triage-issue

triage-issue is a command for coding agents from Lee-W/maigo. It costs 64 tokens per session (2,916 once invoked), scanned A, original, MIT.

A command for reviewing GitHub issues from a maintainer's perspective, meaning deciding how each incoming report should be handled.

In plain words
What is it for?
Use it to inspect issue details and comments in batches, identify missing information or duplicates, and prepare GitHub CLI commands for follow-up.
Why use it?
It sorts multiple issues and gives each one a READY, NEEDSINFO, DUP, or CLOSE verdict without changing GitHub automatically.

Command

Part of the maigo plugin — 24 skills, 15 commands, 5 agents, 4 hooks shipped together

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/lee-w/maigo/triage-issue
Clone the repo
git clone --depth 1 https://github.com/Lee-W/maigo

Or install maigo, the plugin that ships this one along with the rest of its 24 skills, 15 commands, 5 agents, 4 hooks.

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-issue

README.md
[![agentmods](https://agentmods.dev/badge/commands/lee-w/maigo/triage-issue.svg)](https://agentmods.dev/commands/lee-w/maigo/triage-issue)
Your own site
<a href="https://agentmods.dev/commands/lee-w/maigo/triage-issue"><img src="https://agentmods.dev/badge/commands/lee-w/maigo/triage-issue.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,916 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 $0.00064 $0.02916
Opus 5 $0.00032 $0.01458
Sonnet 5 $0.00013 $0.00583
Haiku 4.5 $0.00006 $0.00292

Measured 4d ago against content hash 4dd11fd6796e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

triage-issue 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.

commands/triage-issue.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/maigo:triage-issue

Maintainer 視角的 issue triage——大批 inbound issue 一輪掃完,告訴你哪些 ready / 哪些缺資訊 / 哪些是 dup / 哪些該 close。 跟 /maigo:review 的結構平行——只是對象從 PR diff 換成 issue body + comments,所以立希不上場(issue 沒 diff 可跑、沒 test 可驗)。

使用

/maigo:triage-issue <issue-1> <issue-2> ...   # 多 issue 批次(空白或逗號分隔)
/maigo:triage-issue <github-issue-url> ...    # 接受 URL 形式

不給參數 → 印錯誤訊息「/maigo:triage-issue 需要至少一條 issue 參數」並結束。 v1 不支援 --label needs-triage 之類自動拉清單的旗標——使用者顯式給 issue list。

流程

1. 樂奈 (Raana) — 抓 metadata + 排隊

第一輪 🐱 樂奈以 parallel 方式抓每條 issue 的 lightweight metadata:

gh issue view <N> --repo <repo> --json number,title,author,createdAt,state,labels,comments,body

排序規則(v1 簡單版):

  1. Bucket A — closed / merged → 自動 skip,標 ⏭️ already closed
  2. Bucket B — open → 按 number 升序(舊的先處理)

未來若有需要再加 --quick-win-first 旗標把疑似 dup / 缺 template 的擺前面。

排好後印 queue 表給使用者:

## 排序後 triage queue(共 N 條)

| 順序 | Issue | Title | Author | Age | Labels |
|---|---|---|---|---|---|
| 1 | #X | … | @… | 3d | (none) |
| 2 | #Y | … | @… | 7d | bug |
| — | #W | … | — | — | ⏭️ skipped (closed) |

從 **#X** 開始。

第一條 issue 不必等 go-ahead——使用者送多 issue 進來就授權批次啟動。「等 go-ahead」規則只在 issue 與 issue 之間。

2. 每條 issue — 樂奈 fetch full + 找 dup

🐱 樂奈進場第二輪,這條 issue 抓完整內容:

gh issue view <N> --comments                                           # body + comments
gh api repos/<owner>/<repo>/issues/<N>/timeline --paginate              # linked PRs / cross-references

並 grep repo 找潛在 dup:

  • 從 issue title / body 抽 2-3 個關鍵字
  • gh search issues --repo <owner>/<repo> "<keyword>" --state all 找近似 issue
  • 限定回前 5 條最近的,避免噪音

回報:full body 摘要 + comments 摘要 + linked refs + 疑似 dup #<N> 清單(沒有則「(none found)」)。

3. 燈 (Tomori) — 寫 triage rubric

呼叫 scripts/artifact_path.py triage-rubric --url <issue url> --topic "Triage rubric: <issue title> (#<N>)" 取得路徑(目錄不存在請先 mkdir -p .maigo)。每條 issue 各自一份——同一批多條 issue 不再共用同一個檔案,爽世讀完即可,不需要長期保留(歸屬規則見 artifact-ownership)。

Read the full file on GitHub · 172 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 · 172 lines · 64 tokens per session scan A 4dd11fd6796e

Subscribe to this mod's changes

triage-issue is a command published in the GitHub repository Lee-W/maigo (14 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 2,916 once invoked, about $0.0003 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 2026-08-30.