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.
git clone --depth 1 https://github.com/DojoCodingLabs/remotion-superpowersWrote 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/dojocodinglabs/remotion-superpowers/review-video)<a href="https://agentmods.dev/commands/dojocodinglabs/remotion-superpowers/review-video"><img src="https://agentmods.dev/badge/commands/dojocodinglabs/remotion-superpowers/review-video.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00972 |
| Opus 5 | $0.00021 | $0.00486 |
| Sonnet 5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
review-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Video — AI-Powered Video Feedback Loop
You are reviewing a rendered Remotion video using TwelveLabs to "watch" it and provide professional feedback. This closes the production loop — render, review, improve, repeat.
Load the remotion-production skill for the video-analysis rule.
Workflow
1. Find the Rendered Video
Look for the output video:
ls out/ 2>/dev/null | grep -E '\.(mp4|webm|mov)$'
If no rendered video exists, tell the user to render first:
npx remotion render [CompositionId] out/video.mp4
2. Index with TwelveLabs
Use TwelveLabs MCP to:
1. Create an index (or use existing)
2. Upload the rendered video
3. Wait for indexing to complete
3. Analyze — The Director's Review
Run a comprehensive review across these dimensions:
Visual Quality:
Search: "Analyze the overall visual composition and quality"
- Are scenes well-framed?
- Is text readable?
- Are transitions smooth?
- Any visual glitches, flickering, or empty frames?
Pacing & Timing:
Search: "Analyze the pacing and scene transitions"
- Are scenes too long or too short?
- Does the video feel rushed or dragging?
- Do transitions happen at natural break points?
Audio-Visual Sync:
Search: "Check if spoken words match what's shown on screen"
- Does the voiceover match the visuals?
- Are sound effects timed correctly?
- Is the music mood appropriate for the visuals?
Content Effectiveness:
Search: "Evaluate the opening hook and call to action"
- Does the first 3 seconds grab attention?
- Is the message clear?
- Is there a clear CTA at the end?
4. Present the Review
Format the feedback as a professional director's review:
🎬 Video Review: [filename]
Duration: [X]s | Resolution: [WxH]
📊 Overall Score: [1-10]
✅ What's Working:
- [positive observation 1]
- [positive observation 2]
⚠️ Improvements Needed:
1. [issue] → [specific fix suggestion]
2. [issue] → [specific fix suggestion]
3. [issue] → [specific fix suggestion]
🎯 Priority Fix:
[the single most impactful change to make]
🔄 Next Steps:
- [ ] [actionable task 1]
- [ ] [actionable task 2]
- [ ] [actionable task 3]
Then re-render and run /review-video again.
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.
- 7d ago First seen · 146 lines · 42 tokens per session scan A 6e7f721ed9d6
review-video is a command published in the GitHub repository DojoCodingLabs/remotion-superpowers (118 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 972 once invoked, about $0.0002 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
index-assets
Index or re-index a brand's visual asset library.
render-carousels
Render multi-slide carousels from HTML templates via Playwright.
edit-post
Edit an existing post's copy, visual direction, or metadata.
generate-post
Generate creative for a single post by ID.
match-assets
Match brand assets to calendar posts and assign creative modes.
review
Open the review gallery for the current month's production.