review: add rust-api-ergonomics-reviewer agent and dual-review workflow#79
Merged
review: add rust-api-ergonomics-reviewer agent and dual-review workflow#79
Conversation
Adds a second pre-commit review agent focused on downstream-consumer ergonomics (happy-path friction, lints firing in user crates, runtime footguns, doc drift) to complement rust-code-reviewer's correctness/ safety lens. CLAUDE.md updated to run both in parallel; the ergonomics pass may be skipped for internal/test-only changes.
|
All contributors have signed the CLA ✍️ ✅ |
rpb-ant
approved these changes
Apr 28, 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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a second pre-commit review agent,
rust-api-ergonomics-reviewer, and updatesCLAUDE.mdto run it in parallel with the existingrust-code-reviewer.The two agents are complementary:
rust-code-reviewerrust-api-ergonomics-reviewerThe ergonomics agent's prompt is structured around what a first-time integrator of the crate actually sees in their editor and compiler output, rather than what the test suite catches. It explicitly defers correctness/unsafe-soundness/perf to the existing reviewer to avoid overlap.
Per the updated
CLAUDE.md, the ergonomics pass may be skipped for changes that touch only internal or test code with no public-API surface.