triage-issues

triage-issues is a command for Claude Code from damusix/atomic-claude. It costs 0 tokens per session (1,388 once invoked), scanned A, original, MIT.

A command for reviewing open GitHub issues and proposing labels or follow-up actions based on their status and age.

In plain words
What is it for?
It helps suggest issue labels, draft reporter reminders, and propose closing stale issues after a 14-day nudge and another 14 days of silence.
Why use it?
It separates automatic staleness checks from human decisions, so issues are not changed without approval.

Command for Claude Code

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/damusix/atomic-claude/triage-issues
Clone the repo
git clone --depth 1 https://github.com/damusix/atomic-claude

Made for: Claude Code.

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-issues

README.md
[![agentmods](https://agentmods.dev/badge/commands/damusix/atomic-claude/triage-issues.svg)](https://agentmods.dev/commands/damusix/atomic-claude/triage-issues)
Your own site
<a href="https://agentmods.dev/commands/damusix/atomic-claude/triage-issues"><img src="https://agentmods.dev/badge/commands/damusix/atomic-claude/triage-issues.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,388 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 $0.00000 $0.01388
Opus 5 $0.00000 $0.00694
Sonnet 5 $0.00000 $0.00278
Haiku 4.5 $0.00000 $0.00139

Measured 4d ago against content hash b77360fd6c6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

triage-issues 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 4d 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-issues.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You triage this repo's open GitHub issues. The deterministic half — which issues are stale, and in what way — is computed by make triage-scan (script: scripts/triage-scan.sh); your job is the judgment half: suggest labels, draft the nudge/close comments, propose a plan, and execute only what the user approves. Nothing is applied without an explicit OK — labels, nudges, and closes are all suggestions until confirmed.

Prereqs

  • command -v gh — if missing: tell the user to install it (brew install gh / https://cli.github.com/) then gh auth login. Stop.
  • gh auth status — if unauthed: tell the user gh auth login. Stop.
  • gh repo view --json nameWithOwner,hasIssuesEnabled — if issues are disabled, stop.

Staleness model (the contract)

An issue is on the close track only when it is waiting on the reporter: the last comment is from a maintainer (authorAssociation ∈ OWNER / MEMBER / COLLABORATOR, and not the reporter), and the reporter has gone quiet. Two stages, 14 days each:

maintainer replied last
        │  reporter silent 14d
        ▼
   NUDGE  ── @reporter comment ("reply within 2 weeks or this closes") + label `stale`
        │  still silent 14d more  (≈ 1 month total)
        ▼
   CLOSE  ── courtesy comment + close (reason: not planned). `stale` label stays.

If the reporter replies at any point, the ball is back with the maintainers: no nudge, no close, and if stale was set, propose removing it (unstale). The nudge comment carries a hidden marker <!-- atomic-triage:nudge --> so a later run detects the nudge deterministically instead of guessing.

Workflow

Step 1 — Classify staleness (deterministic — code, not judgment)

Run the scanner. It enumerates open issues and returns each one's staleness action purely from comment authorship and timestamps — do not reimplement this in the prompt or eyeball dates yourself:

make triage-scan

(From the repo root. Scope to specific issues with make triage-scan ISSUES="43 50".) It prints a JSON array; an empty [] means no open issues — report no open issues. and stop. The deterministic logic lives in scripts/triage-scan.sh; if you need to change the staleness rules, edit that script, not this command.

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 0 tokens per session scan A b77360fd6c6e

Subscribe to this mod's changes

triage-issues is a command published in the GitHub repository damusix/atomic-claude (84 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,388 tokens. 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.