A skill for moving issue-tracker tickets and outside pull requests through a set of review states, from initial classification to handoff or closure. An issue tracker is a system for reporting and managing project work; a pull request is a proposed code change for review.

It is for classifying bugs and improvements, requesting details, validating reports, preparing work for an agent or human, and marking items as not planned.

It turns incomplete or unclear reports into structured decisions and agent-ready briefs, while requiring conflicts or missing information to be surfaced.

triage — Skill for Claude Code and Codex by asherzj

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.

Any agent

npx skills add asherzj/ashers-agent-skills --skill triage

Clone the repo

git clone --depth 1 https://github.com/asherzj/ashers-agent-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/triage/github.svg)](https://agentmods.dev/skills/asherzj/ashers-agent-skills/triage)

Your own site

<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/triage"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/triage/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/triage"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,793 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 92% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.01793
Opus 5	$0.00026	$0.00897
Sonnet 5	$0.00011	$0.00359
Haiku 4.5	$0.00005	$0.00179

Measured 10d ago against content hash f5dd41671a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

Origin

This is a copy

92% identical to triage — 102 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

coding/triage/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue 分诊

把项目工单系统（issue tracker）上的 issue 纳入一个由分诊角色组成的小型状态机中流转。

如果本仓库把外部 pull request 也视为请求入口（见 issue-tracker 配置），分诊同样覆盖它们：PR 就是附带代码的 issue，使用相同的角色、相同的状态、同一台状态机，仅有少量差异在下文以「针对 PR」标出。裸的 #42 按 tracker 配置解析为 issue 或 PR。

分诊期间发布到工单系统的每条评论或 issue 都必须以下面的免责声明开头：

> *This was generated by AI during triage.*

参考文档

AGENT-BRIEF.md：如何撰写经久耐用的 agent 简报
OUT-OF-SCOPE.md：.out-of-scope/ 知识库如何运作

角色

两个类别角色：

bug：有东西坏了
enhancement：新功能或改进

五个状态角色：

needs-triage：需要维护者评估
needs-info：等待报告者补充信息
ready-for-agent：规格完整，可交给 AFK agent
ready-for-human：需要人工实现
wontfix：不予处理

针对 PR，同样的状态要结合所附代码来解读：ready-for-agent 表示已附上简报，应由 agent 在 diff 上走出下一步；ready-for-human 表示已可以由人来合并。

每个经过分诊的 issue 都应恰好携带一个类别角色和一个状态角色。如果状态角色冲突，先标记出来并询问维护者，再做其他任何事情。

这些是规范角色名。工单系统中实际使用的标签字符串可能不同。映射关系本应已经提供给你。如果没有，让用户运行 /setup-engineering-skills。

状态流转：未打标签的 issue 通常先进入 needs-triage；再从那里流转到 needs-info、ready-for-agent、ready-for-human 或 wontfix。报告者回复后，needs-info 回到 needs-triage。维护者可以随时推翻；遇到看起来异常的流转，先标记并询问，再继续。

调用

维护者调用 /triage，用自然语言描述想要什么。理解请求并行动。示例：

「把需要我关注的东西列出来」
「我们来看 #42」（issue 或 PR）
「把 #42 移到 ready-for-agent」
「有哪些是 agent 可以接手的？」

展示需要关注的内容

查询工单系统，按最旧优先呈现三类分组：

未打标签：从未分诊。
needs-triage：评估进行中。
needs-info 且自上次分诊记录后报告者有新活动：需要重新评估。

当 PR 在范围内时，把外部 PR 也纳入这些分组，并给每一行加上 [PR] 或 [issue] 标记。发现阶段只呈现外部 PR（tracker 配置定义了谁算外部），因此协作者进行中的 PR 不属于分诊工作。该过滤仅用于发现阶段；被明确点名的 PR 无论作者是谁都会被分诊。

展示数量和每个条目的一行摘要。由维护者来挑选。

对特定 issue 或 PR 进行分诊

收集上下文。 完整阅读该 issue 或 PR（正文、评论、标签、作者、日期；PR 还要读 diff）。解析已有的分诊记录，避免重复提问已解决的问题。使用项目的领域术语表探索代码库，并遵守该区域的 ADR（架构决策记录）。对代码库做两项检查：(a) 冗余性：按领域概念（而不只是请求的措辞）搜索所请求的行为是否已有实现，并报告你查过哪些地方。如果找到，这是一个「已实现」的 wontfix（第 5 步）。(b) 先前否决：阅读 .out-of-scope/*.md，把任何与本请求相似的记录呈现出来。
给出建议。 告诉维护者你推荐的类别和状态及理由，并附上与请求相关的代码库简要总结（包括是否已实现）。等待指示。
验证说法。 在进行任何拷问之前，先核实该说法是否站得住。bug 类要按报告者的步骤复现。PR 类要确认 diff 确实做到了它声称的事：把它 checkout 出来，运行相关测试或命令。报告结果：确认（附代码路径）、失败，或细节不足（强烈的 needs-info 信号）。经过确认的验证会让 agent 简报有力得多。

Read the full file on GitHub · 113 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 113 lines · 53 tokens per session scan A f5dd41671a9f

Subscribe to this mod's changes

triage is a skill published in the GitHub repository asherzj/ashers-agent-skills (2 stars, last pushed 13d ago), licensed MIT. It adds 53 tokens to every session and 1,793 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to triage, differing in 102 lines, and is treated as a copy.

Git and workflow Project management

mcore-split-pr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/skills · 25 tokens

shiplog

Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.

aeonfun/aeon · 46 tokens

llxprt-issue-workflow

Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the stepfun-37 smoke test), open code review (ocr), PR…

vybestack/llxprt-code · 87 tokens

triage