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 guidegit 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/guide)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/guide"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/guide/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/guide"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01991 |
| Opus 5 | $0.00023 | $0.00996 |
| Sonnet 5 | $0.00009 | $0.00398 |
| Haiku 4.5 | $0.00005 | $0.00199 |
Grade A, and why
guide 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/guide — hub skill 地圖
不確定該用哪個 skill 時打 /guide。本 skill 是 router：描述每個 skill 的適用場景與銜接關係，本身不執行任何工作。讀完後直接 invoke 對應 skill。
先看這個：本表分層，不是每一支你都裝了
skill 由 consumer manifest 的 modules 決定裝哪些（canonical .clade/manifest.json，legacy .claude/hub.json 仍可讀）。下表的條目帶標記時，只有宣告對應 module 的 repo 才有那支 skill——沒宣告就是打了也不存在，不是壞掉：
| 標記 | 需要 manifest 宣告 | 沒宣告的 repo |
|---|---|---|
| 〔aixbdd〕 | modules.capabilities 含 "aixbdd" |
沒有 /specify、/tasks、/implement 這條需求管線。待辦走 tasks/ + HANDOFF / tech-debt / ROADMAP，/work-loop 照樣能跑 |
| 〔specformula〕 | modules.capabilities 含 "specformula" |
沒有 .feature / isa.yml 的 BDD 執行層 |
| 〔nuxt〕 | modules.framework = "nuxt" |
沒有 Nuxt 專用的稽核與 dev 工具 |
| 〔node〕 | modules.ecosystem 含 "node" |
沒有 /version-upgrade（它綁 npm/pnpm，不是綁 Nuxt） |
無標記的是 hub-core，每個 consumer 都有。NEVER 因為本表列了某支就斷定這裡裝了它——以該 repo 的 manifest 為準。
主流程（idea → shipped）
一條 change 的完整生命週期，依序銜接：
| 階段 | Skill | 這一站做什麼 |
|---|---|---|
| 提案〔aixbdd〕 | /specify |
建 specs/plans/NNN-<slug>/：驗收標準與 truth-delta |
| 澄清〔aixbdd〕 | /clarify-over-specs |
對 spec.md 的模糊處逐項收斂 |
| 驗收 Gherkin〔aixbdd〕 | /spec-by-example → /ui-plan |
產 features/acceptance/** 與靜態雛形 |
| 設計〔aixbdd〕 | /technical-research、/system-analysis |
定 techstack 與系統設計 |
| 規格落地〔aixbdd〕 | /dsl-refine |
把句型寫進 specs/truth/features/** 與 dsl.md |
| 拆任務〔aixbdd〕 | /tasks |
產 plan package 的 tasks.md；開工前 flow open <slug> --origin tasks:<path> |
| 實作〔aixbdd〕 | /implement（[BDD-GREEN] 委派 /bdd） |
依 tasks.md 逐 phase 落 code 與測試 |
| 人工檢查 | pnpm review:ui（GUI）；批次前先 /review-readiness-scan 看哪些 ready |
UI / 資料類 manual review |
| 提交 | /commit |
依功能分組走品質閘門提交（所有 commit 的唯一入口） |
不確定專案當前該走哪一站：先讀 specs/plans/ 最新的 plan package 與它的 tasks.md，再按使用者目標接續。沒宣告 aixbdd 的 repo 整條主流程不適用——那裡的生命週期是「待辦來源 → tasks/<date>-<slug>.md → /wt → /commit」。
On-ramps（從症狀進入）
- 遇到 bug / 異常行為 → 先查根因（
/wt隔離後調查）；動到規格才回/specify〔aixbdd〕 - 要看 UI 畫面 / 截圖驗證 →
/review-screenshot（統一截圖入口；第一手是 Pi--model gemini --effort high，見該 skill） - 專案還沒有可重跑的 app control／feature map →
/verification-create（建立 consumer-ownedverify-<app>skill） - 既有 verification skill／feature map 要對帳 source 與 live behavior →
/verification-maintain（clean是零 branch／零 commit／零 PR 的成功結果） - 要動 code 而還在 main working tree →
/wt（開 worktree 隔離；/wt A: ... B: ...可並行多條 task） - implementation plan 內有多個獨立 task 想並行 →
/subagent-dev（同 session 派 subagent；跨 change 的並行仍走/wt） - session 要收尾 / 交接 →
/handoff（有 in-progress 工作寫交接；沒有則整理 HANDOFF.md 推薦 outstanding） - 要把待辦無人值守推完（plan package / tasks 檔 / HANDOFF / tech-debt / ROADMAP）→
/work-loop（自主推進 loop；一次性任務不適用） - 外部新資訊要改需求 →〔aixbdd〕
/specify開新的NNN-<slug>；舊 plan package 是歷史，NEVER 回頭覆寫 - 問規格內容 → 直接讀
specs/truth/**（對非 owner skill 唯讀）與該 plan package 的spec.md - 安全視角掃 changed code →
/security-review
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 · +1 lines 6d7472b0745e
- 2d ago Changed 01cbb21acde6
- 3d ago Changed · +5 lines · -2 tokens per session 6153471e40fc
- 5d ago Changed 963b48cde7d7
- 8d ago First seen · 86 lines · 48 tokens per session scan A 3449cbc120fa
guide is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,991 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 2026-09-03.
Other skills, from other repositories
run-feedback
Use when a run of a workflow, skill, command, or test produced errors or friction worth keeping, or when executing the end-of-run Retro Global Protocol — collect findings into the feedback inbox, triage them (defect / work-item / noise), and file defects into the known-issues ledger or work-items into the backlog. NOT…
loop
Poll WritBase for top tasks and work through them autonomously. Use when you want to process the task queue, auto-work, or run the work loop.
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
cron-manager
A command-line manager for scheduled tasks, which are jobs that run at specified times or intervals. It handles creating, viewing, changing, deleting, enabling, disabling, running, and reviewing the history of those tasks.
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…