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 rules/yudefine/nuxt-supabase-starter/screenshot-strategyWrote 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/rules/yudefine/nuxt-supabase-starter/screenshot-strategy)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/screenshot-strategy"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/screenshot-strategy.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.04348 |
| Opus 5 | $0.00000 | $0.02174 |
| Sonnet 5 | $0.00000 | $0.00870 |
| Haiku 4.5 | $0.00000 | $0.00435 |
Grade A, and why
screenshot-strategy 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime adapter boundary
The obligations, predicates, evidence schema, failure handling, and review timing in this source are shared. Concrete browser, dispatch, question, filesystem, and command mechanics are target-native and MUST come from the selected runtime fragment at the matching adapter path. A fragment declares only the capability it can prove; an absent or unverified capability remains blocked and MUST NOT be silently replaced by a neighbouring runtime.
Screenshot Strategy
所有截圖工作都應先判斷：這是一次性探索，還是需要可重現的回歸驗證。
工具選擇
先判斷一次性探索、人工驗收、可重現回歸、多 viewport、跨瀏覽器與量測需求，再由 target adapter 選擇已驗證的 browser carrier、reproducible runner 或 measurement surface。共通判準如下：
| 需求 | 共通選擇規則 |
|---|---|
| 一次性互動與人工驗收 | target adapter 的 interactive browser carrier |
| 多 viewport、跨瀏覽器、多分頁或需重拍的回歸 | target adapter 的 reproducible browser runner |
| LCP/CLS/INP breakdown 或 heap measurement | target adapter 的 measurement-only surface |
| 不需要的上層 runtime / QA 平台 | MUST NOT 取代已批准的 target carrier |
Cloud / clean-browser fallback
遠端 provider、proxy、clean profile 與 CAPTCHA 能力都是 opt-in target capability。只有本機 carrier 確實不可用、目標允許公開資料且不需要私有登入態時，才可依 target adapter 的 consent flow 啟用；provider credential NEVER 寫入 repo。
給 user 開瀏覽器看頁面
agent 自驗、user 可見 headed navigation 與 measurement 是三種不同用途，必須使用 target adapter 明確聲明的 surface。任何 unavailable surface 都保持 blocked；NEVER 用 uncontrolled default browser 代替。
決策樹
- 需要多 viewport / responsive？→ reproducible browser runner
- 需要跨瀏覽器或可重拍回歸？→ reproducible browser runner
- 需要一次性互動？→ target adapter 的 interactive browser carrier
- 純 performance / heap measurement？→ target adapter 的 measurement-only surface
存放方式
screenshots/<environment>/<topic>/
<environment>：local/staging/production<topic>：依用途分兩類，MUST 嚴格區分（見下節）- 評估報告可放
review.md
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 · -110 lines e96df1e60d4f
- 5d ago First seen · 358 lines · 0 tokens per session scan A f072bc9db29e
screenshot-strategy is a cursor rule published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,348 tokens. 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 cursor rules, from other repositories
playwright-agents
Playwright test agent workflows for planning, generating, and healing tests.
playwright
Playwright: e2e testing, page objects, fixtures, assertions.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.