agentmods.dev

triage

triage is a command for Claude Code from juanmhidalgo/claude-plugins. It costs 36 tokens per session (1,216 once invoked), scanned A, original, MIT.

A process for checking whether comments from automated code reviewers on an open GitHub pull request are correct before making changes.

In plain words
What is it for?
Use it to fetch review comments, investigate their context, classify them as valid or incorrect, and identify which issues should be fixed.
Why use it?
Automated review comments can misunderstand the code or suggest unnecessary changes, so this process verifies each one against the actual project.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the code-review plugin — 5 skills, 14 commands, 13 agents shipped together

not rated 8 11d ago A scan 36 tokens original MIT
View the source file juanmhidalgo/claude-plugins
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.

agentmods
npx agentmods add commands/juanmhidalgo/claude-plugins/triage
Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Made for: Claude Code.

Or install code-review, the plugin that ships this one along with the rest of its 5 skills, 14 commands, 13 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

README.md
[![agentmods](https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/triage.svg)](https://agentmods.dev/commands/juanmhidalgo/claude-plugins/triage)
Your own site
<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/triage"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.01216
Opus 5 $0.00018 $0.00608
Sonnet 5 $0.00007 $0.00243
Haiku 4.5 $0.00004 $0.00122

Measured 5d ago against content hash f7a058441886, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

code-review/commands/triage.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

  • Repository: !git remote get-url origin
  • Current branch: !git branch --show-current
  • PR Number: $ARGUMENTS

Core Principle

AI feedback is NOT valid by default. Every comment must be verified.

External AI reviewers (Copilot, Gemini, etc.) lack full context. Their suggestions are starting points for investigation, not instructions to follow blindly.

Process

  1. Fetch PR feedback (optimized for low token usage):

    ${CLAUDE_PLUGIN_ROOT}/scripts/pr-triage-comments.sh OWNER REPO PR_NUMBER
    • Returns all comments (bots and humans) by default with ref_id for each comment
    • Automatically excludes resolved and outdated threads (via GraphQL)
    • Add 1500 true to show only bot comments
    • Add 1500 false true to include resolved threads

  2. For EACH comment, ask:

    • Is this technically correct for THIS codebase?
    • Does the AI have the full context?
    • Would this change break existing functionality?
    • Is there a reason the code is written this way?
    • Is this actually needed or just "best practice theater"?

  3. Classify after verification:

    VERIFIED VALID - Confirmed issues to fix

    • You checked the code and the issue is real
    • Security risk, bug, or genuine problem

    NEEDS INVESTIGATION - Can't determine without more context

    • Might be valid, might not
    • Requires checking tests, related code, or asking the author

    FALSE POSITIVE - Verified as incorrect or unnecessary

    • AI misunderstood the context
    • Suggestion would break existing behavior
    • YAGNI - feature isn't needed
    • Already handled elsewhere

Output Format

# PR #[number] Feedback Triage

## Stats
- Bot comments: X | Human comments: Y | Skipped: R resolved, O outdated
- Verified valid: Z | Needs investigation: W | False positives: V

## VERIFIED VALID
### [Issue title]
📍 `file.py:42` by @copilot | `ref_id: review_comment:123456789`
**Issue:** [description]
**Verified by:** [how you confirmed it's real]
**Priority:** CRITICAL | HIGH | MEDIUM

## NEEDS INVESTIGATION
### [Issue title]
📍 `file.py:15` by @gemini | `ref_id: review_comment:987654321`
**Suggestion:** [what they want]
**Unknown:** [what needs to be checked]
**To verify:** [specific action needed]

## FALSE POSITIVES
### [Issue title]
📍 `utils.py:88` by @copilot | `ref_id: review_comment:456789123`
**Suggestion:** [what they want]
**Why wrong:** [technical reason]
**Evidence:** [code/test that proves it's wrong]
**Dismiss reason:** YAGNI | Already handled | Context | Style | Breaking

Read the full file on GitHub · 137 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. 5d ago First seen · 137 lines · 36 tokens per session scan A f7a058441886

Subscribe to this mod's changes

triage is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 11d ago), licensed MIT. It adds 36 tokens to every session and 1,216 once invoked, about $0.0002 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.

AI-feedbackCode reviewcopilot-reviewfalse-positivesgemini-reviewpr-comments
Related

Other commands, from other repositories

pr-review

Run the PR review pipeline with raw arguments. Supports local PR docs, GitHub PR URLs, --quick, --triage-only, --auto, --history, --review-source, --repo-path, --review-doc, --worktree, --dry-run, and --live.

junyoung2015/pr-review-skill · 57 tokens

checklist

Generate a custom checklist for the current feature based on user requirements.

github/spec-kit · 13 tokens

clarify

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

github/spec-kit · 27 tokens

specify

Create or update the feature specification from a natural language feature description.

github/spec-kit · 13 tokens

analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

github/spec-kit · 26 tokens

converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

github/spec-kit · 35 tokens