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 screenshots-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/screenshots-archive)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/screenshots-archive"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/screenshots-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/screenshots-archive"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/screenshots-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 | $0.00077 | $0.02481 |
| Opus 5 | $0.00039 | $0.01241 |
| Sonnet 5 | $0.00015 | $0.00496 |
| Haiku 4.5 | $0.00008 | $0.00248 |
Grade A, and why
screenshots-archive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
截圖歸檔(Screenshots Archive)
把已完成人工檢查的截圖資料夾從 screenshots/<env>/<topic>/ 搬到 screenshots/<env>/_archive/YYYY-MM/<topic>/,讓 ls screenshots/<env>/(排除 _archive/)= 目前 pending review 清單。
觸發時機
- 「歸檔截圖」「sweep screenshots」「清掉舊的截圖資料夾」
- 「change X 的截圖歸檔」(指定)
/review-archive完成後自動呼叫(指定 change 模式)- 一件工作標
work.done後自動呼叫(指定 work 模式)
輸入
- 指定 work:
/screenshots-archive change <work-slug>→ 只搬該工作對應的 topic(review-archive 與收尾流程自動觸發走此模式) - 指定 topic:
/screenshots-archive <topic-name>→ 直接搬該 topic(跳過對齊檢查,需 user 確認) - 未指定:sweep 所有「在
docs/manual-review-archive.md已收錄」且「screenshots/<env>/<topic>/仍存在頂層」的 topic
流程
Step 1: 列出候選 topic
掃所有 environment(不只 local):
for env in local staging production; do
[ -d "screenshots/$env" ] || continue
for d in "screenshots/$env"/*/; do
[ -d "$d" ] || continue
name=$(basename "$d")
[ "$name" = "_archive" ] && continue
echo "$env|$name"
done
done
Step 2: 對齊 manual-review-archive
讀取 docs/manual-review-archive.md,抽出每個 ## YYYY-MM-DD — \`` 標題的 change-name 集合。
Mode A — 未指定範圍(sweep all aligned)
對 Step 1 的候選:
- candidate.name ∈ archived_changes → 可 sweep
- candidate.name ∉ archived_changes → 跳過,記錄原因「未在 manual-review-archive 找到對應 change」
候選有跳過項目時,回報「N 個 topic 已對齊可 sweep / M 個 topic 未對齊跳過」,列出跳過清單,不追問是否強制。
Mode B — 指定 work(含 review-archive 與收尾流程自動觸發)
/screenshots-archive change <work-slug>:
-
跨所有 environment 掃
screenshots/<env>/<work-slug>/是否存在 -
找到對應 topic:直接 sweep(信任 caller — 它已確認該工作結束;不再對齊 manual-review-archive,避免直接收尾的路徑被擋)
-
找不到對應 topic → 先跑 backend-only 判定,命中就 noop、NEVER 追問:
# carrier 有兩種形狀,兩處都探 carrier=$(ls -d specs/plans/*-<work-slug>/tasks.md tasks/*-<work-slug>.md 2>/dev/null | head -1) spec=$(dirname "$carrier")/spec.md grep -q 'No user-facing journey (backend-only)' "$spec" 2>/dev/null && echo BACKEND_ONLY grep -q 'pre-handoff-verdict: intentional, reason: backend-only' "$carrier" 2>/dev/null && echo BACKEND_ONLY awk '/^## 人工檢查/{mr=1} mr && /\[review:ui\]/{found=1} END{exit found}' "$carrier" 2>/dev/null && echo BACKEND_ONLY
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.
- 2d ago Changed · +18 lines · +2 tokens per session f3935d052769
- 7d ago First seen · 143 lines · 75 tokens per session scan A 249136406a6e
screenshots-archive is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,481 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 2026-09-03.
Other skills, from other repositories
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.
ima-notes
A note-taking tool that uses the IMA service to search, read, list, create, and append notes. IMA is the connected note system it communicates with.
testing-principles
Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.
test-driven-development
Enforces TDD discipline with RED-GREEN-REFACTOR cycle. Use when writing new features, fixing bugs, or refactoring code. Ensures tests genuinely verify behavior.
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"…