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/remembergit 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 | $0.00061 | $0.01490 |
| Opus 5 | $0.00030 | $0.00745 |
| Sonnet 5 | $0.00012 | $0.00298 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
remember 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maigo:remember
把「該被記得的事」從使用者腦袋移到共用的記憶層。
Orchestrator 親自跑，不開新 agent。
使用
/maigo:remember <自然語言描述>
例：
/maigo:remember 以後 review 要記得我偏好 integration test 而非 mock
/maigo:remember 我在所有專案的 commit message 都用 Conventional Commits
/maigo:remember 上次 Soyo 的 review 說明太長，希望更精簡
流程
Orchestrator 親自執行以下步驟（不 delegate 給 Tomori 或 Anon）：
-
讀 input 自然語言
-
推斷
type（user/feedback/project/reference之一）啟發式判斷：
輸入特徵 推斷 type 含「偏好」「習慣」「慣例」「以後都」 project含「上次」「之前」「那次」「有人說」 feedback含 URL 或「文件」「參考」「spec」 reference含「我是」「我叫」「稱呼我」「語言」 user不確定 → 在 AskUserQuestion 列最可能的兩個，讓使用者選。
-
生成 candidate
name（短、可讀；例：「Integration test 偏好」） -
生成 candidate
slug（lowercase + hyphen + ASCII only；例：integration-test-preference）- 確認
~/.config/maigo/memory/<slug>.md不存在 - 若已存在 → 見下方「同 slug 已存在」處理
- 確認
-
AskUserQuestion：
-
共同三題（所有 type）：
- 確認或修改 type（列出推斷的 type 及理由）
- 確認或修改 name
- 要不要編輯 body？（預設 body = 從 input 提煉的一句話 + 原 input 當補充；使用者可直接接受或提供新版）
-
第四題（僅
type: project）：- 要 tag triggered skills 嗎？（optional，list，例：
airflow-aware、commitizen-aware）。預設空，直接 Enter 略過 - 非空 → frontmatter 加
triggers: [...]；空 → 不加triggers欄位 - 此欄位只對
type: project有效；其他 type 不詢問、不寫入
- 要 tag triggered skills 嗎？（optional，list，例：
-
-
使用者確認後：
a.
mkdir -p ~/.config/maigo/memory/b. 寫
~/.config/maigo/memory/<slug>.md：（
triggers行只在type: project且使用者第四題回非空時加進 frontmatter）--- name: <確認的 name> description: <一句話摘要> type: <確認的 type> --- <body 內容>若
type: project且使用者填了 triggers，在type:行後加一行：triggers: [<skill-name>, ...]c. 更新
~/.config/maigo/memory/MEMORY.md：- 若不存在 → 建立，含一行說明 + 第一個 entry
- 若已存在 → append 一行
- [<name>](<slug>.md) — <description>
d. 回報使用者：寫了哪兩個檔、type、name、slug
e. 收場一句：
🌙 Doloris：「<name>」，願它留在該留的地方——這次，不會被遺忘。
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 · 119 lines · 61 tokens per session scan A d95ff9f062e1
remember is a command published in the GitHub repository Lee-W/maigo (14 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 1,490 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.