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/reviewgit clone --depth 1 https://github.com/Lee-W/maigoWrote 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.
[](https://agentmods.dev/commands/lee-w/maigo/review)<a href="https://agentmods.dev/commands/lee-w/maigo/review"><img src="https://agentmods.dev/badge/commands/lee-w/maigo/review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00041 | $0.04243 |
| Opus 5 | $0.00020 | $0.02122 |
| Sonnet 5 | $0.00008 | $0.00849 |
| Haiku 4.5 | $0.00004 | $0.00424 |
Grade A, and why
review 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.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maigo:review
對既有的變更做嚴格 review。跟 /maigo:go 不同，這裡沒有實作環節——
變更已經寫好了，要做的是判斷它對不對。
使用
/maigo:review <github-pr-url> # GitHub PR（需要 gh CLI）
/maigo:review <pr-1> <pr-2> ... # 多 PR 批次（空白或逗號分隔）
/maigo:review <branch-name> # 本地 branch（跟 main / 預設 base 比）
/maigo:review <commit-range> # 例：HEAD~3..HEAD 或 main..feature
不給參數 → 預設 HEAD 對 main（review 你目前 branch 的所有變更）。
要新增 / 刷新跨 session Work Board，直接用
/maigo:board。
模式（optional）：
/maigo:review --mode=design-preview <target> # 只看設計層，不查 evidence
/maigo:review --mode=compliance-only <target> # 只查 convention/safety/magic/TODO/bloat
/maigo:review --bilingual <target> # 雙語輸出（zh-TW 快結 + English detail）
/maigo:review <target> # 預設 full mode（9 項全跑）
Mode 對照表（checklist subset、Taki 是否跑）與 --bilingual 正交關係、mode 旗標的處理機制
（rubric 註解、Soyo 收到的 checklist subset、Taki skip 規則）見
skills/strict-review/references/review-modes.md。
多 PR 批次與狀態前置處理
/maigo:review 接受多個 PR 用空白或逗號分隔。orchestrator 自動排序後一次一個 review；每完成一個 PR 等使用者 go-ahead 才推進。完整排序規則、queue 表格式、merged/closed/draft 前置處理表、一次一個 PR 的 go-ahead 規則，見
skills/strict-review/references/review-batch-queue.md。多 PR 參數代表「現在要開始逐顆 review」；
若只是要把一批 PR 放進跨 session board，改用 /maigo:board <pr-1> <pr-2> ...。
長期跨 session 追一批 PR 時用
/maigo:board 的 Work Board
（.maigo/board.md）——queue 是 per-run，board 記得跨 session 的狀態轉移
（含「你回過但作者又推新東西」）。
雙語輸出
--bilingual 旗標或 repo-detect 自動觸發時（如 apache/airflow），最終 report 前面加一段 Taiwanese Mandarin 快結。觸發規則、zh-TW 行文規範見
skills/strict-review/references/review-modes.md「雙語輸出」；版型範本在
skills/strict-review/references/review-templates.md「雙語版」小節。
流程
1. 樂奈 (Raana) — 抓變更 + 周邊 context。「看完了。相關的在這三個檔案。」
先套 skills/pr-context-cache：跑 python3 "${CLAUDE_PLUGIN_ROOT:-.}/scripts/pr_context_cache.py" <source>——第一次 fetch 後 cache 到本次 review rubric 檔（stdout 的 rubric: 那行給的路徑）開頭的 <!-- pr-context-cache:start v1 --> 段，後續 re-review 同 source 且 diff sha 未變 → 直接還原，跳過 gh pr view / gh pr diff / gh pr checks 重抓。script 跑不起來，或 status: conflict（exit 3） → 依下面指令手動抓（不寫 cache）。
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.
- 4d ago First seen · 203 lines · 41 tokens per session scan A f61eca903523
review is a command published in the GitHub repository Lee-W/maigo (14 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 4,243 once invoked, about $0.0002 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.