venice-video-harness: Skill for Claude Code

.agents/skills/video-editing/SKILL.md

video-editing is a skill for Claude Code, Codex from jordanurbs/venice-video-harness. It costs 130 tokens per session (3,134 once invoked), scanned A, original, MIT.

A workflow for editing video and audio files that already exist, such as recordings, generated shots, or voice tracks. It uses text descriptions to guide editing and checks the media at selected points.

In plain words
What is it for?
Trimming speech, editing raw footage, rescuing incomplete text-to-speech renders, and assembling existing shots into a new cut.
Why use it?
It separates cutting existing media from creating new media, making it easier to remove unwanted parts, repair incomplete files, or change the order of clips.

Skill for Claude CodeCodex

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

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/video-editing/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 video-editing

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jordanurbs/venice-video-harness/video-editing"><img src="https://agentmods.dev/badge/skills/jordanurbs/venice-video-harness/video-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,134 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 48
    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 88
    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 215
    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 217
    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 208
    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 Agent Snooping · line 225
    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 226
    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 $0.00130 $0.03134
Opus 5 $0.00065 $0.01567
Sonnet 5 $0.00026 $0.00627
Haiku 4.5 $0.00013 $0.00313

Measured 11d ago against content hash 9a20aa3de157, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

video-editing 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 11d 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.

.agents/skills/video-editing/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Editing Pipeline

Parallel pipeline to the generation side of the harness. The generation pipeline synthesizes shots; this pipeline cuts already-existing media. They share ffmpeg and the burn-in-subtitles skill but are otherwise independent.

When to Reach For This Skill

Use the editing pipeline when the task involves existing media on disk:

  • Re-cutting a Venice-generated episode because the pacing reads too long
  • Trimming umms/uhs/false-starts out of a talking-head VO take
  • Editing user-supplied raw footage (interview b-roll, phone takes, screen recordings) into a final cut
  • Rescuing a TTS render that truncated mid-script (doubled-ellipsis bug, rule 26)
  • Stitching pre-generated shots in a different order than the original storyboard

Do not reach for this skill when the task is "generate a new shot", "create a storyboard panel", or "render a video from a prompt". Those go through generate-episode-videos, storyboard-episode, or produce-episode.

Core Philosophy: Text + On-Demand Visuals

The LLM reads a 12KB takes_packed.md file — NOT the video itself. Pixels are only consulted at explicit decision points via scripts/timeline-view.ts.

Naive approach: 30 min of footage at 24fps = 43,200 frames × ~1,500 tokens each = 64M tokens of noise. This pipeline: 12KB of text + a handful of composite PNGs.

Same principle as giving an LLM a DOM rather than a screenshot. The transcript is the ground truth; visual sampling is only for ambiguous cuts, retake comparisons, and post-render QA.

The Five Steps

1. Transcribe   -> per-source words.json + takes_packed.md
2. Read pack    -> LLM forms a cut strategy
3. Confirm      -> propose strategy, WAIT for user OK
4. Render EDL   -> ffmpeg concat + 30ms audio fades
5. Self-eval    -> cut-qa agent runs timeline_view at every cut boundary
   -> pass: deliver final-edit.mp4
   -> fail: propose fixes, re-render, loop (max 3 iterations)

Step 1 — Transcribe

npx tsx scripts/transcribe-sources.ts \
  --dir output/<project>/shots \
  --out output/<project>/edit/takes_packed.md \
  --model base.en

Read the full file on GitHub · 231 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. 11d ago First seen · 231 lines · 130 tokens per session scan A 9a20aa3de157

Subscribe to this mod's changes

video-editing is a skill published in the GitHub repository jordanurbs/venice-video-harness (30 stars, last pushed 4d ago), licensed MIT. It adds 130 tokens to every session and 3,134 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens