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.
git 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/rules/yudefine/nuxt-supabase-starter/agent-self-verification.screenshot-evidence)<a href="https://agentmods.dev/rules/yudefine/nuxt-supabase-starter/agent-self-verification.screenshot-evidence"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/agent-self-verification.screenshot-evidence/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/rules/yudefine/nuxt-supabase-starter/agent-self-verification.screenshot-evidence"><img src="https://agentmods.dev/badge/rules/yudefine/nuxt-supabase-starter/agent-self-verification.screenshot-evidence.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 | $0.00000 | $0.02396 |
| Opus 5 | $0.00000 | $0.01198 |
| Sonnet 5 | $0.00000 | $0.00479 |
| Haiku 4.5 | $0.00000 | $0.00240 |
Grade A, and why
agent-self-verification.screenshot-evidence scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**NEVER** 用 `curl POST` / `$fetch` / browser form submit 臨時建 ephemeral data 拍截圖 —— ephemeral data 在任何 db:reset 後消失，截圖全部 stale，被迫重建 + 重拍（per [[pitfall-verify-evidence-ephemeral-fixture-washed-by-db-reset]]）。 How it starts
The opening of the file, as written. The whole thing — 105 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.
Agent Self-Verification — 視覺 evidence 收集
從 [[agent-self-verification]] 抽出（2026-07-31）。那份是 always-load 的 meta rule（NEVER 句型黑名單 + fallback chain + 派工前預檢）；本檔是真的在收截圖 evidence 時才用得到的操作層，對應主檔 § Hard rule 的 MUST 5 / 7 / 8 / 9。
主檔的四條一句話 MUST 是契約，本檔是它們的執行細節與 canonical pattern。兩邊衝突時以主檔為準。
載體分流：capture、DOM、auth 與 screenshot path 的具體命令由 target adapter 提供；本檔只規定每一輪的 shared ordering and evidence contract。缺少 verified carrier 時保持 blocked，並照 MUST 3 寫完整 failure trail。
MUST 3 — (deferred: ...) annotation 的 failure trail 格式
逐層列出 (a)(b)(c)(d) 的嘗試結果。逐字範例：
下面這個 fence 是 live fixture：
test/rule-example-parser-contract.test.ts會現場把它抽出來 餵進vendor/scripts/review-gui.parser.ts。改動它（含標點全半形）等於改動 parser 的驗收條件—— 測試紅了就是兩邊真的不一致，NEVER 為了讓它綠而去改測試的期望值。範例被整段搬走時， 該測試的抽取數守門會失敗，不會靜默失去保護。
（deferred: tried (a) dev-login route 限 E2E user only, edit 後 typecheck fail / (b) service_role 不適用（需驗 RLS 邏輯）/ (c) OAuth callback 撞 redirect URI mismatch / (d) target visual verifier fail with "login required"。剩需 user 親自跑）
MUST 5 — verify:ui / verify:e2e evidence 的 fixture MUST 在 seed.sql
Step 8a evidence collection 發現 seed 缺 fixture（verify item 引用的 entity ID 在 seed.sql 不存在）時，MUST 先把 fixture INSERT 寫進 seed.sql → pnpm supabase:sync → pnpm db:reset → 再拍截圖。
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.
- 3d ago Changed · -27 lines 769670b8f6d1
- 7d ago Changed · +2 lines 873049776114
- 11d ago First seen · 130 lines · 0 tokens per session scan A 26932f027729
agent-self-verification.screenshot-evidence 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 2,396 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.