agentmods.dev

auto-whiteboard-video

auto-whiteboard-video is a skill for Codex from shaomingchan/whiteboard. It costs 69 tokens per session (481 once invoked), scanned A, original, MIT.

A tool for turning a text script into a narrated whiteboard explainer video. It creates the spoken audio, subtitles, drawings, background music, and final video file.

In plain words
What is it for?
Use it to make 1920×1080 whiteboard videos from pasted text or a UTF-8 text file, including narration, illustrations, hand-drawing animation, subtitles, and music.
Why use it?
It removes the need to assemble these video parts by hand from a transcript. The fixed format also keeps the output consistent.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 50repo 3mo ago A scan SkillSpector: pass 69 tokens original MIT

Good fit Use it to make 1920×1080 whiteboard videos from pasted text or a UTF-8 text file, including narration, illustrations, hand-drawing animation, subtitles, and music.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shaomingchan/whiteboard/auto-whiteboard-video
View source ↗ shaomingchan/whiteboard
Install

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.

Any agent
npx skills add shaomingchan/whiteboard --skill auto-whiteboard-video
Clone the repo
git clone --depth 1 https://github.com/shaomingchan/whiteboard

Made for: Codex.

Wrote 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.

agentmods badge for auto-whiteboard-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/shaomingchan/whiteboard/auto-whiteboard-video/github.svg)](https://agentmods.dev/skills/shaomingchan/whiteboard/auto-whiteboard-video)
Your own site
<a href="https://agentmods.dev/skills/shaomingchan/whiteboard/auto-whiteboard-video"><img src="https://agentmods.dev/badge/skills/shaomingchan/whiteboard/auto-whiteboard-video/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.

agentmods 80×15 button for auto-whiteboard-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/shaomingchan/whiteboard/auto-whiteboard-video"><img src="https://agentmods.dev/badge/skills/shaomingchan/whiteboard/auto-whiteboard-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 481 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.00481
Opus 5.5 $0.00028 $0.00192
Sonnet 5.5 $0.00014 $0.00096
Haiku 4.5 $0.00007 $0.00048

Measured 2mo ago against content hash a7046013861e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto-whiteboard-video 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run_video.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/auto-whiteboard-video/SKILL.md · 46 lines

What it actually says

Auto Whiteboard Video

Use the repository's canonical pipeline. Do not rebuild stages manually unless troubleshooting a failed stage.

Workflow

  1. Run scripts/doctor.py from the repository root.
  2. Save pasted text as a UTF-8 .txt file under a user-approved input location when no file is provided.
  3. Choose a stable project directory under output/; reuse it when resuming.
  4. Run the wrapper below and wait for completion.
  5. Read composition_report.json and report the final MP4 path, resolution, duration, and audio/video delta.
python skills/auto-whiteboard-video/scripts/run_video.py `
  --input examples/demo_30s.txt `
  --output-dir output/demo `
  --project-dir output/demo/latest `
  --keep-temp

All arguments are forwarded to auto-whiteboard/scripts/auto_generate.py.

Locked Defaults

  • Output: 1920x1080, 30 fps.
  • Source images: near 16:9; reject clear 3:2, square, and portrait results.
  • Visual style: #F6F1E3 background, black marker lines, restrained amber, faceless round-headed people.
  • Subtitles: size 88, maximum 20 full-width CJK characters per line.
  • BGM: configured default track at -28 dB.
  • Spoken numbers and display subtitles are normalized separately.

Resume Rules

  • Reuse the same --project-dir to preserve caches.
  • Use --force-tts, --force-images, --force-whiteboard, or --force-compose only when that stage must change.
  • Do not delete the project directory to fix a single failed scene.

Success Criteria

Require both final_video.mp4 and composition_report.json. Confirm 1920x1080, single-line subtitles, and output_av_delta_seconds < 0.1 before reporting success.

Files

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.

Changes

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.

  1. 2mo ago First seen · 46 lines · 69 tokens per session scan A a7046013861e

Subscribe to this mod's changes

auto-whiteboard-video is a skill published in the GitHub repository shaomingchan/whiteboard (50 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 481 once invoked, about $0.0003 per session on Opus 5.5. 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.

Creative and mediaLearning and teaching
Related

auto-whiteboard-video compared with skills from other repositories

auto-whiteboard-video next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auto-whiteboard-videoshaomingchan/whiteboardSkill503mo agoMITA69Codex
hr-onboardingnexu-io/open-designSkill106kyesterdayApache-2.0A62Claude Code, Codex
book-mirrorgarrytan/gbrainSkill32kyesterdayMITA138Claude Code
exam-forecastanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A73Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA81Claude Code
eli5companion-inc/feynmanSkill10k6d agoMITA63Claude Code, Codex
deck-course-modulenexu-io/html-anythingSkill9.4k25d agoApache-2.0A25Claude Code, Codex