# Parallel Agents Side by Side — effect skill for AI agent flows > **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q="` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page. Several agent cards work at once in lanes or an orbit, each with its own status, then merge into one result. - **Type:** [Effect](https://varg.ai/how-to/effects.md) · [AI agent flows](https://varg.ai/how-to/browse/skills/agent-flows.md) - **Slug:** `parallel-agents-lanes` - **Status:** live - **Publisher:** HeyGen (community) - **License:** Apache-2.0 - **Source:** https://github.com/heygen-com/hyperframes/tree/main/registry/components/three-orbiting-cards - **Works in:** Claude Code, Claude.ai, Codex, Cursor, OpenClaw, Gemini CLI, Any MCP client, varg Studio - **Requires:** HyperFrames (npx hyperframes), Remotion, CapCut (by hand) - **Cost:** Free — the take renders locally; generated footage, if any, bills by the model ## What it does Built on [Three Orbiting Cards](https://github.com/heygen-com/hyperframes/tree/main/registry/components/three-orbiting-cards) by HeyGen (HyperFrames), Apache-2.0. The write-up and recipes below are varg's. Three to five cards with names (Researcher, Writer, Reviewer) and live status chips; lines converge into a final output card. **When:** Multi-agent systems, subagents, parallel cloud agents. **Watch out:** Do not make every lane busy with motion; one lane leads at a time while others idle-tick. **Timing:** Cards in 0.3 s stagger 0.1 s; status ticks every 0.4–0.8 s; merge 0.6 s. **Also called:** multi-agent, agent swarm, parallel runs ### In HyperFrames ```bash npx hyperframes add three-orbiting-cards npx hyperframes add state-chip-rail ``` ### In Remotion ```tsx agents.map((a,i)=> s.f<=frame)?.label} style={{left:`${12+i*26}%`}}/>) ``` ### In CapCut Split screen into 3 lanes (Templates → split screen), one recording per lane, then cut to the merged result. ### Ready-made components - [Three Orbiting Cards](https://skills.varg.ai/component/hf.three-orbiting-cards/) (hyperframes): npx hyperframes add three-orbiting-cards - [State Chip Rail](https://skills.varg.ai/component/hf.state-chip-rail/) (hyperframes): npx hyperframes add state-chip-rail - [Split Tilt Cards](https://skills.varg.ai/component/hf.split-tilt-cards/) (hyperframes): npx hyperframes add split-tilt-cards ### Where this comes from - [Vox on X: a 4-agent HyperFrames motion team for product videos](https://x.com/Voxyz_ai/status/2104194355556671987) - [Cursor 3 Design Mode and its launch video](https://pasqualepillitteri.it/en/news/3794/cursor-design-mode-what-it-is-how-it-works-cursor-3) ## Use when - Multi-agent systems, subagents, parallel cloud agents. ## Not for - Do not make every lane busy with motion; one lane leads at a time while others idle-tick. ## Install - Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` - Codex: `npx skills add vargHQ/skills --skill varg-video-edit-library -a codex -y` - Cursor: `npx skills add vargHQ/skills --skill varg-video-edit-library -a cursor -y` ## Example output https://s3.varg.ai/how-to/previews/c8425cff36e8/take-parallel-agents-lanes.mp4 — The Three Orbiting Cards component used as its header comment describes, with demo copy (credit: Rendered by varg · HyperFrames Three Orbiting Cards, https://hyperframes.heygen.com/catalog/components/three-orbiting-cards) ## More AI agent flows skills - [Prompt Typed, Then Generate](https://varg.ai/how-to/skills/prompt-typed-then-generate.md): A real task types into the prompt box, the Generate button is pressed, and the result starts to build. - [Answer Streams In](https://varg.ai/how-to/skills/answer-streams-in.md): The assistant's reply arrives in uneven token bursts, the way a real model streams. - [Tool Calls as Status Rows](https://varg.ai/how-to/skills/tool-calls-status-rows.md): Each tool call appears as a row with an icon and label that goes spinner → check, building a visible plan. - [Nodes Wire Up on a Canvas](https://varg.ai/how-to/skills/nodes-wire-up-canvas.md): Nodes pop onto a canvas and connectors draw between them as the camera pulls back to show the whole pipeline. - [Beams Into the Agent Hub](https://varg.ai/how-to/skills/beams-into-agent-hub.md): Light pulses run along curved lines from tool icons into a central agent and back out to a result. - [Thinking… Shimmer Label](https://varg.ai/how-to/skills/thinking-shimmer-label.md): A muted "Thinking…" label with a moving shine shows the model working between prompt and answer. ## Run the generation on varg varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs. - Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a -y` - Grok and any agent that reads SKILL.md: `npx skills add vargHQ/skills --skill varg-ai`, or point it at the skill's SKILL.md - Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp` - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt