What is video-add-captions?

A video-editing workflow for placing word-timed captions on an Open Recut program. It uses a transcript and timeline to create a transparent caption layer that is added to the final video.

It helps group caption text, choose and review a visual style, render the caption overlay, and register it for the shared delivery render.

It keeps captions aligned with spoken words and preserves space for subtitles when other graphics are added later. It also separates caption work from transcription, cutting, and colour changes.

video-add-captions — Skill for Claude Code and Codex by WhiteTowerAI

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/WhiteTowerAI/cut-as-code

agentmods

npx agentmods add skills/whitetowerai/cut-as-code/video-add-captions

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/whitetowerai/cut-as-code/video-add-captions.svg)](https://agentmods.dev/skills/whitetowerai/cut-as-code/video-add-captions)

Your own site

<a href="https://agentmods.dev/skills/whitetowerai/cut-as-code/video-add-captions"><img src="https://agentmods.dev/badge/skills/whitetowerai/cut-as-code/video-add-captions.svg" alt="Measured on agentmods" height="20"></a>

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,111 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 warn 7 Sept 2026

SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium MCP Rug Pull · line 19
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium Excessive Agency · line 310
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 349
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
medium Excessive Agency · line 315
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00061	$0.07111
Opus 5	$0.00030	$0.03556
Sonnet 5	$0.00012	$0.01422
Haiku 4.5	$0.00006	$0.00711

Measured 8d ago against content hash cf587020397e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

video-add-captions 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (public/gsap.min.js), 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/video-add-captions/SKILL.md · 757 lines

How it starts

The opening of the file, as written. The whole thing — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Add Captions

Dependencies

/video-understand is a prerequisite. Run it first so captions use the validated word-level transcript and canonical timeline. Before starting, verify that it is installed. If it is not, warn the user that this prerequisite is missing and stop before processing media.

Require ffmpeg/ffprobe on PATH, Python with Pillow, and Node.js >= 22 (for the .mjs scripts and npx hyperframes, fetched on demand). hyperframes render/snapshot drives a headless Chrome — it manages its own chrome-headless-shell, and falls back to a system Chrome (set CHROME to override) when the cached one is unusable. Check these before processing media.

Scope

This skill owns caption grouping, style selection, review, and the transparent caption track. It does not transcribe, cut, retime, grade, reframe, or choose the delivery audio policy.

Run captions before content cards and graphic motion whenever either is selected. The approved caption layout establishes a reserved subtitle region that both later operations must keep clear. This relative order also applies when only one pair is active.

Use video-understand first. If a cut exists, caption the active program timeline; do not treat source transcript seconds as program seconds.

Protocol Inputs

Required:

work/project.json
work/understand/transcript.json, with word-level source timestamps
work/understand/media.json
work/timeline.json
the source video named by work/project.json

The timeline is the only source-to-program mapping. All ranges are half-open [start_s, end_s). scripts/build_captions.py uses the shared projectlib.map_transcript_to_timeline; words in dropped source ranges disappear, retained words move to program time, and cues always break at clip boundaries.

Durable Outputs

work/captions/
|-- captions-plan.json
|-- caption-spatial-context.json (only for eligible B-roll composites)
`-- caption-interaction.json
work/cache/captions/
|-- preview-project/
|-- preview-snapshots/
|-- overlay-project/
`-- overlay-frames/frame_000001.png ...
review/05-captions/
|-- captions.srt
|-- captions-style-review-<UUID>.html
|-- captions-style-review.html
|-- captions-review.html
|-- preview-early.png
|-- preview-middle.png
|-- preview-late.png
|-- preview-no-caption.png
|-- captions-evidence.json
`-- captions-summary.md

Read the full file on GitHub · 757 lines

Files

What ships with it

60 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.

8d ago First seen · 757 lines · 61 tokens per session scan A cf587020397e

Subscribe to this mod's changes

video-add-captions is a skill published in the GitHub repository WhiteTowerAI/cut-as-code (11 stars, last pushed 15d ago), licensed MIT. It adds 61 tokens to every session and 7,111 once invoked, about $0.0003 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.

Claude Code Creative and media agent-skills ai-video-editing codex short-video video-editing

smart-video-editor

A video-editing workflow that examines raw clips, selects usable moments, arranges them into a story, and renders a finished video with FFmpeg.

Fagan1024/smart-video-editor · 120 tokens

create_profile_style_skill

A workflow for turning a person's video-editing habits into a reusable editing skill file. It examines choices such as pacing, storytelling, audio, subtitles, colour, transitions, and recurring editing rules.

FireRedTeam/FireRed-OpenStoryline · 64 tokens

subtitle_imitation_skill

A video-writing workflow that rewrites a script to match the style of reference text supplied by the user. It uses the footage analysis and reference sample while keeping the script tied to what is actually shown.

FireRedTeam/FireRed-OpenStoryline · 68 tokens

premiere-pro-mcp

Install, verify, troubleshoot, and operate the Adobe Premiere Pro MCP server. Use when a user wants an agent to set up Premiere MCP, connect Claude Code/Codex/Claude Desktop, control Premiere, import media, build sequences, edit timelines, apply effects, or diagnose bridge issues.

hetpatel-11/Adobe_Premiere_Pro_MCP · 64 tokens

ai_transition_editing_skill

A video-editing workflow that connects existing clips with AI-generated transitions. It can organize clips, choose background music, build a timeline, and render the finished video.

FireRedTeam/FireRed-OpenStoryline · 26 tokens

default_editing_workflow_skill

A general video-editing workflow for turning uploaded or found footage into a finished video. It covers loading clips, organizing a story, adding text, voiceover, music, and effects, then rendering the result.

FireRedTeam/FireRed-OpenStoryline · 66 tokens