triage

triage is a command for Claude Code from rikdc/ai-skills. It costs 17 tokens per session (561 once invoked), scanned A, original, MPL-2.0.

A command for reviewing all unresolved comments on a GitHub pull request, a proposed code change awaiting review. It classifies the comments, decides which actions apply, and can create follow-up tasks.

In plain words
What is it for?
Use it to triage the current branch's pull request or a specified pull request, with options to preview decisions or skip resolving comment threads.
Why use it?
It reduces the manual work of sorting review feedback and helps ensure useful comments are handled while irrelevant ones receive an explanation.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the pr-review-triage plugin — 1 skill, 1 command shipped together

Good fit Use it to triage the current branch's pull request or a specified pull request, with options to preview decisions or skip resolving comment threads.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rikdc/ai-skills/triage
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.

Clone the repo
git clone --depth 1 https://github.com/rikdc/ai-skills

Made for: Claude Code.

Or install pr-review-triage, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/rikdc/ai-skills/triage.svg)](https://agentmods.dev/commands/rikdc/ai-skills/triage)
Your own site
<a href="https://agentmods.dev/commands/rikdc/ai-skills/triage"><img src="https://agentmods.dev/badge/commands/rikdc/ai-skills/triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 561 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.
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 $0.00017 $0.00561
Opus 5 $0.00009 $0.00280
Sonnet 5 $0.00003 $0.00112
Haiku 4.5 $0.00002 $0.00056

Measured 7d ago against content hash ba2c5dc59f5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

triage 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 7d 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.

plugins/pr-review-triage/commands/triage.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/triage — PR Review Comment Triage

Triage all unresolved review comments on a pull request. Classifies each comment, decides whether to accept or reject, and takes action.

Usage

/triage                           # Triage current branch's PR
/triage 123                       # Triage PR #123
/triage --dry-run                 # Preview without acting
/triage --no-resolve              # Skip resolving handled threads

Workflow

Execute the triage-reviews skill with the provided arguments.

Use the triage-reviews skill to process the PR review comments. Pass through all arguments from $ARGUMENTS.

Steps

  1. Identify the target PR

    • If $ARGUMENTS contains a number or URL, use that PR
    • Otherwise, run gh pr view --json number,url,title for the current branch
  2. Fetch review comments

    • Get all review comments via gh api repos/{owner}/{repo}/pulls/{number}/comments
    • Get review summaries via gh api repos/{owner}/{repo}/pulls/{number}/reviews
    • Get the PR diff for code context via gh pr diff
  3. Classify each comment into: security, correctness, error-handling, performance, design, testing, style, nit, praise, or question

  4. Evaluate each comment against the actual code and project conventions:

    • Accept: Real issues, valid improvements aligned with project standards
    • Reject: Contradicts conventions, subjective preference, misunderstands intent
    • Acknowledge: Praise (thank), questions (answer)
  5. Present summary table with proposed actions grouped by decision

  6. Wait for user confirmation (unless --dry-run)

  7. Execute actions:

    • Accepted: thumbsup reaction + create beads issue with context and PR comment link
    • Rejected: post respectful reply explaining why, citing conventions, then resolve the thread
    • Praise: post thank-you reply, then resolve the thread
    • Questions: post answer, then resolve the thread (unless uncertain)
  8. Report completion with counts of actions taken

Read the full file on GitHub · 58 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. 7d ago First seen · 58 lines · 17 tokens per session scan A ba2c5dc59f5f

Subscribe to this mod's changes

triage is a command published in the GitHub repository rikdc/ai-skills (2 stars, last pushed 2d ago), licensed MPL-2.0. It adds 17 tokens to every session and 561 once invoked, about $0.0001 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 2026-08-31.