Borrowing it
Nothing to install: this file belongs to swarm-ai-research/swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/swarm-ai-research/swarm/main/.claude/commands/render_promo.mdgit clone --depth 1 https://github.com/swarm-ai-research/swarmWrote 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/swarm-ai-research/swarm/render_promo)<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/render_promo"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/render_promo/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/swarm-ai-research/swarm/render_promo"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/render_promo.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 | $0.00000 | $0.00721 |
| Opus 5 | $0.00000 | $0.00360 |
| Sonnet 5 | $0.00000 | $0.00144 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
render_promo 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 9d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/render_promo
Render the SWARM Remotion promo video to MP4, GIF, or still frame.
Note: The
promo/source code has been moved toswarm-ai-research/swarm-artifacts. Clone that repo first ifpromo/is not present locally.
Usage
/render_promo [--format mp4|gif|still] [--frame N] [--open]
Examples:
/render_promo(renders MP4, opens it)/render_promo --format gif/render_promo --format still --frame 60
Behavior
Step 0: Check promo/ exists
If promo/ is not present, instruct the user:
promo/ not found. Clone it from the artifacts repo:
git clone https://github.com/swarm-ai-research/swarm-artifacts.git /tmp/swarm-artifacts
cp -R /tmp/swarm-artifacts/promo ./promo
Step 1: Install dependencies (if needed)
cd promo && npm ls remotion 2>/dev/null || npm install
Only install if node_modules is missing or incomplete.
Step 2: Type-check
cd promo && node_modules/.bin/tsc --noEmit
If type errors exist, fix them before rendering. Common issues:
- Missing
typescriptdev dependency:npm install typescript --save-dev - Unicode escape sequences in JSX: use actual characters instead of
\uXXXX
Step 3: Render
MP4 (default):
cd promo && npx remotion render SwarmPromo out/swarm-promo.mp4
GIF:
cd promo && npx remotion render SwarmPromo out/swarm-promo.gif --image-format=png --every-nth-frame=2
Still frame:
cd promo && npx remotion still SwarmPromo --frame=<N> out/thumbnail.png
Default frame for stills: 60 (shows the SWARM title fully animated). Frame 0 is too dark.
Step 4: Report and open
Rendered:
Format: <mp4|gif|still>
Output: promo/out/<filename>
Size: <file size>
Duration: <seconds if video>
Then open the output:
open promo/out/<filename>
Project Structure
The Remotion project lives in promo/:
promo/src/Root.tsx— Composition definition (1170 frames, 30fps, 1920x1080)promo/src/SwarmPromo.tsx— Scene sequencing via TransitionSeriespromo/src/scenes/*.tsx— Individual scenespromo/src/theme.ts— Shared colors and fontspromo/out/— Render output (gitignored)
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.
- 9d ago First seen · 96 lines · 0 tokens per session scan A 497e50fa5558
render_promo is a command published in the GitHub repository swarm-ai-research/swarm (41 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 721 tokens. 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
story-cover
A tool for creating web-novel covers by analysing a book title and genre and generating a cover image.
instagram-carousel
Turn one Distribb article or keyword into a viral, save-driven Instagram carousel, build the slides with our 2026 best practices (cover hook, one idea per slide, comment-keyword-to-DM), publish it, and close the SEO loop with a companion article.
review-video
Make a " reviews" video: compile REAL, verified reviews of a competitor, name the recurring gaps, position the connected project's own business as the alternative, hand off to the project's own testimonials, then publish it to YouTube and close the loop with a companion article.
youtube-motion-video
Make a faceless motion-collage explainer video ("In a Nutshell" docu style), optimize it for YouTube SEO with Distribb data, and publish it to the connected YouTube channel.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.