issue-triage

issue-triage is a skill for Claude Code, Codex from New1Direction/korgex. It costs 18 tokens per session (335 once invoked), scanned A, original, MIT.

A process for turning a vague bug report into a clear issue that another developer can reproduce and fix. It records the steps, expected and actual results, environment, error output, type, and priority.

In plain words
What is it for?
It helps reproduce bugs, identify duplicates, distinguish bugs from requests or questions, prioritize impact, and turn the reproduction into a fix check or regression test.
Why use it?
It prevents developers from guessing at problems that lack reproduction steps, versions, or a clear definition of correct behaviour.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/new1direction/korgex/issue-triage
Any agent
npx skills add New1Direction/korgex --skill issue-triage
Clone the repo
git clone --depth 1 https://github.com/New1Direction/korgex

Made for: Claude Code, Codex.

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 issue-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/new1direction/korgex/issue-triage.svg)](https://agentmods.dev/skills/new1direction/korgex/issue-triage)
Your own site
<a href="https://agentmods.dev/skills/new1direction/korgex/issue-triage"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/issue-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 335 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 $0.00018 $0.00335
Opus 5 $0.00009 $0.00168
Sonnet 5 $0.00004 $0.00067
Haiku 4.5 $0.00002 $0.00034

Measured 6d ago against content hash 78ec174f5513, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

issue-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 6d 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.

src/skills_builtin/issue-triage/SKILL.md · 27 lines

What it actually says

A good issue is half the fix. Whether filing or triaging, drive toward a crisp, reproducible statement of the problem.

  1. Reproduce or get repro steps. The most valuable thing in any bug report is a minimal, deterministic way to trigger it. If you can't reproduce it, say what you tried and what info is still needed — don't guess at a fix.
  2. Capture the essentials: exact steps, expected vs actual, environment (version, OS, config), and the actual error/output (not a paraphrase).
  3. Classify: is it a bug, a feature request, a question, or a duplicate? Search existing issues first — link duplicates instead of forking the discussion.
  4. Prioritize by impact × frequency. Severity (data loss / crash / cosmetic) and how many users hit it. Be honest; not everything is P0.
  5. Make it actionable. A triaged issue should tell the implementer where to look and how to know it's fixed (the repro becomes the acceptance test).
  6. For a fix you implement, reference the issue, and add a regression test from its repro so it can't silently come back (see test-driven-development).

Red flag: "it's broken" with no repro, version, or expected behaviour — that's not yet an issue, it's a prompt to gather more.

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. 6d ago First seen · 27 lines · 18 tokens per session scan A 78ec174f5513

Subscribe to this mod's changes

issue-triage is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 335 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.