Repository navigation
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
The
/interrogaterubric checks correctness, root causes, structure, verification, complexity, and security, but it has no lens for the failures agents make most often when they write a diff: changing more than the intent asked for, relying on APIs that don't exist, handling only the happy path, and making design choices nobody was told about. Reviewers catch these sometimes, by accident. Naming them in the rubric makes every reviewer check for them.What changed
pstack/skills/interrogate/references/rubric.md, placed right after Correctness. It lists five checks, each phrased as something the reviewer does against the stated intent and the diff:harness/pstack/claude-codewithscripts/generate-pstack-harness-trees.mjs.Scope
One reference file and its harness copy. No new skill or command, and no change to how
/interrogateruns. Reviewers already receive this rubric in their prompt.Tradeoffs
I considered a standalone checklist skill and rejected it: the rubric is already where reviewers look, so a new skill would duplicate the entry point. Two related failure modes, wrong abstraction and style drift, are left out because Complexity Budget and the code-quality lens (canonical layer, existing helpers) already cover them.
Blast Radius
Adds about ten lines to every
/interrogatereviewer prompt. Nothing else reads this file.Verification
node scripts/check-pstack-docs.mjs: 0 problems.node scripts/generate-pstack-harness-trees.mjs --check: harness up to date.node scripts/validate-plugins.mjs: all plugins validated.