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.
npx agentmods add commands/lee-w/maigo/address-commentsgit clone --depth 1 https://github.com/Lee-W/maigoWhat 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 | $0.00053 | $0.06301 |
| Opus 5 | $0.00026 | $0.03150 |
| Sonnet 5 | $0.00011 | $0.01260 |
| Haiku 4.5 | $0.00005 | $0.00630 |
Grade A, and why
address-comments 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maigo:address-comments
把 PR 上的 review 意見一條一條收掉。
讀當前 branch 對應的 PR、抓 GitHub 上的 comments、列出來讓你挑哪些要處理， 擬一份「哪條意見走哪條 workflow」的路由計畫給你確認，確認後逐項實作。
Orchestrator 親自跑步驟 1–4（不開新 agent）；步驟 5 才把每個 work item
交給 /maigo:quick /
/maigo:go /
/maigo:team 的完整流程。
使用
/maigo:address-comments
不收參數——一律針對當前 branch 對應的 PR。當前 branch 讀不到 PR 就擋下（見步驟 1）。
流程
orchestrator 親自跑步驟 1–4：
1. Pre-flight gate — 讀不到 PR 直接擋下
依序檢查，任一項不過就印錯誤並以非 0 退出，不往下走：
| 檢查 | 命令 | 不過時的訊息 |
|---|---|---|
| 在 git repo 內 | git rev-parse --is-inside-work-tree |
「不在 git repo 內，address-comments 需要一個有 PR 的 branch。」 |
gh 可用且已登入 |
gh auth status |
「gh CLI 未安裝或未登入。先 gh auth login。」 |
| 當前 branch 有對應 PR | gh pr view --json number,title,url,state,headRefName,baseRefName,isDraft |
「當前 branch <branch> 沒有對應的 PR。address-comments 需要一個 PR 才能跑——先開 PR（可用 /maigo:describe-pr 產草稿）。」 |
gh pr view 不帶位置參數時會自動解析當前 branch 的 PR；exit 非 0 或回
「no pull requests found」即視為讀不到 PR，擋下。
過關後記下 number / title / url / headRefName / baseRefName，往下走。
PR 若是 MERGED / CLOSED 狀態——不擋，但在列表時標出狀態提醒使用者。
2. 抓 GitHub 上的 comments
把三種意見來源都抓齊（orchestrator 直接跑 gh）：inline review threads（含 isResolved）、
review 摘要、conversation comments。三段查詢指令逐字稿（GraphQL query、<owner>/<repo>
取法、--json reviews 缺 url 的補丁）見
skills/github-reply-draft/references/comment-fetch-and-triage.md「抓取」。
抓不到任何一種就標 n/a，不要因為單一來源空了就中止。
三種來源都要記下各自的 url，供步驟 4 triage 檔格式填寫與步驟 6 Finale 回覆草稿使用：
inline comment 的 url 已由上方 Inline review threads 的 GraphQL query 傳回；review 的 url 由上述補充 GraphQL query 取得；conversation comment 的 url 由 gh pr view --json comments 直接提供。
若全部來源加起來沒有任何意見 → 印「PR #<number> 目前沒有任何 review 意見，沒東西可處理。」並正常結束（exit 0）——這不是錯誤。
驗證現狀，不要照抄意見原文當 TODO：抓齊三種來源後，逐條對照該 comment 指向的 file:line
在目前 HEAD 的實際內容——force-push / 後續 fixup 可能已經部分或全部處理掉某條意見，thread
標 unresolved 不代表現狀仍然如此。每條判進三桶之一：已處理（現狀已符合意見字面）、
部分處理（原本較大的訴求只剩一部分還沒做）、仍有效。「已處理」只確認字面訴求，不代表行為
正確——若現狀讓人懷疑行為本身有問題（即使字面訴求技術上已滿足），照實列出讓使用者選要不要
順便處理，不要自動歸類成「已處理」了事。若某條意見是 GitHub suggestion block，把建議文字對照
「現在錨定那一行的實際內容」自己 diff 一次——不要從建議的最終狀態反推意圖：同一段最終文字
可能對應完全不同的改動（例如表面像 rename，實際 diff 是拿掉一個沒用到的參數）。
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.
- 2d ago First seen · 257 lines · 53 tokens per session scan A bc8ae50cb440
address-comments is a command published in the GitHub repository Lee-W/maigo (14 stars, last pushed 9d ago), licensed MIT. It adds 53 tokens to every session and 6,301 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.