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 implementgit 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/implement)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/implement"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/implement/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/implement"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/implement.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 | $0.00072 | $0.02102 |
| Opus 5 | $0.00036 | $0.01051 |
| Sonnet 5 | $0.00014 | $0.00420 |
| Haiku 4.5 | $0.00007 | $0.00210 |
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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement
implement 將 tasks.md 視為唯一執行控制平面，但執行上下文必須包含 plan package 與 truth-delta.md。它負責交付 plan，不負責重新定義 truth；若發現 truth 與 tasks 明顯矛盾，應停止受影響 task 並回報需要上游修正。
Operating Principles
- by default 就是 don't stop until deliver / One-Shot：從第一個已解鎖 task 做到目標 plan 全部
[X]。使用者不必再寫這句。 - One-Shot 的一輪任務集恰好是 1 個已解鎖 task；有
Parallel Hint時改為 Hint 列出的[P]批次。One-Shot 不是把後面的序列 task 一次攤開。 - 做完一個任務集就驗證，立刻回寫
tasks.md的[X]，再重算下一筆。未回寫不得開下一個任務集。 - 嚴格執行不能跳步驟。
don't stop until deliver不是跳步驟的許可。 - Feature phase 仍序列。
[BDD-GREEN]、[BDD-REFACTOR]才委派/bdd，並把該 phase 的Test Scope當範疇。 - Phase 3 的
[BDD-ALIGN]、[BDD-REMOVE]、[BDD-RED]不委派/bdd；由 subagent 讀dsl.md該列的StepDef 實作語意寫測試層。 - Phase 3 review 通過前，不得進入 Feature Green。
- 每一個 task 或
Parallel Hint批次中的每一個 task，在回寫[X]前都必須各自執行 consumer 的 canonical doctor；doctor 非零不得完成該 task。 [BDD-RED]的預期 assertion／產品行為失敗不等同 canonical doctor 失敗；保留紅燈測試與證據，並為該 task 另外保存 canonical doctor exit 0 receipt，不得排除測試或以固定成功 wrapper 代替 doctor。- 全部 tasks
[X]後詢問是否 git commit；不得自動 commit。
SOP
Phase 1 -- 對齊 plan 並啟動 One-Shot
- READ 讀取使用者需求、目標 plan package、
tasks.md、truth-delta.md與目前 task 完成狀態，確認指定範圍（若有）與 One-Shot 起點。 - READ 讀取
rules/任務選取與連續續跑判準.md，確認已解鎖 task 的選取、One-Shot 與停止條件。 - READ 讀取
rules/TruthDelta測試對齊與BDD委派判準.md，確認 ADD / MODIFY / DELETE 的執行策略，以及哪些 marker 才委派/bdd。 - THINK 依已讀任務與判準收斂 One-Shot 起點、是否命中
Parallel Hint、所屬 phase；預設做到交付，不停在第一筆。
Phase 2 -- 補強 repo hygiene 與執行前置
- READ 讀取
rules/repo-hygiene-與-ignore-補強判準.md，確認本次需要檢查哪些 ignore surfaces、哪些只可增補不可覆寫。 - THINK 依目前 repo、工具鏈、plan package、truth-delta 與
specs/truth/techstack.md收斂本輪必做的最小 hygiene 補強。 - WRITE 只在實際相關且確有缺口時建立或增補 ignore 設定，避免擴張到無關工具鏈。
Phase 3 -- 收斂本輪任務集（不能跳步驟）
- READ 讀取
rules/嚴格禁止跳步驟判準.md與rules/平行執行與檔案衝突判準.md，確認本輪任務集邊界。 - READ 若
tasks.md當前 phase 含Parallel Hint，讀取rules/ParallelHint平行Subagent與衝突Merge判準.md。 - THINK 收斂本輪任務集：有
Parallel Hint則為 Hint 列出的[P]批次；否則恰好 1 個已解鎖 task。 - THINK 收斂執行模式：Setup 與 Foundational 直接實作並停在該則「只做／不做」；Phase 3 的 ALIGN / REMOVE / RED 走 subagent 測試層；review 走 review 迴圈；
[BDD-GREEN]/[BDD-REFACTOR]委派/bdd；[CODE-REMOVE]、[REGRESSION]直接實作或直接驗證。
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- LICENSE 1.2 KB
- rules/ParallelHint平行Subagent與衝突Merge判準.md 3.5 KB
- rules/repo-hygiene-與-ignore-補強判準.md 3.0 KB
- rules/TruthDelta測試對齊與BDD委派判準.md 3.9 KB
- rules/任務選取與連續續跑判準.md 3.6 KB
- rules/嚴格禁止跳步驟判準.md 5.9 KB
- rules/完成定義-驗證與回寫判準.md 5.3 KB
- rules/平行執行與檔案衝突判準.md 2.8 KB
- rules/技術參照載入與最小上下文判準.md 4.5 KB
- rules/自主決策與阻塞處理判準.md 3.4 KB
- specformula.md 2.9 KB
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 · -2 lines f91c883e09ce
- yesterday First seen · 75 lines · 72 tokens per session scan A efd37ea48aca
implement is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 2,102 once invoked, about $0.0004 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
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.
nw-hotspot
Git change frequency hotspot analysis — find the most-changed files in your codebase.
prd-v07-test-planning
Define test cases BEFORE implementation, ensuring every API, business rule, and user journey has verifiable acceptance criteria during PRD v0.7 Build Execution. Triggers on requests to define tests, plan test coverage, create test cases, or when user asks "define tests", "test planning", "what to test?", "test cases"…
prd-v08-changelog-as-marketing
Design the changelog as a distribution surface bridging engineering releases (DEP-/FEA-) to marketing channels (GTM-) during PRD v0.8 Deployment & Ops. Triggers on requests to set up a changelog system, publish releases, or when user asks "how should we publish releases?", "changelog as marketing", "release notes"…
commit
Smart commit, push, and npm publish with auto-splitting across domains. Creates atomic commits. Use when asked to "commit", "push changes", "publish", "save my work", or after completing implementation work. Automatically groups changes into logical commits.
ask-me
Interview the user relentlessly about the game they want to make until the idea is build-ready, resolving each branch of the design tree one question at a time. Use when the user has a fuzzy or one-line game idea and wants to flesh it out before building: 'grill me about my game', 'help me figure out what game to…