Skip to content

review-pr: harden Pre-Verdict Audit against comment-quality halo effect - #66

Draft
warp-agent-staging[bot] wants to merge 1 commit into
eval-base/019ff1e1from
worker/harden-pre-verdict-audit-comment-check
Draft

review-pr: harden Pre-Verdict Audit against comment-quality halo effect#66
warp-agent-staging[bot] wants to merge 1 commit into
eval-base/019ff1e1from
worker/harden-pre-verdict-audit-comment-check

Conversation

@warp-agent-staging

Copy link
Copy Markdown
Contributor

Summary

Hardens the ## Pre-Verdict Audit section of .agents/skills/review-pr/SKILL.md against a "comment-quality halo effect": a reviewer let a comment's writing quality/technical accuracy substitute for actually checking it against the target repo's commenting guidelines, and missed confirmed rule violations as a result.

Change

Documentation-only edit to exactly one section (## Pre-Verdict Audit), replacing the Comments bullet:

  • Requires enumerating every added/changed comment individually with its file:line (so none get skimmed past as part of a holistic impression).
  • Requires checking each one against the repo's own commenting guidelines, or, if none exist, against the commenting distribution of existing code (density, tone, what's explained vs. omitted).
  • Explicitly forbids treating a comment's writing quality, technical accuracy, or the subtlety/importance of the issue it describes as a mitigating factor for a guideline violation.

No schema, severity labels, safety rules, evidence rules, suggestion-block constraints, or diff-line-annotation contract were touched. The Tests bullet is unchanged.

Ticket

  • ticket_id: eval-full-20260813-019ff1e1-a170-74a5-b5d0-a20775b5947b-trio-r1
  • ticket_source: adhoc

Co-Authored-By: Warp Agent agent@warp.dev

Require enumerating each added/changed comment individually with its
file:line, and evaluate each against the repo's commenting guidelines
(or existing commenting norms when none are written) independently of
the comment's writing quality, technical accuracy, or how
subtle/important the issue it describes is.

Co-Authored-By: Warp Agent <agent@warp.dev>
@warp-agent-staging warp-agent-staging Bot added the factory-ab-eval Factory A/B evaluation replay label Aug 13, 2026
@warp-agent-staging

Copy link
Copy Markdown
Contributor Author

This PR was generated with Warp.

View run View conversation

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

factory-ab-eval Factory A/B evaluation replay

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant