---
name: agent-orchestration
description: Agent Orchestration Rules When the user asks to implement something, use implementation agents t…
category: ai
runtime: Python
---

# agent-orchestration output preview

## PART A: Task fit
- Use case: Agent Orchestration Rules When the user asks to implement something, use implementation agents to preserve main context. Main: Read files → Understand → Make edits → Report (2000+ tokens consumed in main context) Main: Spawn agent("implement X per plan") Agent: Reads files → Understands → Edits → Tests runs entirely locally; runs on Python. Works with Cla….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “The Pattern / When to Use Agents / Key Insight” and do not present inference as author intent.

## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Agent Orchestration Rules When the user asks to implement something, use implementation agents to preserve main context. Main: Read files → Understand → Make edits → Report (2000+ tokens consumed in main context) Main: Spawn agent("implement X per plan") Agent: Reads files → Understands → Edits → Tests runs entirely locally; runs on Python. Works with Cla…”.
- **02** When the source has headings, the agent prioritizes “The Pattern / When to Use Agents / Key Insight” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.

## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.