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-maintaingit 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-maintain)<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/verification-maintain"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/verification-maintain/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-maintain"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/verification-maintain.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 | $0.00015 | $0.01485 |
| Opus 5 | $0.00008 | $0.00743 |
| Sonnet 5 | $0.00003 | $0.00297 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
verification-maintain 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain 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。
Feature map 會隨產品改動而腐化。本 skill 對每一個 feature 做 source reconciliation 與 live drive，但只維護 verification infrastructure，NEVER 在同一輪修產品 code。
Outcomes
每次只能選一個：
| Outcome | 必要條件 | Git／PR 行為 |
|---|---|---|
clean |
每個 feature 都有 source + live coverage，沒有值得落地的 map／harness diff | 現況結果：不建 branch、不 commit、不開 PR；dirty verification diff 必須為零 |
changed |
已 live re-prove 的 doc、map 或 owned harness correction | 只包含 target verification skill；依 consumer workflow_model 建一個 PR，或以 selective commit 落 trunk |
blocked |
coverage 無法完成，或 proven correction 無法安全落地 | 不開 PR；列出已覆蓋範圍、blocker 與 preserved evidence |
clean 是成功交付，不是「什麼都沒做」。 它必須帶 coverage 與 evidence summary，但 repository outcome 保持無 branch／無 commit／無 PR。每日 unattended run 命中 clean 時也遵守同一契約，NEVER 製造空 PR 當活動證明。
Edit scope
只可修改被維護的 <skills-root>/verify-<app>/：SKILL.md、features/ 與它自己擁有的 harness scripts。
- map 描述錯誤 → doc drift，修 map。
- app 正常但 harness 無法 drive → harness gap，修 owned harness 並 live re-prove。
- app 行為真的壞掉 → product gap，只回報；NEVER 改產品 code，NEVER 把 map 改成假裝壞行為正確。
Pass
0. Locate the target
找 <skills-root>/verify-*/SKILL.md。零個 → 停止並 invoke /verification-create；多個 → 讓使用者指定，不靠名稱相似度猜。
1. Validate index hygiene
node <skills-root>/verification-maintain/scripts/check-feature-map.mjs \
<skills-root>/verify-<app>
修 missing／extra／duplicate／dead index entry。若修正只改結構，仍必須進 live pass 才能成為 changed。
2. Source wave
每個 feature 都要有 source evidence。依 clade routing threshold 收集：來源多時用一個 read-heavy／exploration prescan 批次處理，NEVER 照 upstream 原版無上限「一 feature 一 subagent」fan-out。
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 52d7803d1118
- 6d ago First seen · 128 lines · 15 tokens per session scan A c0b0eadcd106
verification-maintain is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 1,485 once invoked, about $0.0001 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
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.