code-review-follow-up

Classify post-fix code-review findings into disposition categories with evidence anchors.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/graysurf/agent-runtime-kit --skill code-review-follow-up
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review-follow-up
Source: https://github.com/graysurf/agent-runtime-kit/tree/main/tests/golden/claude/plugins/code-review/skills/code-review-follow-up/expected
Command: npx skills add https://github.com/graysurf/agent-runtime-kit --skill code-review-follow-up

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Re-checks previous code-review findings after fixes and classifies each item as resolved, unresolved, accepted-risk, or residual risk.

Core Features & Use Cases

  • Re-evaluates past review findings against current code to confirm dispositions.
  • Outputs per-item statuses with evidence anchors and optional reviewer notes.
  • Works in typical PR/workflow contexts where a base ref and fix range are available.

Quick Start

Run this workflow in the target repository to re-evaluate prior findings and produce per-item dispositions with supporting evidence.

Frequently Asked Questions about code-review-follow-up

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I verify code review findings after a pull request fix?

Post-fix code review verification requires previous findings and fix range metadata to validate each repair. The process applies a read-only workflow against the target repository, outputting per-item dispositions like resolved, unresolved, or accepted-risk with supporting evidence anchors.

What is disposition classification in code review follow-up?

Disposition classification in code review follow-up categorizes prior findings as resolved, unresolved, accepted-risk, not-reproducible, or residual-risk. It validates previous findings against current code changes and outputs per-item statuses with evidence anchors and optional reviewer notes.

What do I need to classify pull request dispositions after repairs?

Classifying pull request dispositions requires access to previous code review findings and fix range metadata. The process operates as a read-only validation within the target repository to re-evaluate prior findings and produce evidence-anchored per-item statuses.

Can I use a read-only workflow to validate unresolved code review findings?

Yes, you can validate unresolved code review findings using a read-only workflow in the target repository. It re-evaluates past findings against current code using fix range metadata, confirming resolved, unresolved, or accepted-risk statuses without modifying the repository.

When do I need to re-evaluate past code review findings?

You need to re-evaluate past code review findings when repairs are made in a pull request workflow. This post-fix verification step checks each previous finding against the current code to confirm its disposition, validating fixes with evidence anchors before merging.