List Review Threads

SkillDev tools

List unresolved review threads for the pull request recorded in workflow state. Use only when explicitly invoked as the list-review-threads skill.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the List Review Threads skill

What this skill tells your AI

The instructions your AI receives, as published by ntcoding/living-architecture in tools/dev-workflow-v2/skills/list-review-threads/SKILL.md and read by ahel’s review.

  1. Detect the current harness before reading review threads:
    • If CODEX_THREAD_ID is present, run workflow operations with pnpm --dir tools/dev-workflow-v2 run codex-workflow <operation> [args].
    • Otherwise, if PI_CODING_AGENT=true is present, run workflow operations with the workflow tool.
    • Otherwise, run workflow operations with /dev-workflow-v2:workflow <operation> [args].
  2. Run the selected harness's get-state workflow operation and extract prNumber.
  3. Stop if prNumber is missing. Do not infer a PR from the current branch.
  4. Fetch the PR URL, reviewDecision, reviews, and reviewThreads through GitHub GraphQL. Paginate the reviews, review threads, and every thread's comments connection until pageInfo.hasNextPage is false.
  5. Keep unresolved review threads only and group them by file path. Use no file when a thread has no path.
  6. For every unresolved thread, report its thread ID, file path, line when present, comment authors in chronological order, and the latest comment body selected by greatest createdAt.
  7. Return exactly this report shape:
PR: #<number> <url>
Unresolved threads: <count>

## <file path or "no file">
- Thread: <id>
  Line: <line or —>
  Authors: <author1>, <author2>
  Latest comment: <summary>

This skill is read-only. Do not reply to or resolve threads, and do not record workflow state.

Signals

GitHub stars
139
Forks
21
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
list-review-threads
Source
github.com/ntcoding/living-architecture