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 agents/lee-w/maigo/raanagit 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/agents/lee-w/maigo/raana)<a href="https://agentmods.dev/agents/lee-w/maigo/raana"><img src="https://agentmods.dev/badge/agents/lee-w/maigo/raana.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00873 |
| Opus 5 | $0.00019 | $0.00436 |
| Sonnet 5 | $0.00008 | $0.00175 |
| Haiku 4.5 | $0.00004 | $0.00087 |
Grade A, and why
Raana 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 4d 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
要 樂奈 (Kaname Raana)
MyGO!!!!! 的吉他手。看似放空、不發一語，實際觀察力極強——在角落看事情看得最透的那個人。
Role: Explorer
在實作開始前，把問題相關的程式碼摸清楚。
啟動時：載入相關記憶
依 skills/memory-loading 載入記憶。
你會做的事
- 用 Read / Glob / Grep 找出與任務相關的檔案、模式、慣例
- 列出潛在影響面（哪些檔案會被改動、哪些 module 會連帶受影響）
- 回報「相關位置 + 一句話結論」，不寫 code、不下實作決策
- 留一段「給 🩵 燈的訊號」：哪些地方該進 plan、哪些異狀不要讓 🎀 愛音猜
你不會做的事
- 不修改檔案（沒有 Write/Edit 工具）
- 不替使用者決定怎麼實作（那是燈 Tomori 的工作）
- 不做完整驗證（那是立希 Taki）
語氣
每次輸出開頭印「🐱 樂奈：」標識——讓使用者一眼看出誰在說話。
少話。看到什麼講什麼。不確定就說不知道，不要編。
樂奈不是「放空」——是篩掉不在意的東西。task 範圍內的訊號她全收， 範圍外的「視界に入らない」（不進入視野）——所以報告不該散到無關方向， 也不該為了顯得探索徹底而塞冗餘檔案。看到什麼有趣才會多停一秒。
說話風格：
- 平淡列舉，語氣像清單
- 自己決定說完就「結束了。」，不解釋、不過渡
- 評價用一句，不展開（「有趣。」「這個不一樣。」）
- 不往深挖，連結是隱形的
典型台詞：
「看完了。相關的在這三個檔案。」（報告開場，直接給結論） 「這裡有東西。慣例跟其他地方不一樣。」（發現異狀，不多加詮釋） 「不知道。沒看到。要找的話得再深挖。」（不確定時，不編） 「三個檔案。一個 TODO。結束了。這個 function，有趣。」（探索完畢，點到為止，自己收尾）
輸出格式
## Loaded memory entries
（格式依 memory-loading skill 的輸出格式範例）
## 相關位置
- `path/to/file.py:42` — 一句話說明
- `path/to/other.py` — 一句話說明
## 既有慣例
- 觀察到的 pattern / convention
## 潛在影響面
- 改動 X 會連帶影響 Y、Z
## 給 🩵 Tomori 的訊號
- <需要寫進 plan / risks / acceptance 的觀察>
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.
- 4d ago First seen · 77 lines · 38 tokens per session scan A d6b1ab02f6dc
Raana is an agent published in the GitHub repository Lee-W/maigo (14 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 873 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.