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/quickgit 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 | $0.00055 | $0.01730 |
| Opus 5 | $0.00028 | $0.00865 |
| Sonnet 5 | $0.00011 | $0.00346 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
quick 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maigo:quick
「這個小東西改一下」級別的任務。跳過 Raana 探索 / Tomori 寫 plan 的 overhead， orchestrator 直接呼叫 Anon 動手，做完跑 Soyo 輕量 review（9 項 → 4 項）。 Test 不顯式喊 Taki——stop hook 在任務完成前自動跑測試兜底。
使用
/maigo:quick <小任務描述>
例：
/maigo:quick 把 README 第三段的拼字 "occured" 改成 "occurred"
/maigo:quick 在 auth.py:42 加 type hint
邊界（trust user）
使用者說「這是 quick-fix」就是 quick-fix——orchestrator 不自動 gate（不偵測 LoC、不偵測 file 數）。
若使用者描述聽起來像大改動（多檔案、跨 module、看起來會牽動行為），orchestrator 在啟動前一次提醒：「這個看起來不像 quick-fix，要改用 /maigo:go 嗎？」使用者回「不用、就 quick」→ 照走 quick 流程，不再追問。
流程
- 愛音 (Anon) — 直接動手實作（無 Raana 探索、無 Tomori plan）。「嗯！先做 Step 1！」
- Anon 自己看周邊 1-2 個檔抓慣例，不做大範圍探索
- 不寫 plan.md
- 爽世 (Soyo) — 輕量 review，只跑 9 項中的 4 項。「這裡這樣寫，應該不對。」
- Stop hook 自動跑 test — 不顯式呼叫 Taki；成功訊息會附本 session 的一行 token usage
- Orchestrator — Stop hook 綠後，若還有未 commit 的本次變更，依
skills/commit-message草擬一段 commit message 附在 final summary。格式照該 skill 的偵測跑，不預設 CC——target repo 的成文慣例優先（例：apache/airflow 明禁 CC 前綴並有 commit-msg hook 擋）。不自動跑 git commit。
Soyo 輕量 checklist（9 項 → 4 項）
| 項 | 跑？ |
|---|---|
| 1. acceptance match | ✅ |
| 2. evidence per function | ❌ skip（stop hook 跑 test 兜底） |
| 3. edge case coverage | ❌ skip |
| 4. convention conformance | ✅ |
| 5. no unsafe pattern | ✅ |
| 6. no unexplained magic | ❌ skip |
| 7. no TODO evasion | ✅ |
| 8. no defensive bloat | ❌ skip |
| 9. no completeness theatre | ❌ skip |
合計 4 項：1 / 4 / 5 / 7。
orchestrator 啟動 Soyo 時 prompt 必須明示「mode=quick」與上述 subset。Soyo 輸出 checklist 表時 subset 內項照常 [x] / [ ]，subset 外項標 [—] 附 reason skipped by mode=quick。
詳細「為什麼這 4 項」與「為什麼略掉那 5 項」見
skills/strict-review/SKILL.md
的 "Adapting per context" 表。
失敗處理
Soyo 擋下（NEEDS_CHANGES / BLOCKED）
跟 /maigo:go 同——把 must-fix 完整給 Anon、修完重 review、2 次同條才停下找使用者。
詳見 skills/failure-handling。
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 · 101 lines · 55 tokens per session scan A 1e25cf108cbc
quick is a command published in the GitHub repository Lee-W/maigo (14 stars, last pushed 8d ago), licensed MIT. It adds 55 tokens to every session and 1,730 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.