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 skills/digitalsamba/claude-code-video-toolkit/openclaw-video-toolkitWrote 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/skills/digitalsamba/claude-code-video-toolkit/openclaw-video-toolkit)<a href="https://agentmods.dev/skills/digitalsamba/claude-code-video-toolkit/openclaw-video-toolkit"><img src="https://agentmods.dev/badge/skills/digitalsamba/claude-code-video-toolkit/openclaw-video-toolkit.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
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 →
- high Privilege Escalation · line 91 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 109 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 506 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 507 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]
- low Supply Chain · line 84 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00034 | $0.06528 |
| Opus 5 | $0.00017 | $0.03264 |
| Sonnet 5 | $0.00007 | $0.01306 |
| Haiku 4.5 | $0.00003 | $0.00653 |
Grade C, and why
video_toolkit scanned grade C with 2 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.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
Note: `uv sync` creates its own `.venv/` from the lockfile, so it sidesteps Debian/Ubuntu's managed-Python restrictions (PEP 668) — no `--break-system-packages` needed. If `uv` is missing, install it first: `curl -LsSf h Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Note: `uv sync` creates its own `.venv/` from the lockfile, so it sidesteps Debian/Ubuntu's managed-Python restrictions (PEP 668) — no `--break-system-packages` needed. If `uv` is missing, install it first: `curl -LsSf h How it starts
The opening of the file, as written. The whole thing — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Toolkit
Create professional explainer videos from a text brief. The toolkit uses open-source AI models on cloud GPUs (Modal or RunPod) for voiceover, image generation, music, and talking head animation. Remotion (React) handles composition and rendering.
CRITICAL: Toolkit Path
The toolkit lives at a fixed path. ALWAYS cd here before running any tool command.
TOOLKIT=~/.openclaw/workspace/claude-code-video-toolkit
cd $TOOLKIT
NEVER run tool commands from inside a project directory. Tools resolve paths relative to the toolkit root.
CRITICAL: Progress Reporting
ALWAYS add --progress json to every cloud GPU tool command. This gives you structured JSON Lines on stderr so you can monitor job status, detect stuck jobs, and report progress to the user in real-time.
# CORRECT — always include --progress json
uv run tools/music_gen.py --preset corporate-bg --duration 60 --output bg.mp3 --progress json
# WRONG — no visibility into job status
uv run tools/music_gen.py --preset corporate-bg --duration 60 --output bg.mp3
Tools that support --progress json: music_gen.py, qwen3_tts.py, flux2.py, upscale.py, sadtalker.py, image_edit.py, dewatermark.py, ltx2.py, chain_video.py.
See the Progress Reporting section below for output format and stage definitions.
CRITICAL: Long-Running Tasks — Use yieldMs, Not background:true
Any tool command that takes more than 30 seconds MUST use exec with yieldMs so you can report progress to the user live. This includes: batch FLUX generation, chain_video, SadTalker, music generation, and any multi-scene pipeline.
exec command:"cd ~/.openclaw/workspace/claude-code-video-toolkit && uv run tools/chain_video.py --output-dir /path/ --progress json ..." yieldMs:10000
The polling loop:
execwithyieldMs:10000starts the command and returns control to you every 10 seconds- Read the
--progress jsonoutput — look for"stage":"item"(scene complete) or"stage":"complete"(all done) - Report progress to the user ("Scene 05/30 complete, 17%")
- Poll again:
process action:poll sessionId:<id> - Repeat until
"stage":"complete"
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 · 642 lines · 34 tokens per session scan C 645cb0620cb5
video_toolkit is a skill published in the GitHub repository digitalsamba/claude-code-video-toolkit (2,053 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 6,528 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
creador_videos_ai
Build a 30-second cinematic marketing video for any website URL using the Causal AI Digital pipeline (Playwright iframe scroll tour + ElevenLabs voice off + whisper.cpp word-level synced subtitles + FFmpeg audio mux). Use when the user asks to generate a promotional/marketing video for a website, create a cinematic…
sepia-hemingway
Use when a user asks to write or revise fiction in the Hemingway manner, or asks for strong de-AI on a story; applies Sepia's built-in Hemingway voice profile.
memstack-content-youtube-script
Use this skill when the user says 'YouTube script', 'video script', 'write script for YouTube', 'YouTube video outline', or is creating scripted content for a YouTube video with hooks, chapters, and CTAs. Do NOT use for TikTok/Reels short-form scripts or webinar presentations.
memstack-marketing-facebook-ad
Use this skill when the user says 'facebook ad', 'FB ad', 'Meta ad', 'Instagram ad', or needs social media ad copy with targeting, creative direction, and A/B test plans for Meta Ads Manager. Do NOT use for Google search ads or organic social content.
sound-effects
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.
slides
A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.