search-router 代码搜索路由器：智能选择最高效搜索工具，节省95% token，提升开发效率

search-router by parcadei/continuous-claude-v3

228 周安装量

3,700 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/parcadei/continuous-claude-v3 --skill search-router

开发命令行工具搜索

🇨🇳中文介绍

搜索工具路由器

为每种查询类型使用最高效的搜索工具。

使用场景

搜索代码模式
查找实现位置
寻找特定标识符
理解代码工作原理

决策树

Query Type?
├── 代码探索（符号、调用链、数据流）
│   → TLDR Search - 节省 95% 的 token
│   所有代码搜索的默认选择 - 替代 Grep 使用
│   示例："spawn_agent"、"DataPoller"、"redis usage"
│   命令：tldr search "query" .
│
├── 结构搜索（AST 模式）
│   → AST-grep (/ast-grep-find) - 约 50 个 token 输出
│   示例："def foo"、"class Bar"、"import X"、"@decorator"
│
├── 语义搜索（概念性问题）
│   → TLDR Semantic - 5 层嵌入（P6）
│   示例："how does auth work"、"find error handling patterns"
│   命令：tldr semantic search "query"
│
├── 字面搜索（精确文本、正则表达式）
│   → Grep 工具 - 最后手段
│   仅在 TLDR/AST-grep 不适用时使用
│   示例：错误消息、配置值、非代码文本
│
└── 完整上下文（需要完全理解）
    → Read 工具 - 1500+ token
    找到正确文件后的最后手段

Token 效率对比

工具	输出大小	最佳用途
TLDR	~50-500

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

🇺🇸English

Search Tool Router

Use the most token-efficient search tool for each query type.

When to Use

Searching for code patterns
Finding where something is implemented
Looking for specific identifiers
Understanding how code works

Decision Tree

Query Type?
├── CODE EXPLORATION (symbols, call chains, data flow)
│   → TLDR Search - 95% token savings
│   DEFAULT FOR ALL CODE SEARCH - use instead of Grep
│   Examples: "spawn_agent", "DataPoller", "redis usage"
│   Command: tldr search "query" .
│
├── STRUCTURAL (AST patterns)
│   → AST-grep (/ast-grep-find) - ~50 tokens output
│   Examples: "def foo", "class Bar", "import X", "@decorator"
│
├── SEMANTIC (conceptual questions)
│   → TLDR Semantic - 5-layer embeddings (P6)
│   Examples: "how does auth work", "find error handling patterns"
│   Command: tldr semantic search "query"
│
├── LITERAL (exact text, regex)
│   → Grep tool - LAST RESORT
│   Only when TLDR/AST-grep don't apply
│   Examples: error messages, config values, non-code text
│
└── FULL CONTEXT (need complete understanding)
    → Read tool - 1500+ tokens
    Last resort after finding the right file

Token Efficiency Comparison

Tool	Output Size	Best For
TLDR	~50-500	DEFAULT: Code symbols, call graphs, data flow
TLDR Semantic	~100-300	Conceptual queries (P6, embedding-based)
AST-grep	~50 tokens	Function/class definitions, imports, decorators
Grep	~200-2000	LAST RESORT: Non-code text, regex
Read	~1500+	Full understanding after finding the file

Examples

# CODE EXPLORATION → TLDR (DEFAULT)
tldr search "spawn_agent" .
tldr search "redis" . --layer call_graph

# STRUCTURAL → AST-grep
/ast-grep-find "async def $FUNC($$$):" --lang python

# SEMANTIC → TLDR Semantic
tldr semantic search "how does authentication work"

# LITERAL → Grep (LAST RESORT - prefer TLDR)
Grep pattern="check_evocation" path=opc/scripts

# FULL CONTEXT → Read (after finding file)
Read file_path=opc/scripts/z3_erotetic.py

Optimal Flow

1. AST-grep: "Find async functions" → 3 file:line matches
2. Read: Top match only → Full understanding
3. Skip: 4 irrelevant files → 6000 tokens saved

Related Skills

/tldr-search - DEFAULT - Code exploration with 95% token savings
/ast-grep-find - Structural code search
/morph-search - Fast text search

Weekly Installs

194

Repository

parcadei/contin…laude-v3

GitHub Stars

3.6K

First Seen

Jan 22, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykPass

Installed on

opencode188

codex186

gemini-cli185

cursor184

github-copilot182

amp179