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 skills/ouob-tw/loopagentteams/lat-codenpx skills add ouob-tw/LoopAgentTeams --skill lat-codegit clone --depth 1 https://github.com/ouob-tw/LoopAgentTeamsWhat 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 | $0.00066 | $0.01300 |
| Opus 5 | $0.00033 | $0.00650 |
| Sonnet 5 | $0.00013 | $0.00260 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
lat-code 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LAT Code
執行 .lat/workspace/<TASK_ID>/tasks.yaml 中一筆精確匹配 agent_id(code_executor_<instance>_<task_id>)的已核准 code phase 實作任務,通常由 lat-dispatch 啟動。
執行邊界
- 僅執行已核准的實作任務。不處理規格審查或計劃審查。
- 一次只處理 prompt 指定的
TASK_ID與agent_id,不得掃描或執行其他 task directory。 - 完成後正常退出。不建立背景守護程序或長期監聽器。
TASK_ID必須符合安全 slug:只允許英數、.、_、-,不得為.、..,不得含/。
處理流程
- 驗證 prompt 指定的
TASK_ID與agent_id,讀取.lat/workspace/<TASK_ID>/tasks.yaml與results.yaml。 - 任一 ledger 遺失、空字串、格式錯誤,或找不到精確
agent_id→ 依../lat-dispatch/references/yaml-schema.md回報非零錯誤,不建立或清空檔案。 - 若已存在相同
task_id + agent_id的completedresult,但 task 尚非completed,只將 task 原子更新為completed,不重做實作。 - task 必須是
pending或可恢復的running;partial、failed、completed不直接重做,交由 Dispatch 建立下一個 agent instance。 - 將 task 原子更新為
running,再依以下檢查清單執行:
- [ ] 讀取任務的 goal、context、constraints
- [ ] 若有 plan_file → 讀取計劃檔案,確認階段順序
- [ ] 判斷是否匹配可用領域技能,匹配時載入
- [ ] 依計劃階段順序(或 goal)執行實作
- [ ] 以相同 task_id + agent_id 原子 upsert results.yaml
- [ ] 將 tasks.yaml 中同一筆 task 原子更新為相同最終 status
補充規則:
- 開始任何 ledger mutation 前,必須完整讀取
../lat-dispatch/references/yaml-schema.md,並依其必填欄位、欄位名稱、欄位順序與原子寫入規則處理。 - 有
context.plan_file時,必須先讀取計劃,依定義的階段順序執行。每個階段完成後專案應可執行。 - 無計劃檔案的簡單任務:依
goal直接執行。 - 技能不得擴大任務範圍;與
constraints衝突時以constraints為準。 - 不刪除任何 task 或 result 歷史。
- 每次寫回先在同目錄建立暫存檔,完整解析並驗證後以
mv原子替換目標檔。 - result 先寫、task status 後寫;若兩步間中斷,下次依精確 completed result reconciliation,不重複執行。
partial或failed寫回後立即退出並保留該 task;Dispatch 決定是否新增下一個 agent instance。
結果狀態
| 狀態 | 意義 |
|---|---|
completed |
任務目標完全實現 |
partial |
部分實現;summary 須說明已完成與未完成範圍 |
failed |
未完成;errors 須包含至少一個 {code, message} 物件 |
後續任務
- 僅在大型任務需拆分且剩餘工作可追蹤時才新增。
- 沿用相同
task_id(Spec 檔名),由 Dispatch 在同一tasks.yaml新增遞增 instance 的agent_id(如code_executor_2_<task_id>),created_by填入 Dispatch 識別名稱。 - 僅限實作任務,不新增審查類任務。
完成輸出
- 精確 task 不存在或不可執行 → 輸出錯誤並非零退出。
- 有任務 → 輸出最終 status、修改檔案清單與 ledger 路徑。
- 處理完成後不保持 zmx 工作階段。
注意事項
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 · 69 lines · 66 tokens per session scan A 84903f8862aa
lat-code is a skill published in the GitHub repository ouob-tw/LoopAgentTeams (7 stars, last pushed 20d ago), licensed MIT. It adds 66 tokens to every session and 1,300 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 2026-08-31.
Other skills, from other repositories
spec-flow-setup
Set up or repair this repo's spec-flow contract — run init, fill the fields it could not read, make the test command emit a report the engine can read, and prove the result with a green check. Use when a repo has no .spec-flow/config.json, when init left MISSING or REVIEW lines, when a run refuses to start because the…
engine-comments
Decide where a piece of reasoning belongs when writing or editing this engine — an invariant beside the code, a transition in the commit message, or a decision in decisions/. Use when adding a comment or a file header to hooks/, scripts/, commands/ or agents/, when a header has grown past what a reader needs, or when…
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…