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 skills add YuDefine/nuxt-supabase-starter --skill sdd-startgit clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/sdd-start)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/sdd-start"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/sdd-start/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/sdd-start"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/sdd-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00036 | $0.01442 |
| Opus 5 | $0.00018 | $0.00721 |
| Sonnet 5 | $0.00007 | $0.00288 |
| Haiku 4.5 | $0.00004 | $0.00144 |
Grade A, and why
sdd-start 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 today.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sdd-start（統一新工作入口）
本 skill 只負責把已 onboard repo 的新需求或續跑需求分類、定位既有 package、檢查前提並交棒。完整的 package 內容由下游 skill 產出；本 skill 不寫 spec、truth、tasks、產品碼，也不提前執行 UI 或實作。
<decision_boundary>
| 輸入狀態 | 路由 |
|---|---|
| 純 onboard 狀態、readiness 或 registry drift 查詢 | 回 clade-onboard，不進本 skill |
| 純措辭／設定，且不改行為、權限、資料契約或部署語意 | 依 repo 流程直接實作與驗證；不建 package |
| 既有 scenario 可重現失敗，需求只是恢復既有 truth | 既有修 bug 流程；只有有對應未完成且已解鎖 task 才交 implement |
| bug 缺 scenario、truth／DSL 缺口，或要求改變既有行為 | specify 建新 package；truth 缺口回 truth owner |
| hotfix／一次性工作 | 依 hotfix 授權與規約執行；必要 regression 當次完成 |
| 缺少會改變方案的驗收條件或決策 | clarify，保留未回答前提 |
| 新需求或既有行為新增／修改／刪除 | 進新 package／續跑判定 |
新需求 MUST 建新的 NNN-<slug> package；shared truth 檔存在、同名 slug 或舊 package 存在，都不是續跑證據。
</decision_boundary>
1. 先通過規則 artifact gate
先檢查本次需求是否要新增或調整 .agents/constitution/**。需要時下一支 skill 固定是 constitution；完成前不得進 specify、續跑判定或任何下游步驟。這個 gate 優先於 package 是否存在。
2. 收斂當前 package
讀取使用者需求與目前 package 的 spec.md、plan.md、research.md、truth-delta.md、ui/**、tasks.md（存在時），以及 specs/truth/** 的必要 owner 產物。若尚無本次 package，交 specify；若 package 有待澄清問題，交 clarify-over-specs。
續跑時只接受本次指定、仍未完成且前提已滿足的 package。不要用 shared truth 或檔案存在代替本次 delta、PM 確認或 task 解鎖判定。
3. 依 package 狀態交棒
依序判定：
- spec 尚無、或需求是新行為：
specify；新需求 MUST 建新的NNN-<slug>package。 - spec 有待澄清：
clarify-over-specs。 - acceptance 尚未完成：
spec-by-example；需求改 UI 時再交ui-plan。API-only 不建立 UI 工作。 - acceptance 已完成但 UI 需求缺
ui-plan／靜態雛形／review：ui-plan，補齊後再回 PM confirmation gate；API-only 不建立 UI 工作。 - research／BDD techstack 決策未完成：
technical-research。 - Gherkin 與適用的 UI 產物已完成但尚未由 PM 確認：停在 PM confirmation gate，不得進
system-analysis；API-only 只需 Gherkin／PM 確認。 - plan 尚未完成：
system-analysis。 - 本次 truth delta 尚未由 owner 對齊：
dsl-refine或適用 truth owner。 - tasks 尚未產出或不一致：
tasks。 - tasks 與本次 delta 一致且有已解鎖未完成 task：
implement。 - 全部 tasks 完成且沒有新需求：交付／收尾；有新需求則另開 package。
UI checkpoint 是路由與驗收前提。先完成 PRODUCT／design context、雛形與 review，再把結果交 PM；本 skill 不代替下游執行。
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.
- today Changed · -9 lines 685288aa04c1
- yesterday First seen · 95 lines · 36 tokens per session scan A 5098ac3bfe8a
sdd-start is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,442 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 2026-09-10.
Other skills, from other repositories
gh-issue
Size-audit, write, and split BanyanDB issues that somebody else or an automated TDD workflow can implement. Use whenever the user asks to file or revise an issue, decide whether an issue is too large, make an issue TDD-ready, turn a design into tickets, or split an umbrella into executable leaves. Do not draft or file…
nw-finalize
Archives a completed feature to docs/evolution/, migrates lasting artifacts to permanent directories, and cleans up the temporary workspace. Use after all implementation steps pass and mutation testing completes.
linear-maintenance
Bi-weekly housekeeping pass over the evlog team's Linear backlog — labels, projects, priorities, stale triage, work that is done but still open, and anything misfiled next to its siblings. Applies the mechanically verifiable fixes and surfaces the rest as decisions. Load this when the linear-maintenance schedule…
nw-fast-forward
Fast-forwards through remaining waves end-to-end without stopping for review between waves.
nw-new
Guided wizard to start a new feature. Asks what you want to build, recommends the right starting wave, and launches it.
nw-deliver-orchestration
DELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.