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/checklistgit 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 | $0.00020 | $0.04698 |
| Opus 5 | $0.00010 | $0.02349 |
| Sonnet 5 | $0.00004 | $0.00940 |
| Haiku 4.5 | $0.00002 | $0.00470 |
Grade A, and why
checklist 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
檢查清單目的:「英文單元測試」
關鍵概念:檢查清單是需求撰寫的單元測試——用來驗證特定領域中需求的品質、清晰度與完整性。
不是用於驗證/測試:
- ❌ 不是「驗證按鈕是否能正確點擊」
- ❌ 不是「測試錯誤處理是否正常」
- ❌ 不是「確認 API 回傳 200」
- ❌ 不是檢查程式碼/實作是否符合規格
用於需求品質驗證:
- ✅「所有卡片類型是否都有定義視覺階層需求?」(完整性)
- ✅「『明顯顯示』是否以具體尺寸/位置量化?」(清晰度)
- ✅「所有互動元素的 hover 狀態需求是否一致?」(一致性)
- ✅「是否有定義鍵盤導覽的無障礙需求?」(覆蓋範圍)
- ✅「規格是否有定義 logo 圖片載入失敗時的處理?」(邊界情境)
比喻:如果你的規格像是用英文寫的程式碼,檢查清單就是它的單元測試套件。你是在測試需求是否寫得好、是否完整、明確且可直接實作——而不是測試實作本身是否可用。
用戶輸入
$ARGUMENTS
你在執行前必須考慮用戶輸入(若非空)。
執行步驟
Execution Steps
-
初始化:從 repo 根目錄執行
{SCRIPT},並解析 JSON 以取得 FEATURE_DIR 與 AVAILABLE_DOCS 清單。- 所有檔案路徑必須為絕對路徑。
- 若引數中有單引號(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")。
-
釐清意圖(動態):根據上下文產生最多三個初步釐清問題(不得使用預設題庫)。這些問題必須:
- 依據用戶的描述+從規格/計畫/任務中提取的訊號動態生成
- 僅詢問會實質影響檢查清單內容的資訊
- 若在
$ARGUMENTS中已明確,則個別問題可跳過 - 以精確度優先於廣度
生成演算法:
- 提取訊號:功能領域關鍵字(如 auth、latency、UX、API)、風險指標(如 "critical"、"must"、"compliance")、利害關係人提示(如 "QA"、"review"、"security team")、明確交付項(如 "a11y"、"rollback"、"contracts")。
- 將訊號分群為候選重點領域(最多 4 組),依相關性排序。
- 若未明確,判斷可能的目標對象與時機(作者、審查者、QA、發佈)。
- 偵測缺漏面向:範圍廣度、深度/嚴謹度、風險強調、排除邊界、可衡量的驗收標準。
- 依下列問題原型擇一組成問題:
- 範圍細化(如:「此檢查清單是否需涵蓋與 X、Y 的整合接點,還是僅限於本地模組正確性?」)
- 風險優先排序(如:「這些潛在風險區塊中,哪些需要強制設置檢查關卡?」)
- 深度校準(如:「這是 pre-commit 的輕量 sanity list 還是正式發佈的 release gate?」)
- 目標對象定位(如:「這份檢查清單僅作者自用,還是 PR 審查時同儕也會用?」)
- 邊界排除(如:「本輪是否明確排除效能調校項目?」)
- 情境類型缺口(如:「未偵測到復原流程——rollback/部分失敗路徑是否納入範圍?」)
問題格式規則:
- 若有選項,請產生精簡表格,欄位:Option | Candidate | Why It Matters
- 最多僅列 A–E 選項;若開放式回答更清楚則不需表格
- 絕不要求用戶重述已說過的內容
- 避免臆測分類(不得憑空想像)。若不確定,請明確詢問:「請確認 X 是否屬於範圍內。」
若無法互動時的預設值:
- 深度:標準
- 目標對象:如與程式碼相關則為 Reviewer(PR),否則為 Author
- 重點:前兩大相關性分群
輸出問題時請標示 Q1/Q2/Q3。回覆後:若有兩類以上情境(Alternate/Exception/Recovery/Non-Functional 領域)仍不明確,你可以再追問最多兩個精準後續問題(Q4/Q5),每題附一句理由(如:「復原路徑風險未解決」)。總題數不得超過五題。若用戶明確拒絕,則不得繼續追問。
-
理解用戶需求:結合
$ARGUMENTS與釐清回覆:- 推導檢查清單主題(如 security、review、deploy、ux)
- 彙整用戶明確指定的 must-have 項目
- 將重點選擇映射至分類結構
- 從規格/計畫/任務中推斷缺漏上下文(不得憑空想像)
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 · 264 lines · 20 tokens per session scan A 99b04dfa5e2a
checklist is a command published in the GitHub repository doggy8088/spec-kit (287 stars, last pushed 10mo ago), licensed MIT. It adds 20 tokens to every session and 4,698 once invoked, about $0.0001 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
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.