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 review-archivegit 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-archive)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/review-archive"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/review-archive/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-archive"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/review-archive.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 | $0.00051 | $0.01747 |
| Opus 5 | $0.00026 | $0.00873 |
| Sonnet 5 | $0.00010 | $0.00349 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
review-archive 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
人工檢查歸檔（Review Archive）
將已完成（[x]）的人工檢查項目從 tasks artifact 遷移到歸檔檔案。
觸發時機
- 使用者說「歸檔檢查」「archive review」「#1~#3 做完了」
- Spectra change 歸檔前，整理人工檢查結果
輸入
- 可指定範圍：
/review-archive #1~#5或/review-archive all - 未指定範圍時，遷移所有
[x]項目
流程
Step 1: 定位 tasks artifact
node <flow-cli> status --json
<flow-cli> 在 clade 是 vendor/scripts/flow/flow.ts，consumer 是 .clade/vendor/scripts/flow/flow.ts。由它的 origin 欄位取得該 work item 的 carrier 路徑。
讀該 carrier（tasks/<date>-<slug>.md 或 specs/plans/NNN-<slug>/tasks.md），找 ## 人工檢查 區塊。沒有對應 flow 卡時，直接讀使用者指名的獨立 review 文件。
Step 2: 識別要歸檔的項目
- 如果使用者指定範圍（如
#1~#3）→ 取該範圍的項目 - 如果使用者說
all→ 取所有項目 - 未指定 → 只取
[x]已完成的項目 - 如果指定的項目尚未勾選
[x]，向使用者提問並等答案（見下方 § 向使用者提問）確認是否要標記完成並歸檔
Step 3: 寫入歸檔
讀取 docs/manual-review-archive.md，在 --- 分隔線後插入新區塊（最新的在最上面）：
## YYYY-MM-DD — `<change-name>`
> Specs: `<spec-1>`, `<spec-2>`
- [x] #1 實際操作功能，確認 happy path 正常運作
- [x] #2 測試 edge case — ⚠️ 空資料時缺少提示（已修）
- [x] #3 確認手機/平板響應式顯示正常
- 保留每個項目的
#N編號 - 如果項目有附註（如截圖報告中的觀察），一併帶入
- 截圖檔案路徑不寫入歸檔（截圖在 screenshots/local/ 可能被清除）
Step 4: 更新 tasks artifact
已歸檔的項目在 tasks artifact 中保持 [x]，不刪除。
如果所有項目都歸檔了，在區塊末尾加一行：
> ✅ 全部歸檔於 YYYY-MM-DD → docs/manual-review-archive.md
Step 5: 回報
已歸檔 N 項人工檢查到 docs/manual-review-archive.md：
- #1 實際操作功能 ✅
- #2 edge case ✅
- #3 響應式 ✅
回報後自動進入 Step 6 sweep 截圖；sweep 完成後合併回報尾巴附 sweep 結果（由 screenshots-archive skill 自己印出，不重複格式化）。
Step 6: 自動 sweep 截圖
歸檔完成後自動叫用 screenshots-archive change <change-name> skill，把對應截圖資料夾搬到 screenshots/<env>/_archive/YYYY-MM/。
不再 prompt 是否要做 — review-archive 完成 = 該 change 已寫入 docs/manual-review-archive.md = sweep 對齊條件 100% 滿足，沒有人為再決定一次的空間。
對齊失敗處理（極少見：topic 名與 change 名不一致）：由 screenshots-archive 內部列頂層所有候選 topic 讓 user 手選 + 「跳過」選項，本 skill 不重複 prompt。
向使用者提問
本 skill 每一次「向使用者提問並等答案」都 MUST 滿足三條，與用什麼機制問無關：
- MUST 把選項列完整，含明確的「跳過」/「不做」那一項——使用者要能選擇不動作
- MUST 等到明確答案才執行；NEVER 因為沒收到答案就用預設值往下做
- NEVER 靜默跳過該問的那一題——沒問而直接不動作，與問了得到「跳過」在結果上相同、在使用者知情上完全不同
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 · +4 lines d61c6847db4c
- 4d ago Changed · +13 lines · -26 tokens per session 576dc0caeada
- 5d ago Changed · +4 lines · -2 tokens per session bfe8c70b323e
- 8d ago First seen · 97 lines · 79 tokens per session scan A be7aa8fad01a
review-archive is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,747 once invoked, about $0.0003 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…