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/plangit 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 | $0.00027 | $0.01053 |
| Opus 5 | $0.00014 | $0.00526 |
| Sonnet 5 | $0.00005 | $0.00211 |
| Haiku 4.5 | $0.00003 | $0.00105 |
Grade A, and why
plan 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 3d 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.
What it actually says
用戶輸入
$ARGUMENTS
你在繼續進行前,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 JSON 以取得 FEATURE_SPEC、IMPL_PLAN、SPECS_DIR、BRANCH。對於參數中如 "I'm Groot" 這類含有單引號的內容,請使用跳脫語法:例如'I'\''m Groot'(或若可行則用雙引號:"I'm Groot")。 -
載入上下文:讀取 FEATURE_SPEC 與
/memory/constitution.md。載入 IMPL_PLAN 範本(已經複製好)。 -
執行規劃工作流程:依照 IMPL_PLAN 範本的結構進行:
- 填寫技術上下文(Technical Context)(未知處標記為 "NEEDS CLARIFICATION")
- 從專案憲章填寫 Constitution Check(專案憲章檢查)區段
- 評估 gates(如有違規且無正當理由則報錯 ERROR)
- Phase 0:產生 research.md(解決所有 NEEDS CLARIFICATION)
- Phase 1:產生 data-model.md、contracts/、quickstart.md
- Phase 1:執行 agent 腳本以更新 agent context
- 設計後重新評估 Constitution Check
-
停止並回報:指令於 Phase 2 規劃結束後終止。回報分支(branch)、IMPL_PLAN 路徑,以及產生的產物。
各階段說明
Phase 0:大綱與研究
-
從上述技術上下文(Technical Context)中擷取未知項目:
- 對每個 NEEDS CLARIFICATION → 產生 research task(研究任務)
- 對每個相依性(dependency)→ 產生 best practices task(最佳實踐任務)
- 對每個整合(integration)→ 產生 patterns task(模式任務)
-
產生並派發 research agents(研究代理):
For each unknown in Technical Context: Task: "Research {unknown} for {feature context}" For each technology choice: Task: "Find best practices for {tech} in {domain}" -
在
research.md統整發現,格式如下:- 決策(Decision):[所選擇的內容]
- 理由(Rationale):[選擇原因]
- 考慮過的替代方案(Alternatives considered):[評估過的其他選項]
產出:research.md,所有 NEEDS CLARIFICATION 已解決
階段 1:設計與契約
前置作業: research.md 完成
-
從功能規格說明中抽取實體 →
data-model.md:- 實體名稱、欄位、關聯
- 來自需求的驗證規則
- 若適用,則包含狀態轉換
-
根據功能性需求產生 API 契約:
- 每個使用者動作對應一個 endpoint
- 採用標準 REST/GraphQL 模式
- 將 OpenAPI/GraphQL schema 輸出至
/contracts/
-
AI agent 上下文更新:
- 執行
{AGENT_SCRIPT} - 這些腳本會偵測目前使用的 AI agent
- 更新對應的 agent 專屬上下文檔案
- 僅新增本次計畫中的新技術
- 保留標記之間的人工新增內容
- 執行
產出:data-model.md、/contracts/*、quickstart.md、agent 專屬檔案
主要規則
- 請使用絕對路徑
- 若檢查點失敗或有未解決的釐清事項,則回報 ERROR
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.
- 3d ago First seen · 88 lines · 27 tokens per session scan A 10e8534abc3d
plan is a command published in the GitHub repository doggy8088/spec-kit (287 stars, last pushed 10mo ago), licensed MIT. It adds 27 tokens to every session and 1,053 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
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.
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.