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/retrogit 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 | $0.00057 | $0.01988 |
| Opus 5 | $0.00028 | $0.00994 |
| Sonnet 5 | $0.00011 | $0.00398 |
| Haiku 4.5 | $0.00006 | $0.00199 |
Grade A, and why
retro 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maigo:retro
Session 快結束時，那些「使用者剛指出的偏好」、「約好的慣例」、「學到的教訓」 常常就這樣消失在下一個 prompt 裡。retro 命令把這些抓回來，逐筆問使用者要不要存。
Orchestrator 親自跑，不開新 agent。
使用
/maigo:retro
（無參數）
流程
路徑 A — 同 session（orchestrator 有 conversation context）
-
orchestrator 從 session 對話 context 撈出 N 個候選 retro 點（建議 ≤ 5；多於 5 取最有信號的前 5）。
候選來源：
- 使用者顯式講的偏好 / 反饋（例：「以後 review 別寫這麼長」）
- session 中浮現的約定（例：commit message 風格、test naming）
- 學到的事 / 踩過的雷（例：「這個 lib 在 macOS 行為跟 linux 不同」）
-
逐筆 propose（一次一筆，不要一口氣全列）：
- 印一段「候選 #i / N」摘要：原始 context 引用 + orchestrator 推斷的 type / name / description。
- 先判斷目的地（印在摘要裡）：
個人 memory：使用者的偏好、workflow 習慣、跨 session 記憶的事實maigo 文件缺口：描述的是「maigo 如何工作 / maigo 的某個慣例 / 實作規範」 → 應進 maigo 的 source file（例：docs/reference/memory.md、CONTRIBUTING.md），而不是寫進個人 memory
- 依目的地調整問法：
- 個人 memory → AskUserQuestion「要存這筆嗎？」選項：
存/修改/跳過/結束 retro - maigo 文件缺口 → AskUserQuestion「要更新 maigo 文件嗎？」選項：
更新 maigo 文件（orchestrator 直接 Edit 指定 source file）/改存 personal memory/跳過/結束 retro
- 個人 memory → AskUserQuestion「要存這筆嗎？」選項：
-
使用者選「存」或「修改」→ reuse
/maigo:remember流程步驟 5（AskUserQuestion 確認三題） 與步驟 6（寫檔 + 更新 MEMORY.md + rollback）。 觸發點：把 retro 候選當作/maigo:remember的 input 自然語言， 從步驟 2（推斷 type）開始走，一路走完步驟 6。使用者選「更新 maigo 文件」→ orchestrator 直接 Edit 目標 source file，完成後印「已更新
<file>」，不寫 memory。 -
該筆寫完 → 回到步驟 2 的下一筆候選。
-
所有候選跑完，或使用者「結束 retro」→ 印 summary：「本次 retro 存了 K 筆：
<name1>（<type1>）、<name2>（<type2>）...」。 -
🌑 Mortis 結算（一句）
Summary 印完後，再加一行——把本次 retro 的核心壓縮成一句。
硬性字數限：1 句。
範例：
🌑 Mortis：本次 retro 的核心是「Soyo review 要更精簡」。守則：
- 溫柔包裹克制——短句；不刻意冷酷；結尾常是靜靜的收束
- 不感嘆號、不鼓勵語
- 候選為 0 筆 → 跳過結算（沒存任何東西的 retro 不需要結算）
路徑 B — 跨 session fallback（orchestrator 無 conversation context）
-
orchestrator 判斷：session 對話 context 為空 / 不存在 / 無有意義 turn → 進入 fallback。
-
AskUserQuestion 問使用者：「上次的 session 沒在這條對話裡。剛剛做了什麼任務？ 有沒有想記下來的偏好 / 約定 / 學到的事？」
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.
- 3d ago First seen · 113 lines · 57 tokens per session scan A 3266ede6cff4
retro is a command published in the GitHub repository Lee-W/maigo (14 stars, last pushed 9d ago), licensed MIT. It adds 57 tokens to every session and 1,988 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.