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/brendanciccone/storysyncWrote 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/rules/brendanciccone/storysync/cursor)<a href="https://agentmods.dev/rules/brendanciccone/storysync/cursor"><img src="https://agentmods.dev/badge/rules/brendanciccone/storysync/cursor/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/rules/brendanciccone/storysync/cursor"><img src="https://agentmods.dev/badge/rules/brendanciccone/storysync/cursor.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 | $0.00056 | $0.34545 |
| Opus 5.5 | $0.00022 | $0.13818 |
| Sonnet 5.5 | $0.00011 | $0.06909 |
| Haiku 4.5 | $0.00006 | $0.03454 |
Grade A, and why
cursor 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 3d 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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storysync: Storybook to Figma
Read components from Storybook MCP and recreate them in Figma MCP as a visually accurate component library, with design token foundations.
Requirements
- Storybook dev server running with
@storybook/addon-mcp(Vite-based Storybook 10.1+, Node 18+;snapneeds Node 20+) - Storybook MCP in
.cursor/mcp.json:{ "mcpServers": { "storybook": { "url": "http://localhost:6006/mcp" } } } - Figma MCP:
/add-plugin figmain Agent chat (or a"figma": { "url": "https://mcp.figma.com/mcp" }entry in.cursor/mcp.json), and sign in to Figma when prompted - Figma Full seat (Dev seats are read-only)
- storysync 0.4.0 or later, run as
npx storysync: 0.3.0 has no tokenpx, componentid,--exclude-propsor--merge, and 0.2.0 and earlier have nosnaporverify - If storysync says Storybook has no MCP endpoint (
answered HTTP 404, withRun `storysync init`, then restart Storybook), ask the user to runnpx storysync init, which asks before each change it makes, and then to restart Storybook. If its install fails, it prints the command to run by hand afterRun manually:: pass that line on rather than retrying. - The CLI's own
storysync diffcan't sign in to Figma, so againsthttps://mcp.figma.com/mcpit fails with HTTP 401 by design. Audit with the Audit section below instead, throughuse_figma, and don't retry it.
Running storysync from Cursor
Cursor runs the agent's terminal commands in a sandbox when it can, and the sandbox blocks loopback addresses (localhost, 127.0.0.1, ::1) by default. list, map, inspect and snap all talk to Storybook on localhost, and snap also launches a browser, so request full permissions to run them outside the sandbox. If one of them fails to reach Storybook from inside the sandbox, re-run it with full permissions before telling the user Storybook is down. tokens, figma tokens, figma code, figma next and verify read and write only local files. figma upload posts pictures to the upload URLs Figma's upload_assets hands out, so it needs network access: run it outside the sandbox too.
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.
- 3d ago Changed · +200 lines 4b6b282a2b81
- 15d ago Changed · +84 lines · +45 tokens per session 80c67ec71422
- 1mo ago First seen · 135 lines · 11 tokens per session scan A e87b332d9ccb
cursor is a cursor rule published in the GitHub repository brendanciccone/storysync (75 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 34,545 once invoked, about $0.0002 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 2026-08-30.
Other cursor rules, from other repositories
explorer-interface-brief
Use when asked to design the interface for an interactive 3D explorer, plan a UI for exploring a 3D model of a topic, or write an image-model prompt for a 3D learning app mock-up. Produces, from a topic, the UI design brief (audience, layout, panels, interactions, label style, colour palette, accessibility) and an…
prototype-previewer
Build interactive prototype reviewers with synced review notes and Figma capture pages.
figma-performance
Handling large documents efficiently in the Plugin API.
ant-design
A set of guidelines for using Ant Design, a collection of ready-made interface components, in React applications. It covers code organization, performance, security, testing, and common mistakes.
7-day-nextjs-web-design-cursor
A seven-day design workflow for web products that will be built in Next.js.
clone-ai
Site Clone AI — website klonlama pipeline kuralları.