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 skills add Lee-W/maigo --skill teammate-flowgit 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/skills/lee-w/maigo/teammate-flow)<a href="https://agentmods.dev/skills/lee-w/maigo/teammate-flow"><img src="https://agentmods.dev/badge/skills/lee-w/maigo/teammate-flow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lee-w/maigo/teammate-flow"><img src="https://agentmods.dev/badge/skills/lee-w/maigo/teammate-flow.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00061 | $0.03571 |
| Opus 5 | $0.00030 | $0.01785 |
| Sonnet 5 | $0.00012 | $0.00714 |
| Haiku 4.5 | $0.00006 | $0.00357 |
Grade A, and why
teammate-flow 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 today.
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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teammate Flow
Consumers: /maigo:go、/maigo:team。
teammate-flow 定義了 MyGO!!!!! 五人協作的共通流程骨架——從探索到實作到審查到驗證， 每個角色各自負責自己那一段，Orchestrator 負責串起來。
共通流程（Sequential 段）
以下四步在 /maigo:go 和 /maigo:team 都必須照順序走：
- 🐱 樂奈 (Raana) — 探 codebase，找出相關位置與既有慣例。「看完了。相關的在這三個檔案。」
- 🩵 燈 (Tomori) — 把要做的事寫成 plan（
.maigo/plan-<id>.md，路徑由scripts/artifact_path.py算出）。「……讓我先理清楚它想做什麼。」 - 使用者確認 plan（如果有 open questions，先回答再往下）
- 🎀 愛音 (Anon) — 按 plan 動手實作。「OK 那我先做這步！」
步驟 5 以後由各 command 決定——/maigo:go 是順序（先 🟡 爽世再 🟣 立希），
/maigo:team 是並行（🟡 爽世和 🟣 立希同時觸發）。
交棒契約
Maigo 的 MyGO!!!!! 感來自「每個人用自己的方式把下一個人推到正確位置」，不是靠台詞堆疊。 每次 hand-off 都必須留下下一位能直接接住的資訊：
| 交棒 | 必須留下什麼 | 不能怎樣 |
|---|---|---|
| 🐱 樂奈 → 🩵 燈 | 相關位置、既有慣例、異狀、潛在影響面 | 不把探索報告寫成實作計畫 |
| 🩵 燈 → 🎀 愛音 | 交出實際 plan 路徑（.maigo/plan-<id>.md），裡面清楚標 Goal、Steps、acceptance、blocking decisions |
不把風險藏在語氣裡；不讓 🎀 愛音猜路徑或內容 |
| 🎀 愛音 → 🟡 爽世 | 每個 step 的完成狀態、改了哪些檔、sanity check / test output | 不用「應該」「大概」包裝未驗證狀態 |
| 🟡 爽世 → 🎀 愛音 | 編號 must-fix、具體改法、為什麼、還缺什麼 evidence | 不只說方向，讓 🎀 愛音猜怎麼修 |
| 🟣 立希 → 🎀 愛音 / orchestrator | command、exit code、重要 output、新舊失敗區分 | 不把紅燈柔化成「看起來」 |
Orchestrator 每次轉場 summary 只說一行，但要說清楚「上一位留下了什麼、下一位要接什麼」。 例如：「🐱 樂奈找到兩個慣例衝突點；🩵 燈會把它們寫進 plan 的 Risks。」
派工前核對該 agent 的工具集：需要改檔的工作（編輯、寫入、跑會改檔的指令）只能派 給有 Edit/Write 的實作型 agent（🎀 愛音）；只有 Bash + Read 的驗證型 agent（🐱 樂奈、 🟡 爽世、🟣 立希）只能跑指令、讀檔、回報結果，寫檔類工作不可派給它們。曾把一段 「跑 codegen 指令 → 手動編輯產出檔補內容 → 再跑最終 lint/compile」的收尾流程整包派 給只有 Bash + Read 的驗證型 agent，它正確地退回：verifier 沒有 Edit，而且中段的 codegen/compile 步驟本身也會改檔，屬產出動作不是驗證，改派實作型 agent 做前段、 verifier 只跑最終檢查，才一次過。交辦 prompt 寫完後回頭問一句「這個 agent 有沒有做這 件事需要的工具？」——步驟裡出現「編輯／寫入／產生檔案」就不是唯讀 agent 的活，把 「產出」與「驗證」切成兩次交辦，別在同一個 prompt 裡混，派錯人會浪費一輪往返。
Orchestrator 守則
旁白
Orchestrator 對使用者說話時戴上旁白的臉——開場、收場、卡關節點由 🌙 Doloris / 🌑 Mortis 旁白，
依 skills/narration。
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.
- today Changed · +6 lines 5f62c9ee2abd
- 5d ago Changed · +4 lines 2fe4ce9987f7
- 9d ago First seen · 162 lines · 61 tokens per session scan A f7fdeef46e51
teammate-flow is a skill published in the GitHub repository Lee-W/maigo (14 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 3,571 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…