triage

triage is a command for Claude Code from mjmorales/claude-prove. It costs 16 tokens per session (1,067 once invoked), scanned A, original, MIT.

A command for maintainers to review and organize open GitHub issues in the prove plugin repository. Triage means examining reports, adding labels, deciding their priority, and planning fixes.

In plain words
What is it for?
Use it to inspect one issue, issues with a chosen label, or all open issues, then prepare an overview with titles, labels, age, authors, and planned follow-up.
Why use it?
It gathers issue details in one review so maintainers can see what needs attention. It also checks that the GitHub command-line tool is authenticated before accessing the repository.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the prove plugin — 25 skills, 30 commands, 21 agents, 5 hooks, 1 MCP server shipped together

Good fit Use it to inspect one issue, issues with a chosen label, or all open issues, then prepare an overview with titles, labels, age, authors, and planned follow-up.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mjmorales/claude-prove/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/mjmorales/claude-prove

Made for: Claude Code.

Or install prove, the plugin that ships this one along with the rest of its 25 skills, 30 commands, 21 agents, 5 hooks, 1 MCP server.

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/mjmorales/claude-prove/triage.svg)](https://agentmods.dev/commands/mjmorales/claude-prove/triage)
Your own site
<a href="https://agentmods.dev/commands/mjmorales/claude-prove/triage"><img src="https://agentmods.dev/badge/commands/mjmorales/claude-prove/triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,067 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 $0.00016 $0.01067
Opus 5 $0.00008 $0.00534
Sonnet 5 $0.00003 $0.00213
Haiku 4.5 $0.00002 $0.00107

Measured 7d ago against content hash e7a45d2947b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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.

.claude/commands/triage.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage Issues: $ARGUMENTS

Review and triage open issues on the prove plugin repository. This is a project-local command for maintainers — it does not ship with the plugin.

Instructions

Step 0: Guard — verify context

  1. Verify gh auth status succeeds. If not, guide the user to authenticate.
  2. This command is for plugin maintainers. All operations target mjmorales/claude-prove via --repo flag; no local repo check needed.

Step 1: Fetch issues

If $ARGUMENTS is a number, fetch that single issue:

gh issue view $ARGUMENTS --repo mjmorales/claude-prove --json number,title,body,labels,createdAt,author,comments

If $ARGUMENTS is a label (e.g., "bug", "enhancement"), filter:

gh issue list --repo mjmorales/claude-prove --label "$ARGUMENTS" --state open --json number,title,labels,createdAt,author --limit 25

Otherwise, fetch all open issues:

gh issue list --repo mjmorales/claude-prove --state open --json number,title,labels,createdAt,author --limit 25

Step 2: Present overview

Display issues in a table:

Open Issues (N total)

#  | Title                              | Labels       | Age  | Author
---|-------------------------------------|-------------|------|--------
12 | /prove:update runs in plugin dir   | bug         | 2d   | user1
11 | Add coding standards reference     | enhancement | 5d   | user2

Step 3: Triage each issue

For each issue (or the single requested issue), read the full body and comments, then assess:

  1. Assess clarity: Is the issue description clear enough to act on? Are reproduction steps or acceptance criteria present?
  2. Classify severity:
    • critical — blocks core functionality (init, update, orchestrator)
    • high — breaks a specific command/skill
    • medium — incorrect behavior with workaround
    • low — cosmetic, docs, nice-to-have
  3. Security check: If the issue involves credential exposure, injection, or unauthorized access, apply the security label. Do NOT discuss reproduction details in public comments.
  4. Identify affected components: Which commands, skills, agents, or tools are involved? Use directory names as component labels (e.g., commands, agents, packages/cli/src/topics/cafi).
  5. Estimate scope: quick fix (< 30 min), medium task, or needs planning.
  6. Check for duplicates: Search existing open issues for similar reports before accepting.

Read the full file on GitHub · 118 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 · 118 lines · 16 tokens per session scan A e7a45d2947b0

Subscribe to this mod's changes

triage is a command published in the GitHub repository mjmorales/claude-prove (2 stars, last pushed 28d ago), licensed MIT. It adds 16 tokens to every session and 1,067 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.