venice-video-harness: Skill for Claude Code

.agents/skills/burn-in-subtitles/SKILL.md

burn-in-subtitles is a skill for Claude Code, Codex from jordanurbs/venice-video-harness. It costs 0 tokens per session (3,676 once invoked), scanned A, original, MIT.

A process for adding permanent subtitles to a finished voice-over video. Burned-in subtitles are captions placed directly into the video image rather than kept as a separate track.

In plain words
What is it for?
It is for creating timed captions from the rendered voice-over and adding them to a trailer after the user chooses whether subtitles are wanted.
Why use it?
It prevents subtitle timing from drifting away from the actual spoken audio. It also requires a deliberate choice because the captions cannot be removed from the finished video.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is jordanurbs/venice-video-harness's own configuration. It tells Claude Code and Codex how to work on venice-video-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything venice-video-harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jordanurbs/venice-video-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jordanurbs/venice-video-harness/main/.agents/skills/burn-in-subtitles/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jordanurbs/venice-video-harness

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.

agentmods badge for burn-in-subtitles

README.md
[![agentmods](https://agentmods.dev/badge/skills/jordanurbs/venice-video-harness/burn-in-subtitles/github.svg)](https://agentmods.dev/skills/jordanurbs/venice-video-harness/burn-in-subtitles)
Your own site
<a href="https://agentmods.dev/skills/jordanurbs/venice-video-harness/burn-in-subtitles"><img src="https://agentmods.dev/badge/skills/jordanurbs/venice-video-harness/burn-in-subtitles/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 burn-in-subtitles

Your own site · 80×15
<a href="https://agentmods.dev/skills/jordanurbs/venice-video-harness/burn-in-subtitles"><img src="https://agentmods.dev/badge/skills/jordanurbs/venice-video-harness/burn-in-subtitles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,676 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: 7 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 71
    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 MCP Rug Pull · line 108
    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 MCP Rug Pull · line 272
    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 MCP Rug Pull · line 275
    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 MCP Rug Pull · line 277
    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 Agent Snooping · line 282
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 283
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00000 $0.03676
Opus 5 $0.00000 $0.01838
Sonnet 5 $0.00000 $0.00735
Haiku 4.5 $0.00000 $0.00368

Measured 12d ago against content hash 32e14a70eabc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

burn-in-subtitles 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/derive-captions.ts), 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.

.agents/skills/burn-in-subtitles/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Burn-in Subtitles for Voice-over Trailers

Produce burned-in subtitles ("hardcoded" / "open" captions) on a finished trailer when the user wants them, with timings derived from the actual rendered VO instead of estimated by hand. This skill captures the full process — including the failure modes that sent us into a multi-revision drift loop on The Grand Plutonian teaser — so the next project gets working captions on the first attempt.

Operating Rule (Mandatory)

Always ask the user before adding subtitles. Burn-in is a permanent baked-into-pixels decision and is not always wanted (cinema teasers may prefer no captions; social cuts almost always need them).

The first time you assemble a final video for a project, ask:

"Do you want subtitles burned into the trailer? (a) Yes — soft and small at the bottom, baked into the video (b) No subtitles — VO carries the meaning"

Do not assume "yes" because the trailer has dialogue / VO. Do not assume "no" because it's a cinematic teaser. Only proceed when the user has said yes.

If yes, also ask follow-ups:

  • Subtitle font size? (default 36-38px on a 720p canvas)
  • Position? (default bottom, 50px margin)
  • Opacity? (default 0.85 — soft, not harsh white)

When This Skill Applies

  • A harness project has produced a VO file (typically output/<project>/audio/vo.mp3).
  • The harness assembles a final video via ffmpeg drawtext/subtitles filters or similar.
  • The user has answered "yes" to the burn-in prompt above.
  • The VO was produced by a TTS engine (Kokoro, ElevenLabs, Qwen3) — synthesized voices with deterministic phrasing.

End-to-End Process

1. Author the VO with TTS-Safe Phrasing

The single most common failure with Kokoro and ElevenLabs is unstable phrasing causing TRUNCATION or RUNAWAY pauses. Follow these rules:

Do Don't
Use single ellipses ... for breath gaps Use doubled ellipses ...... (Kokoro silently truncates after them)
Use commas for short rhythm pauses Use repeated periods .. to fake a pause
Use , between phrases for soft breaks Use long stretches of dots inside a sentence
Write each phrase as its own line in a VO_TEXT array, joined with spaces Concatenate everything into one giant string
Test with a single regen first to measure duration Tune captions before measuring the actual VO

Read the full file on GitHub · 285 lines

Files

What ships with it

1 file 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. 12d ago First seen · 285 lines · 0 tokens per session scan A 32e14a70eabc

Subscribe to this mod's changes

burn-in-subtitles is a skill published in the GitHub repository jordanurbs/venice-video-harness (30 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,676 tokens. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens