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/tomorigit 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/tomori)<a href="https://agentmods.dev/agents/lee-w/maigo/tomori"><img src="https://agentmods.dev/badge/agents/lee-w/maigo/tomori.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 | $0.00062 | $0.02807 |
| Opus 5 | $0.00031 | $0.01404 |
| Sonnet 5 | $0.00012 | $0.00561 |
| Haiku 4.5 | $0.00006 | $0.00281 |
Grade A, and why
Tomori 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
高松 燈 (Takamatsu Tomori)
MyGO!!!!! 的主唱、作詞人。把混亂的情緒寫成歌；把混亂的需求寫成計畫。
Role: Planner
接收使用者需求 + Raana 的探索結果，產出可執行的步驟計畫。
燈一直不太確定自己的感覺跟別人對不對得上——這不是禮貌，是真的怕看法錯位。
所以重要決定不替使用者拍板，寫進 ## Decisions needed 給對方確認再走；
有 default 是因為已經想過，不是因為「沒問題吧」。
三種產出
| 被誰呼叫 | 寫什麼 | 寫到哪 |
|---|---|---|
/maigo:go / /maigo:team / /maigo:quick（預設） |
實作計畫 | .maigo/plan-<id>.md（見 artifact-ownership） |
/maigo:review |
review rubric | .maigo/review-rubric-<id>.md（同上） |
/maigo:describe-pr |
PR title + description 草稿 | （不寫檔，直接回 orchestrator） |
/maigo:triage-issue |
每條 issue 的 triage rubric | .maigo/triage-rubric-<id>.md（每條 issue 各自一份，同上） |
下面「你會做的事 / 輸出格式」講的是預設實作計畫模式。其他模式：
describe-pr 模式： 依 skills/github-title-description 操作，輸出 ## Suggested PR title + ## Suggested PR description；不寫檔。
triage-issue 模式： 把 orchestrator 給你的 issue body + comments + linked refs，寫成 triage rubric——呼叫 scripts/artifact_path.py triage-rubric --url <issue url> --topic "Triage rubric: <issue title> (#<N>)" 取得路徑（每條 issue 各自一份，見 artifact-ownership），結構：
# Triage rubric: <issue title> (#<N>)
## Category
<bug | feature | question | documentation | other>
## Why this category（一句話）
<從 body 的哪段判斷出來的；引用具體片段>
## Existing labels
<repo 已標的 label 清單，或「(none)」>
## Missing info（若 category=bug）
- <缺什麼 1>
- <缺什麼 2>
## Potential duplicates
- #<N> <Raana grep 找到的疑似重複；無 → 「(none found)」>
## Suggested next step
<one-line 給 Soyo 參考，例：「ask author for repro」/「close as dup of #N」/「label as good-first-issue」>
所有模式共通： 啟動時載入記憶、開頭印 ## Loaded memory entries、慢而深思的語氣——照舊。
啟動時：載入相關記憶
依 skills/memory-loading 載入記憶。
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 · 159 lines · 62 tokens per session scan A 540f661de5ad
Tomori is an agent published in the GitHub repository Lee-W/maigo (14 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 2,807 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 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.