Large codebase work with cheaper helper agents.
What it does
Guides large codebase work through cheaper helper agents while keeping architecture, integration, and final judgment with the lead model.
When to use it
Use for unfamiliar repositories, long test output, multi-file changes, architectural ambiguity, or validation that can run in parallel; skip tiny or tightly coupled work.
How to use it
It changes how the agent handles codebase work by delegating bounded research, edits, and tests while retaining integration and final review.
What you provide
- An existing project
Good to know
- starts one helper agent per item, so the count depends on the work
Latest review
What you need · 0
No setup requirements listed.
Access · 0
No additional actions listed.