Repository navigation
Land #57 and #58 on main - #59
Merged
Merged
Conversation
…ing sentence; triage proves its MUSTs After the maintainer's review, a fix that only rewords other text gets no re-review: review.md § Passes, the triage step and sdd-pr status's Next line now agree. A binding sentence a triage fix writes is proven with one sdd-pr guard run before its flip, the check the next pass used to make. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
artefact-prose.md § Prose register caps a finding at about 30 words and a PR body at about 300 besides its checklist, and asks a report for one item per line. sdd-close and the review brief apply it; the PR-body template asks for a three-sentence Summary and at most three notes; the AGENTS.md template carries the short form. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
review.md § Passes says what a written MUST is (a MUST, SHALL or REQUIRED line added to a specification, or the constitution on the informative profile); triage, status, the quick start and the tables use that term. This repository's PR template asks for the same short Summary and notes as the scaffolded one. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…es; budgets follow the sizes The conformance and doc reviewer descriptions restated when sdd-review dispatches them, and one copy disagreed with the plan sdd-pr start prints; sdd-review step 3 is the one home, and it now names a changed MUST, as the plan does. The implementer description drops the process its body states. The word budgets drop to the files' current sizes. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…strator's call /sdd-review --panel, the panel lines /sdd-deliver printed before the maintainer's review and the agents.review_panel descriptor key are gone. A second pass in any host that loads the plugin is /sdd-review --pr N; a reviewer that does not load it gets the review request in docs/ai-workflow.md § Review, filled with the range sdd-pr scope prints. A descriptor that still lists review_panel keeps an unread key. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
feat!: drop the review panel; which host reviews is the orchestrator's call
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.
#57 and #58 were stacked PRs. They merged into their stacked base branches (
feat/review-cost,feat/lean-after-triage) after #56 had already merged, so their changes never reachedmain. This PR brings them over unchanged: the re-review rule, triage guarding its MUSTs, the length rule, the description trims, and the removal of the review panel.No new changes; the diff is #57 + #58.
🤖 Generated with Claude Code