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 reviewgit 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/review)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/review"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/review/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/review"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/review.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 | $0.00033 | $0.00861 |
| Opus 5.5 | $0.00013 | $0.00344 |
| Sonnet 5.5 | $0.00007 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
review 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 8d 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
Review lifecycle（統一入口）
review 是 review 支援生命週期的統一入口：查有沒有卡等人判（scan）、UI 截圖取證與判定（screenshot），以及已退役的 archive／screenshots 歸檔。
SOP
Phase 1 -- 判定 mode
- THINK 依使用者請求判 scan（有沒有卡等人判）、screenshot（截圖、看畫面、跑 UI 檢查清單、UI 驗收或除錯截圖）、archive 或 screenshots（已退役，走 Phase 5）；product code review 交設定好的 code-review agent，Lighthouse／performance trace 交 browser-devtools。
Phase 2 -- scan
- DELEGATE 在 consumer 根（不帶
CLADE_HOME）執行node ~/offline/clade/vendor/scripts/flow/flow.ts gates --repo-only --json，依 gate family 回報每一張卡；--require-emptyexit 2 表示判不出來，不是「沒有」。
Phase 3 -- screenshot：取證
- THINK 先讀取
rules/截圖取證與判定分工判準.md，確認本次由 Pi Gemini 取證、Opus 判定，以及各自不可用時的處置。 - WRITE 先讀取
templates/截圖取證brief.md與templates/截圖取證brief.example.md，依種類（ad-hoc／人工檢查清單／除錯）寫出逐項 item、截圖輸出路徑、URL、ready signal 與允許操作，並指定 worker 讀取references/screenshot-worker-contract.md。 - DELEGATE 主線直接執行
node <clade-vendor>/scripts/pi-dispatch.ts --brief <absolute-brief.md> --cwd <consumer-root> --label <descriptive-label> --model gemini --effort high --route routing-table --tier-basis table-row --table-row screenshot-review-verify --workspace-access mutation，依 agent-routing 的 Pi watch 收割 completion 與 evidence manifest。
Phase 4 -- screenshot：判定與回報
- DELEGATE 需要符合性 gate 時，把每張實際圖片路徑與完整 item 交給獨立 Opus 5.5 dispatch（
screenshot-match-analysis）。 - THINK 先讀取
rules/截圖證據可採性判準.md，逐張覆核 manifest 的discriminating，標 NON-EVIDENCE／UNREACHABLE。 - WRITE 回報摘要表、需人工確認項與截圖路徑（需要使用者拍板時，向使用者提問並等待回答，不自行補完未決事項）、
screenshots/<env>/<語義>/review.md位置；verify:ui由主線依 watch protocol 呼叫verify-ui-receipt.ts。
Phase 5 -- 已退役的 archive／screenshots
- THINK 先讀取
rules/歸檔停寫判準.md。 - WRITE archive：確認完成項已在 work package 打
[x]，回報「不再寫入docs/manual-review-archive.md；結論在<carrier>」後停止；screenshots：回報已停 rotate，列screenshots/<env>/頂層 topic，不搬檔。
提問載體 — Claude Code
Phase 4 需要使用者拍板時，以 Claude Code AskUserQuestion 列出每個有效選項與明確的略過選項，等回答後再往下。這只是共同提問義務在本 runtime 的載體。
What ships with it
6 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.
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.
- 8d ago Changed · -1 lines a7572ed5f384
- 9d ago Changed · -13 lines 8a9ce57f3ad5
- 19d ago Changed eb5e8356252c
- 21d ago Changed 9268ef9c80a2
- 23d ago Changed · +5 tokens per session b7d3eae4c45c
- 24d ago Changed · -1 lines b02e39308a53
- 1mo ago First seen · 57 lines · 28 tokens per session scan A 7b12f92e75d6
review is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (44 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 861 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
agentflow
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review.
dotcanvas
Author and edit a Grida .canvas board — a .canvas.json manifest plus document files (references, generated images, notes) placed on an infinite canvas. Use when working on a .canvas bundle or arranging visuals/design work spatially. For a linear deck/presentation, use the slides skill instead.
kanban-board
A Kanban board is a visual task list with columns for stages such as To do, In progress, In review, and Done. It can show filters, labels, due dates, assignees, comments, and swimlanes that group cards.
nw-fp-usable-design
Naming conventions, API ergonomics, and usability patterns for functional code.
nw-taste-evaluation
Design taste evaluation framework — DVF primary filter, Apple/Google/Jobs design principles as explicit scoring criteria, weighted decision matrix, and option ranking for the DIVERGE wave.
nw-ux-emotional-design
Emotional design and delight patterns for product owners. Load when designing onboarding flows, empty states, first-run experiences, or evaluating the emotional quality of an interface.