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/teamgit 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 | $0.00035 | $0.00940 |
| Opus 5 | $0.00017 | $0.00470 |
| Sonnet 5 | $0.00007 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
team 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.
What it actually says
/maigo:team
跟 /maigo:go 同一條工作流，差別在最後審查 + 驗證階段並行。
🟡 爽世跟 🟣 立希互不依賴（爽世讀 diff、立希跑 command），可同時動。
使用
/maigo:team <任務描述>
/maigo:team --force-sequential <任務描述> # 退回 /maigo:go 順序版
流程
共通 sequential 段（🐱 樂奈 → 🩵 燈 → 使用者確認 → 🎀 愛音）依
skills/teammate-flow。
Parallel（同時觸發兩個 Task）
5a. 🟡 爽世 (Soyo) — review 變更（依 skills/strict-review）。「你說的『應該』，是有跑過、還是只是『應該』？」
5b. 🟣 立希 (Taki) — 跑 test / lint / type check。「跑出來爆了，看 line 42。」
- 合流——兩邊都回來後一起處理。
Orchestrator 守則（旁白、不自實作、不跳關、commit message draft、fence tracking）依
skills/teammate-flow，
並行專屬追加規則：
- 真的並行：用一條 message 內兩個 Task tool call 觸發 🟡 爽世和 🟣 立希
- 不要假裝並行（先爽世完才呼叫立希不算）
- 合流時把兩份輸出分開呈現給使用者，不要混在一起
Trade-off
| 模式 | Wall clock | 「白做工」風險 |
|---|---|---|
/maigo:go 順序 |
100% | 0（爽世擋下就不跑 test） |
/maigo:team 並行 |
~60-70% | 中（爽世擋下時，立希已經跑完了） |
多數情況淨值正——大部分變更會通過 review，並行省的時間 > 偶爾白跑 test 的成本。
但若是高風險變更（重構、scope 大）建議用 /maigo:go 避免白做工。
合流邏輯
| 爽世 | 立希 | 處理 |
|---|---|---|
| APPROVED | PASS | 完成。給使用者 summary |
| APPROVED | FAIL | 回到愛音修 test failure（review 通過不重跑） |
| NEEDS_CHANGES / BLOCKED | PASS | 回到愛音修 must-fix，修完要重跑 Soyo + Taki（不能假設 test 還會綠） |
| NEEDS_CHANGES / BLOCKED | FAIL | 回到愛音兩邊一起修，重跑 Soyo + Taki |
失敗處理
依 skills/failure-handling——一樣 2 次同條卡關才停下找使用者。
--force-sequential
使用者明確要求順序版時用。等於把 step 5a/5b 改回 5 → 6（先 🟡 爽世再 🟣 立希）。 適用場景：
- 變更高風險，不想白跑 test
- Debug 並行流程本身（懷疑兩邊互相影響）
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 · 67 lines · 35 tokens per session scan A 65651e5cf959
team is a command published in the GitHub repository Lee-W/maigo (14 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 940 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.