video-narrative-arc

video-narrative-arc is a skill for Claude Code from AnastasiyaW/codex-claude-code-config. It costs 167 tokens per session (2,460 once invoked), scanned A, original, MIT.

A collection of timestamped story structures for product videos and advertisements, matched to different video lengths and goals.

In plain words
What is it for?
Use it to choose a narrative structure and create scripts, scene plans, or storyboards for short ads, demos, launches, and brand stories.
Why use it?
It avoids starting every script from scratch or presenting a product as an unstructured list of features.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-code-config plugin — 57 skills, 8 agents shipped together

Good fit Use it to choose a narrative structure and create scripts, scene plans, or storyboards for short ads, demos, launches, and brand stories.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anastasiyaw/codex-claude-code-config/video-narrative-arc
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 AnastasiyaW/codex-claude-code-config --skill video-narrative-arc
Clone the repo
git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config

Made for: Claude Code.

Or install claude-code-config, the plugin that ships this one along with the rest of its 57 skills, 8 agents.

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 video-narrative-arc

README.md
[![agentmods](https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/video-narrative-arc/github.svg)](https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/video-narrative-arc)
Your own site
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/video-narrative-arc"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/video-narrative-arc/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 video-narrative-arc

Your own site · 80×15
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/video-narrative-arc"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/video-narrative-arc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,460 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 $0.00167 $0.02460
Opus 5 $0.00084 $0.01230
Sonnet 5 $0.00033 $0.00492
Haiku 4.5 $0.00017 $0.00246

Measured 10d ago against content hash 1fff32698ff7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

video-narrative-arc 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 10d 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.

skills/video-production/video-narrative-arc/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Narrative Arc Templates

Proven narrative structures for product videos. Pick a template, fill slots from your Product Brief, get a timestamped script with emotional beats.

Rule #1: Brief First

ALWAYS create a Product Brief (use product-meaning-extractor) BEFORE choosing a template. Without a brief, you'll write generic feature lists.

Template Selection

Duration Best For Template Emotional Arc
10-15s Social ads, teasers Pattern Interrupt Surprise → Curiosity → Action
15-20s Product awareness Problem-Solution Flash Pain → Relief → Action
30s Product demos Hook-Pain-Demo-Proof-CTA Attention → Recognition → Desire → Trust → Action
45-60s Launches, explainers Apple Keynote Mini Understanding → Frustration → Hope → Amazement → Delight
60-90s Brand stories, pitches Full Story Arc Empathy → Tension → Discovery → Wonder → Inspiration

Template 1: Pattern Interrupt (10-15s)

For: TikTok, Reels, YouTube Shorts, social ads.

[0-3s] INTERRUPT
  Break the scroll. Unexpected visual or bold text on dark bg.
  Use: provocative question, shocking stat, or visual contrast.
  Example: "Why are you still [painful manual task]?"

[3-7s] CURIOSITY GAP
  Show what's possible. Product in action, before→after, result.
  One phrase that captures the transformation.
  Example: Split-screen transformation in real time.

[7-12s] PROMISE + CTA
  Product name + key benefit + action.
  Example: "[Product]. [One-line value]. Try free."

Key rule: First frame must have useful/surprising information. No logos, no gradients, no decorative intros.


Template 2: Problem-Solution Flash (15-20s)

For: Instagram/Facebook ads, product awareness.

[0-3s] HOOK - Customer pain in THEIR words
  Dark bg, large text, one line from Customer Language Bank.
  Example: "45 minutes. Per. Photo."
  BEAT: TENSION

[3-8s] AGITATE - Stack the problems (2-3 rapid pain points, 1.5s each)
  Example: "Scratches. Noise. Shadows. Every. Single. Time."
  BEAT: FRUSTRATION PEAK

[8-10s] PIVOT
  Visual shift (dark→light, blur→sharp). Two words max.
  Example: "Not anymore." / "Until now." / "There's a better way."
  BEAT: RELIEF BEGINS

[10-16s] SOLUTION - Product in action
  Show the unique mechanism (from brief), not just the name.
  Example: "AI retouching. Original resolution. Editable .PSD."
  BEAT: DESIRE

[16-20s] CTA
  Low-friction call to action. Logo + URL + free offer.
  Example: "Try free. No signup. [url]"
  BEAT: ACTION

Read the full file on GitHub · 241 lines

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. 10d ago First seen · 241 lines · 167 tokens per session scan A 1fff32698ff7

Subscribe to this mod's changes

video-narrative-arc is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed 2d ago), licensed MIT. It adds 167 tokens to every session and 2,460 once invoked, about $0.0008 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.