feat(rules): OCR images when the model cannot read them

Merged
SH
25d ago
+6-0

Summary

  • Add an ## Images section to the tool-search rule: when the model cannot read an image, OCR it before replying instead of claiming it cannot see one.
  • Document tesseract image.png - (with --psm 4 for multi-column screenshots and terminal captures) and the nix shell nixpkgs#tesseract --command fallback.

Why

Models without image input otherwise stall on a pasted screenshot. This session hit that on a T3 Code screenshot and only OCR recovered the content.

Verification

  • bun run check passes (Ruler apply + Biome).
  • Regenerated ~/.claude/CLAUDE.md locally to confirm the rule reaches the generated output.

Summary by cubic

Adds an Images section to the tool-search rule so agents OCR images with tesseract before replying, instead of claiming they cannot see them when the model lacks image input.