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/boardgit 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 | $0.00074 | $0.02559 |
| Opus 5 | $0.00037 | $0.01280 |
| Sonnet 5 | $0.00015 | $0.00512 |
| Haiku 4.5 | $0.00007 | $0.00256 |
Grade A, and why
board 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maigo:board
🌙 Doloris：「先看清楚球在誰手上，再決定下一步要往哪裡走。」
Work Board 是跨 session 的工作看板：issue triage / 接工、自己的 PR、正在 review 的 PR
全都放進 .maigo/board.md，依單一優先序排名（下一件事排最上面）分成三個 section。
命令由 orchestrator 直跑，不動員五人；正典規格在
skills/work-board。
使用
/maigo:board <targets...> # 混貼 issue/PR 編號或 URL；入板後刷新全板、印 🎯
/maigo:board # 無參數：刷新全板、印 🎯 + 其他區計數
/maigo:board --all # 刷新後印整板
/maigo:board --learn # 對已勾但未 🧠 的項目跑學習盤點
/maigo:board --check <n...> # 標記「我親自處理過」，作為 --learn 訊號
/maigo:board --uncheck <n...> # 取消「我親自處理過」標記
/maigo:board --drop <n...> # 不追了，移進 ✅ 最近結案（狀態詞 已放棄，7 天後跟其他結案行一起清）
targets 可混用裸編號、GitHub issue URL、GitHub PR URL。裸編號以當前 repo 判定；
URL 若指到其他 repo，行內保留 owner/repo#n 全稱。
流程
1. 載入或建立 board
若 .maigo/board.md 不存在，先建立骨架。若偵測到舊的 .maigo/review-board.md
且 board.md 尚不存在，依
work-board 的併入遷移規則
搬到新 board，舊檔改名成 .maigo/review-board.md.migrated 留底。
若 board.md 存在但仍是球權三分區時代的舊格式（讀到舊版 section 標題），刷新時取每行的
checkbox / 🧠 / 狀態詞後，整檔以新的三 section 骨架重寫，不做逐行 in-place 遷移。
2. 加入 targets（有參數時）
每個 target 先做型別偵測：
- URL 直接解析 owner / repo / issue-or-PR / number
- 裸編號用
gh api repos/<owner>/<repo>/issues/<n>；有pull_requestkey 就是 PR - PR 再比對
gh api user --jq .login與 author，分成 🔀 你的 PR / 👀 在審的 PR - 抓不到就標狀態詞
抓不到（rank P0，併進 🎯 最上面），附錯誤末行
加入時以 #<n> 或 owner/repo#<n> 為 key upsert；既有 checkbox 與 🧠 狀態必須保留。
3. 刷新分區
除 --learn 外，每次都刷新 board 上所有抓得到的項目：把每項的 type / gh_meta /
prior_status（讀自現有 board 行）/ url 組成 JSON 陣列，餵給
scripts/board_state.py
的 classify() 分類，取回 section / rank / status / next_action / detail_path，依
rank 升序 ＋ 同 rank 內 updatedAt 升序寫回 🎯 的編號清單（⏳/✅ 依 updatedAt 降序、
無編號）：
echo '<[{type, gh_meta, prior_status, url}, ...]>' \
| python3 scripts/board_state.py --you <login> --repo <owner/name>
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 · 140 lines · 74 tokens per session scan A ae0726658cfc
board is a command published in the GitHub repository Lee-W/maigo (14 stars, last pushed 9d ago), licensed MIT. It adds 74 tokens to every session and 2,559 once invoked, about $0.0004 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.