Repository navigation
feat: Better AI documentation - #465
Merged
mihajlo-stojkovic merged 8 commits intoMar 18, 2026
Merged
Conversation
Signed-off-by: Ilya Boyandin <[email protected]>
Signed-off-by: Ilya Boyandin <[email protected]>
…ce (#425) Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: copilot-swe-agent[bot] <[email protected]> Co-authored-by: dmitriy-kostianetskiy <[email protected]>
) Co-authored-by: copilot-swe-agent[bot] <[email protected]> Co-authored-by: dmitriy-kostianetskiy <[email protected]>
Co-authored-by: copilot-swe-agent[bot] <[email protected]> Co-authored-by: dmitriy-kostianetskiy <[email protected]> Co-authored-by: Dmitriy Kostianetskiy <[email protected]>
Contributor
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
…n-docs # Conflicts: # CLAUDE.md # CLAUDE.md~chore_remove-openassistant-dep # packages/notebook/src/cellOperations/AddNewCellDropdown.tsx
ilyabo
approved these changes
Mar 12, 2026
mihajlo-stojkovic
merged commit Mar 18, 2026
50d8ce6
into
chore/remove-openassistant-dep
3 checks passed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Restructures
AGENTS.mdandCLAUDE.mdto follow progressive disclosure principles, replacing the 270-lineCLAUDE.mdwith a lean root file and a set of topic-specific docs loaded on demand.Inspired by A Complete Guide To AGENTS.md.
What changed
AGENTS.md— rewritten as a minimal root fileThe previous
CLAUDE.mdloaded ~270 lines of architecture docs, patterns, troubleshooting, and common tasks into every AI request regardless of relevance. The newAGENTS.mdis ~41 lines covering only what every agent always needs: project description, requirements, key commands, and critical gotchas.CLAUDE.md— replaced with a symlinkCLAUDE.mdis now a symlink toAGENTS.md, so Claude Code and Cursor both read the same canonical file without drift.contributing/— progressive disclosure docsA new
contributing/folder at the repo root (outsidedocs/, not picked up by VitePress orllms.txt) holds six topic-specific files agents load only when relevant:architecture.mdpatterns.mdadding-features.mdtroubleshooting.mdpython.mdcursor-cloud.mdWhy
AI agents load
AGENTS.mdon every request regardless of what they're actually doing. A 270-line file that covers architecture, patterns, troubleshooting, and common tasks wastes that budget on content irrelevant to some, if not most tasks, and frontier models start dropping instructions around the 150–200 mark anyway.The new structure gives agents a fast, focused entry point and lets them pull in deeper context only when the task calls for it.