venice-video-harness: Command for Claude Code

.agents/commands/edit-footage.md

edit-footage is a command for Claude Code from jordanurbs/venice-video-harness. It costs 0 tokens per session (2,058 once invoked), scanned A, original, MIT.

A command for editing existing video footage through cuts, trims, reordering, and filler-word removal. It produces an edited MP4 from source media already stored on disk.

In plain words
What is it for?
Use it to edit interviews, phone recordings, screen captures, or previously rendered episodes. It can also remove umms and false starts and help handle truncated voice-over audio.
Why use it?
It provides a defined workflow for checking the source material, confirming the edit plan, applying changes, and reviewing the result. It is intended for editing existing footage, not generating new video shots.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). 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 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 →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { createEmptyEdl, addClip, writeEdl } from '../../src/editing/edl.js';.

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/commands/edit-footage.md
Clone the repo
git clone --depth 1 https://github.com/jordanurbs/venice-video-harness

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 edit-footage

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/jordanurbs/venice-video-harness/edit-footage"><img src="https://agentmods.dev/badge/commands/jordanurbs/venice-video-harness/edit-footage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,058 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.
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 $0.02058
Opus 5 $0.00000 $0.01029
Sonnet 5 $0.00000 $0.00412
Haiku 4.5 $0.00000 $0.00206

Measured 11d ago against content hash 7e9630d2a15d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

edit-footage 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 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.

Makes network callslowCapability

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

curl -L -o ~/.cache/whisper.cpp/ggml-base.en.bin \
.agents/commands/edit-footage.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/edit-footage

End-to-end editing pipeline for existing media. Read the video-editing skill before running this command — it defines the EDL format, the ask-confirm-execute-self-eval loop, and the anti-patterns to avoid.

Scope: cuts, trims, re-orderings, filler-word removal, and delivery of an edited mp4 from sources already on disk. This is NOT the generation pipeline. For synthesizing new shots use /produce-episode or /generate-videos.

When To Use

  • User brings raw footage (interview takes, phone recordings, screen caps) and wants a cut
  • User wants to re-cut a Venice-generated episode without re-rendering shots
  • User needs to rescue a truncated TTS VO by editing the working audio
  • User asks to trim umms / false-starts from a talking-head take

Preflight

Confirm before starting:

  1. Source directory — where are the clips? Typically output/<project>/shots/ or a user-supplied folder.
  2. Output targetoutput/<project>/edit/final-edit.mp4 by default.
  3. Ground-truth script (if any) — for TTS-generated content, locate the VO_TEXT config so the transcriber can run in aligned mode and flag VO truncation.
  4. Format expectations — aspect ratio (pull from series.json if it exists), target duration, cut style (hard cuts by default; crossfades only if user asks).

If the directory is missing or contains zero matching sources, stop and ask the user for the correct path.

Step 1 — Transcribe

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

If a ground-truth script exists:

npx tsx scripts/transcribe-sources.ts \
  --dir <sources_dir> \
  --out output/<project>/edit/takes_packed.md \
  --aligned-from scripts/<project>/config.ts

The transcriber writes one *.words.json per source plus takes_packed.md. Transcription time: ~0.1x realtime for the base.en model on an M-series Mac.

If transcription fails with a "whisper-cpp binary not found" or "model not found" error, print the install commands to the user and stop:

Read the full file on GitHub · 197 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 · 197 lines · 0 tokens per session scan A 7e9630d2a15d

Subscribe to this mod's changes

edit-footage is a command published in the GitHub repository jordanurbs/venice-video-harness (30 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,058 tokens. 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.