make-viral-video

make-viral-video is a skill for Claude Code from sonichi/sutando. It costs 48 tokens per session (2,143 once invoked), scanned A, original, MIT.

A tool for producing a short, landscape news-explainer video from one source URL or news event. Each video centers on one memorable fact, image, or quote and includes a script, fetched assets, a rendered MP4, and validation files.

In plain words
What is it for?
Use it to make roughly 30–60-second 1280×720 news videos with narration, images, H.264 video, AAC audio, and build logs that can be independently checked.
Why use it?
It turns a source story into a focused video package without requiring separate manual work for scripting, asset collection, editing, and technical checks.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: positional $N argument; mentions Codex.

Good fit Use it to make roughly 30–60-second 1280×720 news videos with narration, images, H.264 video, AAC audio, and build logs that can be independently checked.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sonichi/sutando/make-viral-video
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 sonichi/sutando --skill make-viral-video
Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando

Made for: Claude Code.

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 make-viral-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonichi/sutando/make-viral-video.svg)](https://agentmods.dev/skills/sonichi/sutando/make-viral-video)
Your own site
<a href="https://agentmods.dev/skills/sonichi/sutando/make-viral-video"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/make-viral-video.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,143 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00048 $0.02143
Opus 5 $0.00024 $0.01071
Sonnet 5 $0.00010 $0.00429
Haiku 4.5 $0.00005 $0.00214

Measured 8d ago against content hash 76020664156c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

make-viral-video 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 8d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/asset_cache.py, scripts/build.sh, scripts/render.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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Fetch the source URL (curl + Playwright fallback for JS-rendered pages)
skills/make-viral-video/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

make-viral-video

Build a short (~30-60s, 1280×720 landscape, h264+aac) news-explainer video around a single source URL or news event. Designed for shareability via the specificity-shape framing (Chi's pick 2026-05-09): one striking number, image, or quote — not a comprehensive overview.

Distinct from Lucy's recursive-meta-explorer v8-v12 lineage (which optimized for completeness). This skill optimizes for the one moment that makes someone share.

Usage

bash "$SKILL_DIR/scripts/build.sh" --topic "DoW UAP file release" --source "https://war.gov/UFO" --out results/

Produces:

  • results/viral-{ts}/video.mp4 — the rendered video
  • results/viral-{ts}/script.md — the narration script
  • results/viral-{ts}/assets/ — fetched images with hash + validation log
  • results/viral-{ts}/build.log — full build trace (codex iterations + validation results)
  • results/viral-{ts}/verify.sh — script to independently re-validate the build

Required tools

  • python3 ≥ 3.10 (PIL for frame composition)
  • ffmpeg (encode + ffprobe gate)
  • gemini API key (free tier, default) OR openai API key (fallback)
  • Codex CLI (for script generation per pass)

Architecture

Three-phase build with self-heal

Phase 1 — Source ingestion + script generation

  • Fetch the source URL (curl + Playwright fallback for JS-rendered pages)
  • Codex generates a narration script + asset manifest with the specificity-shape framing:
    • One striking opening fact (the hook)
    • 3-5 supporting details (context)
    • One closing twist or open question (the share moment)
  • Asset manifest is JSON: [{"url": "...", "alt": "...", "purpose": "hook|support|closer"}]

Phase 2 — Asset validation (the self-heal loop)

For each asset URL:

  1. Fetch
  2. Hash check: refuse duplicates (catches the v12 PR46-404-dupe pattern)
  3. Content-type check: must be image/* or fall back
  4. 404 detector: known-404-page hash list + OCR keywords ("404", "page not found", "Not Found")
  5. Resolution check: ≥600×400 (sub-thumb assets are not viral-grade)
  6. Re-fetch on failure with up to 2 retries
  7. If validation still fails → script regen with that asset removed, NOT a silent skip

Read the full file on GitHub · 170 lines

Files

What ships with it

8 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. 8d ago First seen · 170 lines · 48 tokens per session scan A 76020664156c

Subscribe to this mod's changes

make-viral-video is a skill published in the GitHub repository sonichi/sutando (393 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 2,143 once invoked, about $0.0002 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 2026-08-30.