Choose code search tools based on the question: AST-grep for code structure, LEANN for meaning, and Grep for exact names. Read complete files after locating relevant matches to limit unnecessary output and token use.
Search Tool Hierarchy
Review the instructions the agent will receive before you install.
Use the most token-efficient search tool for each query type.
Query Type?
├── STRUCTURAL (code patterns)
│ → AST-grep (~50 tokens output)
│ Examples: "def foo", "class Bar", "import X", "@decorator"
│
├── SEMANTIC (conceptual questions)
│ → LEANN (~100 tokens if path-only)
│ Examples: "how does auth work", "find error handling patterns"
│
├── LITERAL (exact identifiers)
│ → Grep (variable output)
│ Examples: "TemporalMemory", "check_evocation", regex patterns
│
└── FULL CONTEXT (need complete understanding)
→ Read (1500+ tokens)
Last resort after finding the right file
| Tool | Output Size | Best For |
|---|---|---|
| AST-grep | ~50 tokens | Function/class definitions, imports, decorators |
| LEANN | ~100 tokens | Conceptual questions, architecture, patterns |
| Grep | ~200-2000 | Exact identifiers, regex, file paths |
| Read | ~1500+ | Full understanding after finding the file |
The grep-to-leann.sh hook automatically:
# STRUCTURAL → AST-grep
ast-grep --pattern "async def $FUNC($$$):" --lang python
# SEMANTIC → LEANN
leann search opc-dev "how does authentication work" --top-k 3
# LITERAL → Grep
Grep pattern="check_evocation" path=opc/scripts
# FULL CONTEXT → Read (after finding file)
Read file_path=opc/scripts/z3_erotetic.py
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
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Coordinate background agents through saved files, keeping lengthy work transcripts out of the main conversation. It defines how to pass results between agents, monitor progress, and verify completed work with tests.
Delegate implementation, file reading, and testing to separate agents, then bring concise summaries back to the main conversation. The rules explain when delegation helps and when a small edit is better handled directly.
Organize implementation work across research, planning, validation, implementation, and review agents. Each stage passes files to the next, while implementation starts with failing tests and the main conversation coordinates the workflow.
Connect Agentica SDK agents to Claude Code CLI through a proxy, an intermediary server. Use setup and debugging guidance to address file permissions, streamed responses, result formatting, and agents reporting success without performing the requested operations.
Consult Agentica APIs when building workflows where multiple AI agents cooperate. This reference covers eleven coordination patterns, agent tracking, shared state, handoffs, and ways to combine results, with pointers to detailed API specifications.
Write clearer instructions for Agentica and REPL agents by specifying roles, file operations, and output formats. Includes templates for dividing research, coordinating specialists, reviewing solutions, and passing results between agents through files.