Search Router
- 467 installs
- 3.9k repo stars
- Updated January 26, 2026
- parcadei/continuous-claude-v3
search-router is an agent skill that routes codebase search queries to the most token-efficient tool—TLDR Search, AST-grep, or Grep—based on query type for developers who need fast symbol, call-chain, and structural code
About
search-router is an AI & Agent Building skill from parcadei/continuous-claude-v3 (user-invocable: false) that implements a decision tree for codebase search. Code exploration queries for symbols, call chains, and data flow default to TLDR Search via tldr search, cited for 95% token savings over Grep. Structural AST pattern queries route to AST-grep, while other query types follow the embedded decision tree. Developers reach for search-router when agents waste tokens on broad Grep scans, need efficient symbol lookup like spawn_agent or DataPoller, or must choose between TLDR Search and AST-grep for structural versus exploratory code queries.
- search-router
Search Router by the numbers
- 467 all-time installs (skills.sh)
- +2 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #903 of 4,347 Backend & APIs skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill search-routerAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 467 |
|---|---|
| repo stars | ★ 3.9k |
| Last updated | January 26, 2026 |
| Repository | parcadei/continuous-claude-v3 ↗ |
Which search tool saves the most tokens for code?
Use search-router for development tasks
Who is it for?
Developers whose agents explore large codebases and need a decision tree to pick TLDR Search or AST-grep over expensive Grep scans.
Skip if: Simple single-file lookups or developers without TLDR Search or AST-grep installed should use basic Grep or IDE search instead.
When should I use this skill?
An agent searches for code patterns, symbols, call chains, data flow, or structural AST patterns and needs the token-efficient tool selected.
What you get
Correctly routed search results from TLDR Search, AST-grep, or Grep with reduced token consumption on code exploration queries.
- Routed search results
- Token-efficient code exploration output
By the numbers
- TLDR Search cited for 95% token savings over Grep
- AST-grep cited for ~50 token efficiency on structural patterns
Files
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 fileToken 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.pyOptimal 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 savedRelated Skills
/tldr-search- DEFAULT - Code exploration with 95% token savings/ast-grep-find- Structural code search/morph-search- Fast text search
Related skills
Lark Openapi ExplorerInstantly explore, test, and generate calls against the full Lark (Feishu) OpenAPI surface without leaving their agent workflow.493k
Lark EventConsume real-time events from Lark/Feishu as structured NDJSON streams inside AI agent workflows.387k16kLark Openapi ExplorerWhen an existing Lark/Feishu skill or CLI command cannot fulfill a specific requirement and they need to discover and invoke the exact native OpenAPI endpoint.386k16k
Just ScrapeQuickly search, crawl, extract structured JSON, or monitor web pages without writing custom scraping code.245k41Lark AppsQuery the current visibility and permission scope of a Lark (Feishu) app without writing HTTP client code.235k16k
Design An InterfaceGenerate multiple radically different interface or API designs in parallel before committing to one.188k198kHow it compares
Pick search-router when agents need a decision tree for token-efficient search; use raw Grep only for simple literal string matches in small files.
FAQ
When should agents use TLDR Search over Grep?
search-router defaults code exploration queries—symbols, call chains, data flow—to TLDR Search via tldr search, achieving 95% token savings compared to Grep. Examples include queries for spawn_agent, DataPoller, or redis usage.
What query types does search-router send to AST-grep?
search-router routes structural AST pattern queries to AST-grep for efficient matching. Code exploration and identifier lookups follow separate branches in the decision tree, with TLDR Search as the default for symbol and call-chain searches.