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/implementgit 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 | $0.00026 | $0.02707 |
| Opus 5 | $0.00013 | $0.01354 |
| Sonnet 5 | $0.00005 | $0.00541 |
| Haiku 4.5 | $0.00003 | $0.00271 |
Grade A, and why
implement 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 — 139 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,你必須考慮用戶輸入(若非空)。
大綱
-
從 repo 根目錄執行
{SCRIPT},並解析 FEATURE_DIR 及 AVAILABLE_DOCS 清單。所有路徑必須為絕對路徑。對於參數中如 "I'm Groot" 這類帶有單引號的字串,請使用跳脫語法:例如 'I'''m Groot'(或若可行則使用雙引號:"I'm Groot")。 -
檢查 checklists 狀態(若 FEATURE_DIR/checklists/ 存在):
-
掃描 checklists/ 目錄下所有檢查清單檔案
-
對每個檢查清單,統計:
- 總項目數:所有符合
- [ ]、- [X]或- [x]的行 - 已完成項目數:符合
- [X]或- [x]的行 - 未完成項目數:符合
- [ ]的行
- 總項目數:所有符合
-
建立一個狀態表:
| Checklist | Total | Completed | Incomplete | Status | |-----------|-------|-----------|------------|--------| | ux.md | 12 | 12 | 0 | ✓ PASS | | test.md | 8 | 5 | 3 | ✗ FAIL | | security.md | 6 | 6 | 0 | ✓ PASS | -
計算整體狀態:
- PASS:所有 checklists 都沒有未完成項目(incomplete items 數量為 0)
- FAIL:有一個或多個 checklists 存在未完成項目
-
若有任何 checklist 未完成:
- 顯示包含未完成項目數量的表格
- 停止並詢問:「有些 checklists 尚未完成。你仍要繼續進行實作嗎?(yes/no)」
- 等待用戶回應後才繼續
- 若用戶回覆 "no"、"wait" 或 "stop",則停止執行
- 若用戶回覆 "yes"、"proceed" 或 "continue",則繼續執行第 3 步
-
若所有 checklists 均已完成:
- 顯示所有 checklists 通過的表格
- 自動進入第 3 步
-
-
載入並分析實作上下文(implementation context):
- 必須:讀取 tasks.md 以取得完整任務清單與執行計畫
- 必須:讀取 plan.md 以取得技術堆疊、架構與檔案結構
- 若存在:讀取 data-model.md 以取得 entity 與關聯
- 若存在:讀取 contracts/ 以取得 API 契約與測試需求
- 若存在:讀取 research.md 以了解技術決策與限制
- 若存在:讀取 quickstart.md 以取得整合(integration)場景
-
專案設定驗證(Project Setup Verification):
- 必須:根據實際專案設定建立/驗證 ignore 檔案:
偵測與建立邏輯(Detection & Creation Logic):
-
檢查下列指令是否成功,以判斷 repository 是否為 git repo(若是則建立/驗證 .gitignore):
git rev-parse --git-dir 2>/dev/null -
檢查是否存在 Dockerfile* 或 plan.md 中有 Docker → 建立/驗證 .dockerignore
-
檢查是否存在 .eslintrc* 或 eslint.config.* → 建立/驗證 .eslintignore
-
檢查是否存在 .prettierrc* → 建立/驗證 .prettierignore
-
檢查是否存在 .npmrc 或 package.json → 建立/驗證 .npmignore(若需發佈時)
-
檢查是否存在 terraform 檔案(*.tf)→ 建立/驗證 .terraformignore
-
檢查是否需要 .helmignore(有 helm charts 時)→ 建立/驗證 .helmignore
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 · 139 lines · 26 tokens per session scan A 3998c24a890e
implement is a command published in the GitHub repository doggy8088/spec-kit (287 stars, last pushed 10mo ago), licensed MIT. It adds 26 tokens to every session and 2,707 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.