[FEATURE] Semantically meaningful plan names

Resolved 💬 2 comments Opened Jan 2, 2026 by backnotprop Closed Jan 2, 2026

Preflight Checklist

  • [x] I have searched existing requests and this feature hasn't been requested yet
  • [x] This is a single feature request (not multiple features)

Problem Statement

Claude will perform much better if it can read the names of plans on disk. It's a very simple context enhancement. As Claude wouldn't actually have to read the plan.

Instead of arbitrary-random-plan.md
you would have detailed-feature-description.md

Proposed Solution

Instead of arbitrary-random-plan.md
you would have detailed-feature-description.md

Alternative Solutions

Before Claude had its own plan mode, I had my own planning alchemy, and the key feature that would enable Claude to get caught up to speed was ls of the plan directory - all the file names get Claude an immediate understanding of where the project's at from a high-level.

Priority

High - Significant impact on productivity

Feature Category

File operations

Use Case Example

_No response_

Additional Context

Please also fix https://github.com/anthropics/claude-code/issues/15755

View original on GitHub ↗

This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗