Claude Code Video Toolkit is a workspace that lets Claude Code create videos by producing scripts, voiceovers, music, visuals, and rendered MP4 files. It is for developers using AI-assisted, programmatic video production with tools such as Remotion and open-source media models. The catalogue entries provide commands, skills, instructions, and settings for this workflow.
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.
git clone --depth 1 https://github.com/digitalsamba/claude-code-video-toolkitnpx agentmods add commands/digitalsamba/claude-code-video-toolkit/versionsWrote 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.
[](https://agentmods.dev/commands/digitalsamba/claude-code-video-toolkit/versions)<a href="https://agentmods.dev/commands/digitalsamba/claude-code-video-toolkit/versions"><img src="https://agentmods.dev/badge/commands/digitalsamba/claude-code-video-toolkit/versions/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.
<a href="https://agentmods.dev/commands/digitalsamba/claude-code-video-toolkit/versions"><img src="https://agentmods.dev/badge/commands/digitalsamba/claude-code-video-toolkit/versions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00006 | $0.02019 |
| Opus 5.5 | $0.00002 | $0.00808 |
| Sonnet 5.5 | $0.00001 | $0.00404 |
| Haiku 4.5 | $0.00001 | $0.00202 |
Grade C, and why
versions scanned grade C 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules package-lock.json How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Versions
Check for version mismatches in project dependencies and toolkit updates.
Entry Point
On invocation, perform checks and present results:
Step 1: Detect Context
1. Check if in a project directory (has package.json with Remotion)
2. Read _internal/toolkit-registry.json for toolkit version
3. Determine what checks to run
Step 2: Run Checks
Toolkit-wide staleness (always)
uv run scripts/check_versions.py # table; add --json when scripting
This is the source of truth for everything below the project-level check. It reports every
Remotion pin under templates/, examples/, showcase/, tests/ against the latest npm
release (patches behind, age of the pin), flags caret ranges and projects whose pins disagree,
checks uv.lock against pyproject.toml plus outdated direct Python deps, and compares the
registry version with the latest GitHub release. Staleness alone is informational — bumps are
deliberate (see "Bump policy" below). Caret ranges and internal mismatches are defects.
Project Dependency Check (if in project)
# Run Remotion's built-in version checker
npx remotion versions
Parse output for:
- Version mismatches between @remotion/* packages
- Any packages on different versions
Toolkit Version Check
1. Read current version from _internal/toolkit-registry.json
2. Fetch latest from GitHub API:
https://api.github.com/repos/digitalsamba/claude-code-video-toolkit/releases/latest
3. Compare versions
Bump policy
Templates pin exact Remotion versions for reproducibility (people clone at a tag). Being
N patches behind is expected. Bump on a driver — a needed feature/fix, starting a new project,
or a quarterly check — one template at a time, sprint-review-v2 first, and only with the
render-baseline check green (scripts/render-baseline.mjs, see tests/render-baseline/).
Step 3: Present Results
All Good:
Version Check
## Project: my-video
Remotion packages: 4.0.387 (all aligned)
## Toolkit
Remotion pins: 4.0.425 across 9 projects (92 patches behind latest 4.0.518, pinned 188d ago)
Python: uv.lock in sync, 2 direct deps outdated (elevenlabs, boto3)
Current: v0.18.0
Latest: v0.18.0
Everything consistent. Remotion is behind by policy — run a bump when there's a driver.
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.
- 1mo ago First seen · 320 lines · 6 tokens per session scan C d1f592ea067d
versions is a command published in the GitHub repository digitalsamba/claude-code-video-toolkit (2,256 stars, last pushed 4d ago), licensed MIT. It adds 6 tokens to every session and 2,019 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
playwright-test-plan
Create test plan for basic operations of the todo app. Test plan should contain around 20 tests.
playwright-test-heal
Run all my tests and fix the failing ones.
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; run or list flows…
cli-anything-web:list
List all available CLI-Anything-Web CLIs (installed and generated).
setup-elevenlabs
A setup command for connecting to the ElevenLabs API. ElevenLabs is a service that provides AI-generated voice and speech tools through an API.
call-me
Make an outbound phone call to a number with an autonomous AI agent that pursues a goal and reports back. Usage: /call-me.