claude: add readability reviewer agent to review-crdb#165700
Open
tbg wants to merge 1 commit intocockroachdb:masterfrom
Open
claude: add readability reviewer agent to review-crdb#165700tbg wants to merge 1 commit intocockroachdb:masterfrom
tbg wants to merge 1 commit intocockroachdb:masterfrom
Conversation
Contributor
|
Merging to
|
Member
3c86d4f to
52f7912
Compare
1308552 to
f13f06a
Compare
|
Detected infrastructure failure (matched: self-hosted runner lost communication with the server). Automatically rerunning failed jobs. (run link) |
Member
Author
|
Todo: some kind of feedback loop that offers to update the skill as follow-up from human reviews. |
Add a new review agent focused on whether the code helps a reader who is familiar with CockroachDB but new to the subsystem follow along. The existing review agents verify correctness, style, test coverage, type design, and commit structure, but none checks whether a newcomer to the code can follow its intent and structure without reconstructing it. The readability reviewer checks: - Datadriven command specification (documenting the command vocabulary) - Datadriven testdata narration (inline comments explaining state and intent) - Test infrastructure clarity (design rationale for mocks and helpers) - Test organization (separation of different test types, testdata splitting) - Orientation before complexity in production code (roadmap comments) - State narration in complex flows (phase labels and separation) - Stub and placeholder method documentation (TODO vs intentional no-op) - Working memory load (variable proximity, function structure) The agent is scoped to avoid overlap with existing agents -- it focuses specifically on cognitive load and narrative flow rather than style rules, simplification opportunities, test coverage, or type design. Co-Authored-By: roachdev-claude <roachdev-claude-bot@cockroachlabs.com>
f13f06a to
0ac5630
Compare
rafiss
reviewed
Mar 23, 2026
| --- | ||
| name: crdb-readability-reviewer | ||
| description: > | ||
| Reviews CockroachDB code changes for reader-friendliness — whether the code |
Collaborator
There was a problem hiding this comment.
there appears to be some overlap with the goals of the crdb-simplifier agent: https://github.com/cockroachdb/cockroach/blob/master/.claude/agents/crdb-simplifier.md
clarity and maintainability are called out there specifically. do you feel that the goals of each agent are distinct, or should we find a way to combine the two?
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.
Add a new review agent focused on whether the code helps a reader who is
familiar with CockroachDB but new to the subsystem follow along. The
existing review agents verify correctness, style, test coverage, type
design, and commit structure, but none checks whether a newcomer to the
code can follow its intent and structure without reconstructing it.
The readability reviewer checks:
The agent is scoped to avoid overlap with existing agents — it focuses
specifically on cognitive load and narrative flow rather than style rules,
simplification opportunities, test coverage, or type design.
Epic: none