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/doggy8088/spec-kit/tasksgit clone --depth 1 https://github.com/doggy8088/spec-kitWhat 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 | $0.00032 | $0.02073 |
| Opus 5 | $0.00016 | $0.01037 |
| Sonnet 5 | $0.00006 | $0.00415 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade A, and why
tasks 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用戶輸入
$ARGUMENTS
在繼續執行前,必須考慮用戶輸入(若非空)。
大綱
-
設定:從 repo 根目錄執行
{SCRIPT},並解析 FEATURE_DIR 與 AVAILABLE_DOCS 清單。所有路徑必須為絕對路徑。若參數中有單引號,如 "I'm Groot",請使用跳脫語法:例如 'I'''m Groot'(或若可行則用雙引號:"I'm Groot")。 -
載入設計文件:從 FEATURE_DIR 讀取:
- 必要:plan.md(技術堆疊、函式庫、結構)、spec.md(用戶故事及其優先順序)
- 可選:data-model.md(實體)、contracts/(API endpoint)、research.md(決策)、quickstart.md(測試情境)
- 注意:並非所有專案都具備所有文件。請依現有文件產生任務。
-
執行任務產生工作流程:
- 載入 plan.md 並擷取技術堆疊、函式庫、專案結構
- 載入 spec.md 並擷取用戶故事及其優先順序(P1、P2、P3 等)
- 若有 data-model.md:擷取實體並對應至用戶故事
- 若有 contracts/:將 API endpoint 對應至用戶故事
- 若有 research.md:擷取決策以產生設定任務
- 依用戶故事產生任務(詳見下方任務產生規則)
- 產生顯示用戶故事完成順序的相依性圖
- 為每個用戶故事建立平行執行範例
- 驗證任務完整性(每個用戶故事皆具備所有必要任務,且可獨立測試)
-
產生 tasks.md:以
.specify/templates/tasks-template.md為結構,內容包含:- 從 plan.md 取得正確的功能名稱
- Phase 1:設定任務(專案初始化)
- Phase 2:基礎任務(所有用戶故事的阻斷前置作業)
- Phase 3+:每個用戶故事一個階段(依 spec.md 優先順序排列)
- 每個階段包含:故事目標、獨立測試標準、測試(如有需求)、實作任務
- 最後階段:優化與橫切關注點
- 所有任務必須遵循嚴格的檢查清單格式(詳見下方任務產生規則)
- 每個任務需有明確的檔案路徑
- 相依性區塊顯示用戶故事完成順序
- 每個用戶故事的平行執行範例
- 實作策略區塊(先做 MVP(最小可行性產品),逐步交付)
-
報告:輸出產生的 tasks.md 路徑及摘要:
- 任務總數
- 各用戶故事的任務數量
- 已識別的平行執行機會
- 各用戶故事的獨立測試標準
- 建議的 MVP(最小可行性產品)範圍(通常僅為 User Story 1)
- 格式驗證:確認所有任務皆符合檢查清單格式(勾選框、ID、標籤、檔案路徑)
任務產生上下文:{ARGS}
tasks.md 應可立即執行——每個任務都必須具體明確,使大型語言模型(LLM)無需額外上下文即可完成。
任務產生規則
重要:任務必須依用戶故事組織,以利獨立實作與測試。
測試為可選:僅於功能規格明確要求或用戶要求 TDD(測試優先)時產生測試任務。
檢查清單格式(必須遵循)
每個任務必須嚴格遵循以下格式:
- [ ] [TaskID] [P?] [Story?] Description with file path
格式組成:
- 核取方塊:一律以
- [ ](Markdown 核取方塊)開頭 - 任務 ID:依執行順序遞增編號(T001、T002、T003...)
- [P] 標記:僅在任務可並行時加入(不同檔案、且不依賴未完成任務)
- [Story] 標籤:僅限 User Story 階段任務必須加上
- 格式:[US1]、[US2]、[US3] 等(對應 spec.md 中的 user stories)
- Setup 階段:不加 story 標籤
- Foundational 階段:不加 story 標籤
- User Story 階段:必須加上 story 標籤
- Polish 階段:不加 story 標籤
- 描述:明確動作,並標示精確檔案路徑
範例:
- ✅ 正確:
- [ ] T001 Create project structure per implementation plan - ✅ 正確:
- [ ] T005 [P] Implement authentication middleware in src/middleware/auth.py - ✅ 正確:
- [ ] T012 [P] [US1] Create User model in src/models/user.py - ✅ 正確:
- [ ] T014 [US1] Implement UserService in src/services/user_service.py - ❌ 錯誤:
- [ ] Create User model(缺少 ID 與 Story 標籤) - ❌ 錯誤:
T001 [US1] Create model(缺少核取方塊) - ❌ 錯誤:
- [ ] [US1] Create User model(缺少任務 ID) - ❌ 錯誤:
- [ ] T001 [US1] Create model(缺少檔案路徑)
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 · 132 lines · 32 tokens per session scan A 9288576cc859
tasks is a command published in the GitHub repository doggy8088/spec-kit (287 stars, last pushed 10mo ago), licensed MIT. It adds 32 tokens to every session and 2,073 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 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.