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/memorygit 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 | $0.00028 | $0.00789 |
| Opus 5 | $0.00014 | $0.00394 |
| Sonnet 5 | $0.00006 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
memory 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:memory
列出記憶層目前儲存的跨專案偏好 / 慣例 / 反饋。
Orchestrator 親自跑,不開新 agent。
使用
/maigo:memory # 列全部
/maigo:memory project # 只列 project type
/maigo:memory user # 只列 user type
/maigo:memory feedback
/maigo:memory reference
流程
-
檢查
~/.config/maigo/memory/MEMORY.md是否存在。- 不存在 / 空 → 印友善訊息:「目前無跨專案記憶。要建立第一筆,用
/maigo:remember <自然語言描述>。」並結束。
- 不存在 / 空 → 印友善訊息:「目前無跨專案記憶。要建立第一筆,用
-
讀
MEMORY.md,解析每行- [<name>](<slug>.md) — <description>。 -
對每個 slug,讀
~/.config/maigo/memory/<slug>.md的 YAML frontmatter, 抽出name/type/description/triggers(optional)。 -
若使用者帶了
<type>參數,filter 掉 type 不符的 entry。<type>不在{user, feedback, project, reference}→ 印「不支援的 type<x>,可用值:user / feedback / project / reference」並報錯結束(非 0 退出)。- filter 後 0 筆 → 印「(目前無 type=
<type>的記憶)」並正常結束(不視為錯誤)。
-
以 markdown table 輸出:
Name Type Description Triggers ... ... ... ...(無 triggers 留空) -
table 末尾印一行 footer:「共 N 筆。詳全文:
cat ~/.config/maigo/memory/<slug>.md」 -
收場一句:
🌑 Mortis:「共 N 筆」。你手上的,就這些了。(N 帶入實際筆數)
Orchestrator 守則
- 旁白:orchestrator 對使用者說話時戴上旁白的臉——開場、收場由 🌙 Doloris / 🌑 Mortis 旁白,依
skills/narration。 - 對話:對話本體(旁白節點以外)的互動節奏與用詞,依
skills/orchestrator-voice。 - 不寫任何檔——read-only。
- 不 delegate 給任何 agent。
- parse frontmatter 失敗的 entry → 跳過,印 warning「
<slug>.mdfrontmatter 解析失敗,已跳過」,繼續處理其他 entry,不 crash。 - filter 參數比對忽略大小寫。
→ 完整 storage spec:Memory reference
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 · 58 lines · 28 tokens per session scan A 99a54c5b8e54
memory is a command published in the GitHub repository Lee-W/maigo (14 stars, last pushed 8d ago), licensed MIT. It adds 28 tokens to every session and 789 once invoked, about $0.0001 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.