜索 | 10 分钟 |
搜索来源优先级
- 项目已有依赖（检查 package.json/go.mod 等）
- 项目技术栈生态的官方推荐
- 包管理器搜索（npm search / pip search 等）
- GitHub trending + awesome-xxx 列表
- WebSearch 通用搜索
决策记录模板 | Decision Template
### 搜索决策: [功能描述]
**搜索范围**: [npm/GitHub/WebSearch]
**候选方案**:
1. [方案A] - [优劣概述]
2. [方案B] - [优劣概述]
**决策**: [Adopt/Extend/Compose/Build] [方案名]
**理由**: [1-2 句]
**置信度**: [高/中/低]
最佳实践 | Best Practices
- 搜索有时间上限 — 超时用 MVP 方案，标记 TBD
- 不是每个工具都要搜索 — 区分"已知成熟方案"和"新需求"
- 检查维护状态 — star 多但 3 年未更新的比新库风险更高
- 考虑退出成本 — 深度耦合的依赖要慎重选择
- 记录搜索过程 — 即使决定 Build，也记录为什么不 Adopt
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.
- 4d ago First seen · 120 lines · 30 tokens per session scan A 672cde6449b4
search-first is a skill published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,149 once invoked, about $0.0002 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
source-command-audit-whitepapers
Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.