Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/digitalsamba/claude-code-video-toolkit/videogit clone --depth 1 https://github.com/digitalsamba/claude-code-video-toolkitWhat 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 | $0.00010 | $0.03196 |
| Opus 5 | $0.00005 | $0.01598 |
| Sonnet 5 | $0.00002 | $0.00639 |
| Haiku 4.5 | $0.00001 | $0.00320 |
Grade A, and why
video 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video
Unified command for video projects. Scans for existing projects and offers to resume or create new.
Entry Point Logic
On invocation, scan for projects and adapt:
Step 0: Check Setup (first-time only)
If .env does not exist or no cloud GPU provider is configured (no MODAL_*_ENDPOINT_URL or RUNPOD_*_ENDPOINT_ID values set):
Tip: Run /setup to configure AI voiceovers, image generation, and music.
It takes ~5 minutes and most features are free. You can skip this and
create videos with just Node.js — run /setup anytime later.
This is a one-line hint, not a blocker. Proceed to Step 1 immediately.
Step 1: Scan Projects
1. Glob projects/*/project.json
2. For each project found:
- Read project.json
- Check filesystem for actual assets (public/demos/*, public/audio/*)
- Reconcile status vs reality
- Calculate health (ready/blocked/stale/complete)
3. Sort by last updated (most recent first)
Step 2: Present Options
No projects found:
No video projects found. Let's create one!
Which template would you like to use?
1. Sprint Review - internal demos, release videos
2. Product Demo - marketing, launches, features
3. Concept Explainer Short - vertical TikTok/Reels/Shorts explainers
→ Proceed to New Project Flow
One project found:
Found: **my-release-video** (sprint-review)
Phase: assets
Progress: 2 of 5 demos recorded
Last worked: 2 days ago
→ Resume this project
→ Start a new project
Multiple projects found:
Found 3 video projects:
1. **my-release-video** (sprint-review)
Phase: assets - 2/5 demos recorded
Last worked: 2 days ago
2. **product-launch** (product-demo)
Phase: audio - voiceover needed
Last worked: 5 days ago
3. **tutorial-v1** (sprint-review)
✅ Complete
Rendered: 2 weeks ago
Which project? (or 'new' for a new project)
Resume Flow
When resuming a project:
Step 1: Read State
1. Read project.json
2. Read VOICEOVER-SCRIPT.md for context
3. Glob public/demos/* and public/audio/*
4. Compare to project.json expectations
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.
- 2d ago First seen · 484 lines · 10 tokens per session scan A 24ce290b2d25
video is a command published in the GitHub repository digitalsamba/claude-code-video-toolkit (2,035 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 3,196 once invoked, about $0.0001 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.
Other commands, from other repositories
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; request automation of…
cli-anything-web:test
Run tests for a cli-anything-web CLI and update TEST.md with results.
cli-anything-web:validate
Validate a cli-anything-web CLI against the tiered quality checklist (Tier 1 critical / Tier 2 comprehensive). Reports per-category and per-tier results.
cli-anything-web:list
List all available CLI-Anything-Web CLIs (installed and generated).
setup
Set up Poster Maker for first use.
setup-elevenlabs
Command "setup-elevenlabs" from minicoohei/ai-agent-camp, covering elevenlabs api セットアップ, step 0: セットアップ進捗の確認, このセッションでやること, 準備チェック and step 1: ブラウザでelevenlabsを開く.