v4.2.0: per-task reviewer on Opus 4.7 - #61
Merged
Merged
Conversation
`/code:ship` now runs the per-task reviewer fork and the review fix-pass on `opus` (4.7) instead of `sonnet` (4.6). Implementer stays on Sonnet 4.6. Anthropic's published numbers put Opus 4.7 at 87.6% SWE-bench Verified vs Sonnet 4.6's 79.6% — an 8-pt gap. The leverage is asymmetric: implementer errors get caught by reviewer + post-merge audit, but reviewer misses fail silently into the feature branch. Pay for capability where the cost of being wrong is highest. Also: `/code:fix` effort xhigh → high (single-bug intake is multi-file work with design choices, not architecture). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
/code:shipmove fromsonnet(4.6) →opus(4.7). Implementer stays on Sonnet 4.6./code:fixeffort loweredxhigh→high(single-bug intake is multi-file work with design choices, not architecture).Why
Anthropic's published numbers put Opus 4.7 at 87.6% SWE-bench Verified vs Sonnet 4.6's 79.6% — an 8-pt gap. The leverage of that gap is asymmetric across the two roles in
/code:ship:Review fix-pass moves with the reviewer to keep judgment consistent across the find/fix pair.
The principle in
code-et-implementer/CLAUDE.mdupdates accordingly: heavy lifting (planning, judgment, review) on Opus; routine coding from a complete brief on Sonnet; breadth gathering on Haiku.Test plan
/code:shipon a small feature, confirm reviewer fork is dispatched withmodel: "opus"and review fix-pass withmodel: "opus"./code:fixinvocation reportseffort: high.4.2.0shows in plugin metadata after/plugin marketplace update.🤖 Generated with Claude Code