triage-review

triage-review is a skill for Claude Code from helderberto/agent-skills. It costs 116 tokens per session (928 once invoked), scanned A, original, MIT.

A read-only tool for sorting unresolved comments on a GitHub pull request (PR), including comments from people and Copilot, GitHub’s coding assistant. It checks each comment against the current code and gives it a category with a short reason.

In plain words
What is it for?
Use it to decide which PR comments to fix, skip, mark optional, or discuss after checking the current code.
Why use it?
It helps separate useful feedback from comments that no longer apply or do not need action. It does not reply to or resolve review threads.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the hb plugin — 38 skills, 6 agents shipped together

Good fit Use it to decide which PR comments to fix, skip, mark optional, or discuss after checking the current code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/helderberto/agent-skills/triage-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add helderberto/agent-skills --skill triage-review
Clone the repo
git clone --depth 1 https://github.com/helderberto/agent-skills

Made for: Claude Code.

Or install hb, the plugin that ships this one along with the rest of its 38 skills, 6 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for triage-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/helderberto/agent-skills/triage-review/github.svg)](https://agentmods.dev/skills/helderberto/agent-skills/triage-review)
Your own site
<a href="https://agentmods.dev/skills/helderberto/agent-skills/triage-review"><img src="https://agentmods.dev/badge/skills/helderberto/agent-skills/triage-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for triage-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/helderberto/agent-skills/triage-review"><img src="https://agentmods.dev/badge/skills/helderberto/agent-skills/triage-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 928 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00116 $0.00928
Opus 5 $0.00058 $0.00464
Sonnet 5 $0.00023 $0.00186
Haiku 4.5 $0.00012 $0.00093

Measured 10d ago against content hash 5acd06deef92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

triage-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/triage-review/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Review Comments

Consume the review comments already on a PR — Copilot and human reviewers — and sort them into what's worth fixing and what isn't. This is judgment, not a fresh review: each comment is verified against the current code before a verdict.

Read-only. Never reply to threads, resolve conversations, or post anything. The output is a decision aid for the user.

Distinct from siblings: /code-review and /review generate new findings; this skill evaluates existing reviewer comments.

Workflow

  1. Fetch with gh — pull the PR's review comments (default to the current branch's PR). Cover both inline thread comments and top-level review summaries, from Copilot and human reviewers. Keep only unresolved threads — resolution state lives in the GraphQL reviewThreads field (isResolved), not REST pulls/comments, so reach for gh api graphql when you need to filter out resolved/outdated noise. Capture author, path, line, and body for each. No unresolved comments → report that and stop.

  2. Verify each against current code — read the file at path:line and confirm the comment still applies. Reviewers (especially bots) comment on stale diffs and miss surrounding context. An outdated: true thread defaults toward Skip unless the concern still holds in the current code. Completion: every comment has been checked against the actual code, not judged from its text alone.

  3. Classify each comment using the rubric below. Every verdict carries a one-line rationale grounded in what you saw in step 2.

  4. Output the triage table — grouped Address-first (see Output). Completion: every fetched comment appears in the table with a verdict and rationale.

  5. Offer to fix — ask whether to implement the Address items. On yes, hand them to /tdd (test-first). Don't auto-implement; don't touch Skip/Optional/Discuss items.

Rubric

Verdict When
Address Verified against current code as a real bug, risk, correctness gap, or clearly valid improvement.
Skip Wrong, false positive, outdated (code already changed), contradicts an established codebase convention, or outside this PR's scope. Rationale must cite the evidence, not just assert it.
Optional Subjective/style/preference with no correctness impact — the user's call.
Discuss Valid concern needing a decision you can't make alone (product tradeoff, breaking change, architectural direction).

Read the full file on GitHub · 65 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 65 lines · 116 tokens per session scan A 5acd06deef92

Subscribe to this mod's changes

triage-review is a skill published in the GitHub repository helderberto/agent-skills (14 stars, last pushed 9d ago), licensed MIT. It adds 116 tokens to every session and 928 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

generic-react-code-reviewer

Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or…

travisjneuman/.claude · 71 tokens

generic-fullstack-code-reviewer

Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.

travisjneuman/.claude · 64 tokens

generic-static-code-reviewer

Review static site code for bugs, security issues, performance problems, accessibility gaps, and CLAUDE.md compliance. Enforces pure HTML/CSS/JS standards, minimal page weight, mobile-first design. Use when completing features, before commits, or reviewing changes.

travisjneuman/.claude · 59 tokens

generic-code-reviewer

Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.

travisjneuman/.claude · 70 tokens

ecosystem-tools

Third-party Claude Code token/context/code-review tools. Use when choosing or recommending an external tool to reduce token usage, manage context, or review large codebases (caveman, code-review-graph, token-savior, context-mode...).

TheBeardedBearSAS/claude-craft · 52 tokens

git-workflow

Git workflow and conventional commits. Use when working with git, branches, commits, pull requests, code review, or version control strategy.

TheBeardedBearSAS/claude-craft · 31 tokens