Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starternpx agentmods add skills/yudefine/nuxt-supabase-starter/review-readiness-scanWrote 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-readiness-scan)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/review-readiness-scan"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/review-readiness-scan/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-readiness-scan"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/review-readiness-scan.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 | $0.00038 | $0.02400 |
| Opus 5 | $0.00019 | $0.01200 |
| Sonnet 5 | $0.00008 | $0.00480 |
| Haiku 4.5 | $0.00004 | $0.00240 |
Grade A, and why
review-readiness-scan 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-readiness-scan
主動掃描 consumer 端所有 active change 的 ## 人工檢查 區塊,把「已 ready / 尚未 ready」分組寫入 HANDOFF.md,讓使用者能在合適時機批次跑 pnpm review(從 clade home),而不是每條 change 個別開 GUI 才知道沒準備好。
前置:consumer 必須已從 clade 散播到 scripts/review-gui.ts(各 consumer 預設都有;若沒有,跑 pnpm hub:check 確認)。
Step 1 — 跑 headless scan
cd ~/offline/clade
node vendor/scripts/review-gui.ts --scan
預設從 clade home 掃,輸出會聚合 consumers.local 內所有 consumer + worktree。若是 CI / debug 要只掃單一 consumer,才改用 node vendor/scripts/review-gui.ts --repo <consumer-path> --scan。
reviewPort 是 loopback probe port。後續 handoff MUST 原樣複製 entry 的 reviewUrl(永遠 https://review-gui.<maintainer-domain> + reviewPath),不要硬寫 5174,也不要把 probeUrl 交給人。
輸出 JSON(schema: review-readiness-scan/v2)到 stdout,結構:
{
"schema": "review-readiness-scan/v2",
"generatedAt": "<ISO8601>",
"repoRoot": "<abs>",
"reviewHost": "127.0.0.1",
"canonicalHost": "review-gui.<maintainer-domain>",
"reviewPort": 5174,
"counts": {
"ready": N,
"notReady": M,
"buckets": { "ready": N, "readyForEvidence": N, "applyInProgress": N }
},
"ready": [ { "name": "<change>", "consumerId": "<consumer-a>",
"changeKey": "<consumer-a>:<change>",
"reviewUrl": "https://review-gui.<maintainer-domain>/review/<consumer-a>:<change>",
"probeUrl": "http://127.0.0.1:5174/review/<consumer-a>:<change>",
"bucket": "ready", "pending": N, "issued": N, "total": N } ],
"notReady": [ { "name": "<change>", "consumerId": "<consumer-a>",
"changeKey": "<consumer-a>:<change>",
"reviewUrl": "https://review-gui.<maintainer-domain>/review/<consumer-a>:<change>",
"bucket": "readyForEvidence", "pending": N, "issued": N, "total": N,
"readinessHits": N, "malformed": N,
"hitsByCode": { "UI_ITEM_NO_URL": 2, "REVIEW_UI_BACKEND_ROUNDTRIP": 1 },
// evidenceMissing:item 標了 [verify:e2e/api/ui] 但缺對應 (verified-*:) annotation。
// 落 notReady 群的另一條觸發路徑(與 readinessHits / malformed 並列),各 entry 一個 item。
"evidenceMissing": [ { "itemId": "#3", "description": "...",
"kinds": ["e2e", "api", "ui"] } ] } ],
"buckets": {
"ready": [ /* 可直接開 reviewUrl 給 user 做 GUI review */ ],
"readyForEvidence": [ /* 實作已接近完成,先跑 Verify Channel Pass 補 evidence */ ],
"applyInProgress": [ /* implementation 還沒完成,不該補 evidence */ ],
"applyBlocked": [ /* impl 卡外部 blocker(@apply-blocked marker),交還 user,不要硬推 */ ],
"healthCheckNeeded": [ /* manual-review pattern hits,先 ingest/fix tasks.md */ ],
"awaitArchiveWalkthrough": [ /* 只剩 [discuss],走交付前收尾 walkthrough */ ],
"awaitingUserDecision": [ /* Claude 已標 (awaiting-user-decision:),等 user 商業拍板,不要硬推 */ ],
"feedbackGiven": [ /* user 已標 issue 或 verify pending,交回 Claude 處理 */ ]
}
}
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 56751c339465
- 3d ago Changed · +3 lines e1b47617197c
- 8d ago First seen · 155 lines · 38 tokens per session scan A a356a6661e1b
review-readiness-scan is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 2,400 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
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…
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
prd-v07-implementation-loop
Execute implementation within EPICs following test-first development, continuous SoT updates, and code traceability during PRD v0.7 Build Execution. Triggers on requests to start building, implement an epic, begin coding, or when user asks "start building", "implement epic", "coding", "development", "build execution"…
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"…
implementation-phase
Executes implementation tasks using Test-Driven Development, prevents code duplication through anti-duplication checks, and maintains quality through continuous testing. Use when implementing features from tasks.md, during the /implement phase, or when the user requests TDD-based implementation. (project).