Agent skill

List Review Threads

by NTCoding in NTCoding/living-architecture

List unresolved review threads for the pull request recorded in workflow state.

Apache-2.0Auto-check passedDevelopment

Install List Review Threads

skills CLI
$ npx skills add NTCoding/living-architecture --skill list-review-threads -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NTCoding/living-architecture list-review-threads --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NTCoding/living-architecture.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tools/dev-workflow-v2/skills/list-review-threads .claude/skills/list-review-threads && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
list-review-threads
GitHub stars
139
Token cost
~400 tokens
SKILL.md length
171 words
Files
2
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

List unresolved review threads for the pull request recorded in workflow state.

  • Works in 7 steps: Detect the current harness before… → Run the selected harness's get-state… → Stop if prNumber is missing. Do not… → …
  • Tasks that involve Pull requests
  • Calls pnpm

What it does

List Review Threads is an agent skill from NTCoding/living-architecture. List unresolved review threads for the pull request recorded in workflow state. Use only when explicitly invoked as the list-review-threads skill.

Its SKILL.md is about 400 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Pull requests. The repository describes itself as: Extra software architecture from your code as living documentation. AI-assisted. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Pull requests

Example prompts

  • “/list-review-threads”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Detect the current harness before reading review threads
  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…
  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…
  7. Return exactly this report shape

What it can do on your machine

Read from SKILL.md and the folder at commit a24bc9f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

List Review Threads loads about 400 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 171 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~400

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NTCoding/living-architecture at commit a24bc9f, republished under its Apache-2.0 licence (© NTCoding). 171 words, ~400 tokens.

Download SKILL.mdSave it as .claude/skills/list-review-threads/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
list-review-threads
description
List unresolved review threads for the pull request recorded in workflow state. Use only when explicitly invoked as the list-review-threads skill.

List Review Threads

  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:
text
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.

© NTCoding, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in tools/dev-workflow-v2/skills/list-review-threads of NTCoding/living-architecture.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit a24bc9f

Compare with similar skills

List Review Threads next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

List Review Threads compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
List Review Threads this skillNTCoding/living-architecture139—~400Automated safety check: PassApache-2.0
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT
PR Design DocOpenHands/OpenHands90k—~2.4kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    90k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

More from NTCoding/living-architecture

  • Ddd

    NTCoding/living-architecture

    Explore and evaluate domain models collaboratively before implementation.

    139 GitHub stars~4k tokensUpdated 2 days ago
    Auto-check passed
  • Dev Workflow Start Implementation

    NTCoding/living-architecture

    Start implementation for a GitHub issue. An agent skill from NTCoding/living-architecture.

    139 GitHub stars~193 tokensUpdated 2 days ago
    Auto-check passed
  • Workflow

    NTCoding/living-architecture

    Execute a low-level dev-workflow-v2 state operation. An agent skill from NTCoding/living-architecture.

    139 GitHub stars~200 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about List Review Threads

What does List Review Threads do?

List unresolved review threads for the pull request recorded in workflow state. List Review Threads is an agent skill from NTCoding/living-architecture. List unresolved review threads for the pull request recorded in workflow state.

When should I use List Review Threads?

List Review Threads fits situations like: tasks that involve Pull requests.

How do I install List Review Threads in Claude Code?

Run `npx skills add NTCoding/living-architecture --skill list-review-threads -a claude-code`. Or copy the skill folder (tools/dev-workflow-v2/skills/list-review-threads in NTCoding/living-architecture) into .claude/skills/list-review-threads in your project. Claude Code loads it when a task matches its description.

How do I install List Review Threads in Codex?

Run `npx skills add NTCoding/living-architecture --skill list-review-threads -a codex`. Or copy the skill folder (tools/dev-workflow-v2/skills/list-review-threads in NTCoding/living-architecture) into .agents/skills/list-review-threads in your project. Codex loads it when a task matches its description.

Can I use List Review Threads in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NTCoding/living-architecture --skill list-review-threads -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/list-review-threads, .gemini/skills/list-review-threads, .github/skills/list-review-threads and .opencode/skills/list-review-threads in your project.

What does List Review Threads need to run?

Going by SKILL.md and its folder, List Review Threads needs the command-line tools its instructions call (pnpm).

Does List Review Threads access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is List Review Threads safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does List Review Threads use?

List Review Threads is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does List Review Threads use?

About 400 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to List Review Threads?

Skills that share tags, products or a category with List Review Threads: Finishing a Development Branch (obra/superpowers, 296k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 86k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains List Review Threads?

NTCoding (a GitHub user) maintains it in NTCoding/living-architecture, which has 139 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 5, 2026.

Source: NTCoding/living-architecture on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.