chore(agents): trim rules to save context overhead - #22923
Open
isaacs wants to merge 1 commit into
Open
Conversation
Found by `claude doctor` as a significant source of context usage, leading to more frequent compaction. Trim details out of the AGENTS.md file to only include what agents can't already infer. This saves a few thousand tokens of context used in every session. The package script table, package layout listing, and skill index all restated things agents read anyway: root `package.json`, the `packages/` tree, and `.claude/skills/`. Each one costs context on every session and goes stale on every rename. Keep only the parts that aren't discoverable: `packages/types` is deprecated, and an AI provider integration spans three packages. Everything else points at the source of truth. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
nicohrubec
approved these changes
Jul 31, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Found by
claude doctoras a significant source of context usage, leading to more frequent compaction.Trim details out of the AGENTS.md file to only include what agents can't already infer. This saves a few thousand tokens of context used in every session.
The package script table, package layout listing, and skill index all restated things agents read anyway: root
package.json, thepackages/tree, and.claude/skills/. Each one costs context on every session and goes stale on every rename.Keep only the parts that aren't discoverable:
packages/typesis deprecated, and an AI provider integration spans three packages. Everything else points at the source of truth.