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 agentmods add skills/understudy-ai/understudy/prepare-delivery-previewnpx skills add understudy-ai/understudy --skill prepare-delivery-previewgit clone --depth 1 https://github.com/understudy-ai/understudyWrote 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/understudy-ai/understudy/prepare-delivery-preview)<a href="https://agentmods.dev/skills/understudy-ai/understudy/prepare-delivery-preview"><img src="https://agentmods.dev/badge/skills/understudy-ai/understudy/prepare-delivery-preview.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 | $0.00015 | $0.00173 |
| Opus 5 | $0.00008 | $0.00086 |
| Sonnet 5 | $0.00003 | $0.00035 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
prepare-delivery-preview 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 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.
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
prepare-delivery-preview
Overall Goal
Prepare the delivery preview payload and metadata for human approval.
Inputs
- target.json
- brief.md
- draft.mp4
- cover.png
Outputs
- delivery/preview.json
Staged Workflow
- Draft the title, summary, and metadata.
- Point the preview payload at the cover and draft video.
- Write
delivery/preview.json.
Tool Route Options
- shell for deterministic JSON output
Detailed GUI Replay Hints
- None. Delivery should only happen after preview approval.
Failure Policy
- Keep the last valid preview payload if a new one cannot be generated safely.
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 First seen · 43 lines · 15 tokens per session scan A b6ecb1c17b37
prepare-delivery-preview is a skill published in the GitHub repository understudy-ai/understudy (456 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 173 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 2026-08-30.
Other skills, from other repositories
vrm-springbone-physics
Debugging and fixing VRM SpringBone physics issues in three-vrm, including hair/clothing physics that flies upward, sticks out horizontally, or behaves unnaturally.
vrm-mtoon-outline
Adjusting VRM MToon material outline thickness in three-vrm. Covers outline width modes, property access, and how to fix outlines that appear too thick when models are scaled.
3d-camera-interaction
Three.js 中处理 3D 模型拖拽、缩放、边界检测的正确方法。解决鼠标移动与模型移动不同步、缩放后只能看到模型一部分等问题。.
gemini-openai-api
Gemini 模型通过 OpenAI 兼容 API 接入指南。包含：(1) 辅助 API 配置（summary/correction/emotion/vision），(2) extrabody 格式用于控制 thinking，(3) 响应格式处理（markdown 代码块）。当需要将 Gemini 作为辅助模型接入、配置 thinking 参数、或处理 Gemini API 返回格式时使用。.
ssr-hydration-scraping
Best practices for extracting data from modern React/Vue SSR pages (like Next.js or Nuxt.js) by targeting hydration state blocks (NEXTDATA, NUXT) using regex and jmespath, avoiding brittle DOM selector scraping.
tts-error-reporting
Convention for reporting errors from multiprocessing TTS workers to the main process frontend. Use this skill when modifying, adding, or debugging TTS workers in ttsclient.py to ensure connection errors, quotas, and API limits correctly display Toast notifications to the user rather than failing silently.