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 verification-creategit 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/verification-create)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/verification-create"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/verification-create/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/verification-create"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/verification-create.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 | $0.00014 | $0.01363 |
| Opus 5 | $0.00007 | $0.00681 |
| Sonnet 5 | $0.00003 | $0.00273 |
| Haiku 4.5 | $0.00001 | $0.00136 |
Grade A, and why
verification-create 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Drive | 現有 Playwright/Cypress/PTY/curl/debug harness；沒有才選通用工具 | How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create project verification infrastructure
本檔的
<skills-root>指該 runtime 的 skill 投影根目錄：Claude.claude/skills/、Codex.agents/skills/、Cursor.cursor/skills/。NEVER 在別的 runtime 上照抄 Claude 的字面路徑；找不到該目錄就回報標準未送達，不猜一個。
把 pstack 的 create-verification-skill 內化成 clade 的跨 runtime 版本。產物寫給下一個冷啟動 agent 使用，不是寫給本次 session 自己看的說明。
Decision boundary
- 已存在
<skills-root>/verify-*/features/README.md，需求是更新或重跑 → invoke/verification-maintain。 - 需求只是替目前 change 收集 UI 截圖 → invoke
/review-screenshot。 - 需求是 implementation 與規格對帳 → 讀
specs/truth/**與該 work 的 carrier 自行對帳；動到規格回交 truth owner skill。 - 本 skill 只建立 verification infrastructure；不替某個產品 change 宣告驗收通過。
Output contract
建立一個 consumer-owned、tracked 的 canonical skill：
<skills-root>/verify-<app>/
├── SKILL.md
├── features/
│ ├── README.md
│ └── <feature>.md
└── scripts/ # 只有 repo 真的需要 helper 才建立
.agents/、.codex/、.cursor/ 是投影面，NEVER 直接把 canonical source 寫進那些目錄。現有 sync-to-codex／sync-to-cursor 負責跨 runtime 投影。
Workflow
1. Interview the repo
從 repo 與實跑結果回答以下六欄；能自行找到的資訊不問使用者：
| 欄位 | 必須查明 |
|---|---|
| Surface | 使用者實際碰的 Web、CLI/TUI、desktop、API、mobile 或 library surface |
| Launch | repo 官方啟動指令、port、env、seed、auth、ready signal、teardown |
| Doctor | 一條唯讀 health check，能辨認 instance、revision、port ownership 與 auth |
| Drive | 現有 Playwright/Cypress/PTY/curl/debug harness；沒有才選通用工具 |
| Observe | screenshot、ARIA、transcript、response、log、exit code、side effect |
| Isolate | port、data dir、profile、session 與 concurrent run 的隔離方式 |
若 checkout 不能 build 或 launch，停止並精確回報 baseline blocker。只有與產品行為無關的缺失靜態目錄或 sample config 才可建立 verification scaffolding，且 cleanup 必須移除。
2. Generate verify-<app>
SKILL.md 必須有可發現的 name／description，並依序包含：
Launch— exact command、ready signal、teardown；server/UI 使用 verification lease。Doctor— first drive、fresh session 與 surprising failure 後都可重跑的唯讀檢查。Drive— repo 現有 stable selector／command；UI 優先 role、accessible name、route 與既有 test handle。Evidence— real user path、action + result、second-view side-effect proof、artifact location。Cleanup— 只清自己建立的 process／scratch state，NEVER 依 process name 殺程序，NEVER 刪 evidence。Helpers— 每支 helper 的 invocation、inputs、outputs 與 executable bit。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +4 lines 12faca1370b1
- 6d ago First seen · 107 lines · 14 tokens per session scan A 3d08de6c1972
verification-create is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 1,363 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
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"…
python
Python development with ruff, mypy, pytest - TDD and type safety.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
python-testing-patterns
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
bug-fix
Regression-first TDD bug fix workflow with real tests. Use when: fixing bugs, resolving regressions, addressing runtime errors, debugging failures, or when the user reports something broken. Triggers on words like: bug, broken, error, crash, regression, not working, fix.