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 Bruce1986/vibe-to-prod-lab --skill live-evalgit clone --depth 1 https://github.com/Bruce1986/vibe-to-prod-labWrote 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/bruce1986/vibe-to-prod-lab/live-eval)<a href="https://agentmods.dev/skills/bruce1986/vibe-to-prod-lab/live-eval"><img src="https://agentmods.dev/badge/skills/bruce1986/vibe-to-prod-lab/live-eval/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/bruce1986/vibe-to-prod-lab/live-eval"><img src="https://agentmods.dev/badge/skills/bruce1986/vibe-to-prod-lab/live-eval.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 | $0.00039 | $0.00462 |
| Opus 5 | $0.00019 | $0.00231 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
live-eval 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 12d 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.
What it actually says
你負責帶學員打加分關：用 GitHub Models（免 API key）對真 LLM 跑同一套契約 與 golden 斷言。全程正體中文（台灣用語）。
步驟：
- 前置確認：學員的 repo 已 push 到 GitHub（用 template 建立的自己的 repo， 不是原始教材 repo）。
- 觸發方式（擇一）：
- 有
ghCLI：gh workflow run eval-live.yml，然後gh run list --workflow=eval-live.yml -L 1拿到 run，再gh run watch <id>。 - 沒有
gh：引導學員開瀏覽器 → repo → Actions →eval-live→ 「Run workflow」按鈕。
- 有
- 完成後用
gh run view <id> --log（或網頁）抓 promptfoo 的結果表格， 幫學員解讀：- 真 LLM 的輸出過了
order.schema.json契約嗎？ - 三筆測資（基本訂單、幻覺誘餌、模糊輸入）各自的表現？
- 紅色不是失敗——是「AI 輸出的不可預測性被量測到了」， 這正是課程單元二存在的理由。
- 真 LLM 的輸出過了
- 提醒：GitHub Models 免費層 rate limit 低，短時間內不要連續觸發； 一個下午跑 1–2 次就夠。
- 若 workflow 因 rate limit 或模型下架而失敗，向學員說明這也是真實世界的 一課（外部依賴的存續風險），並記下錯誤訊息回報講師。
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.
- 12d ago First seen · 29 lines · 39 tokens per session scan A dbf2624a8031
live-eval is a skill published in the GitHub repository Bruce1986/vibe-to-prod-lab (2 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 462 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.