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 skills add desplega-ai/agent-swarm --skill motion-design-replicationgit clone --depth 1 https://github.com/desplega-ai/agent-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/skills/desplega-ai/agent-swarm/motion-design-replication)<a href="https://agentmods.dev/skills/desplega-ai/agent-swarm/motion-design-replication"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/motion-design-replication/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/skills/desplega-ai/agent-swarm/motion-design-replication"><img src="https://agentmods.dev/badge/skills/desplega-ai/agent-swarm/motion-design-replication.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 | $0.00095 | $0.02614 |
| Opus 5.5 | $0.00038 | $0.01046 |
| Sonnet 5.5 | $0.00019 | $0.00523 |
| Haiku 4.5 | $0.00010 | $0.00261 |
Grade A, and why
motion-design-replication 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 14d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motion-design replication
Takes a reference clip and produces a replica that matches its craft (resolution, fps, duration, camera, DOF, easing, caption style, outro) while swapping everything brand-specific (palette, logo, shapes, copy) for agent-swarm's. Built on a run that rebuilt Linear's "Loops updates" dial as a Schedules teaser. Keep the working R3F + postprocessing + label setup from your first 3D composition in your Remotion project and reuse it.
The bar is the highest quality of content. A render that passes automated checks proves nothing about how it looks. The loop in Step 5 is the work.
Step 1 — analyse and write the rebuild spec
Run motion-design-video-analysis on the reference, including its rebuild-spec section and the by-eye claim check. You need, in frames: every cut, every caption change, every transition window. Pull 10 fps windows around each transition; a cut hidden under a fast element reads as a "camera move" to both you and the model until you step frames.
Step 2 — pick the swarm subject and map it onto the reference's metaphor
Pick the feature whose shape matches the reference's central object (a dial ⇒ Schedules, because a dial reads as a clock and a clock maps onto cron). Write captions that follow one real run of that feature, in product vocabulary, checked against the repo docs (agent-swarm/docs-site/content/docs/). Keep the reference's caption count and rhythm, not its words.
Step 3 — collect real brand assets; never redraw
Copy, don't approximate. For Agent Swarm:
- Mark:
apps/ui/public/logo.pngindesplega-ai/agent-swarm(the hex mark; byte-identical todocs-site/public/logo.pngandhttps://agent-swarm.dev/logo.png; verify withsha256sum). There is no logo SVG. - Wordmark: "Agent Swarm", Space Grotesk 600, tracking -0.01em, near-white. If your project only vendors Space Grotesk 400/500/700, 600 renders as 700; say so if it matters.
- Fonts: Space Grotesk (display) + Space Mono (labels).
- Colour: amber-400 #fabc00, amber-300 #ffd237, zinc-950 #09090b, zinc-400 #9f9fa9 (amber-500 #f69e00 reads brown at low alpha). three.js wants hex: convert oklch tokens with culori (
formatHex(clampChroma(parse(x),'oklch'))). - Feature icons: the app's own lucide icons (
apps/ui/src/components/layout/app-sidebar.tsx), e.g. Schedules =ClockIcon.
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.
- 14d ago First seen · 86 lines · 95 tokens per session scan A 5b80e8a8607c
motion-design-replication is a skill published in the GitHub repository desplega-ai/agent-swarm (890 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 2,614 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
security-observability
A read-only tool for examining security events already saved by agent-sec-cli, a command-line security log. It can connect those events to an agent session, run, or trace.
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
skill-ledger
A security record for agent skills, which are reusable instruction packages for coding agents. It shows their status, reviews risk exposure, and can certify them with quick or user-approved deeper scans.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
pr-body
A tool that reviews all commits on the current branch and creates or updates a pull request title and description. A pull request is a proposed code change submitted for review.
prompt-scanner
A scanner for text sent to an AI agent, looking for prompt injection and jailbreak attempts. Prompt injection is text that tries to override an agent's instructions; a jailbreak tries to bypass its safety limits.