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/vercel/ai-elementsWrote 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/vercel/ai-elements/ultracite)<a href="https://agentmods.dev/rules/vercel/ai-elements/ultracite"><img src="https://agentmods.dev/badge/rules/vercel/ai-elements/ultracite/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/vercel/ai-elements/ultracite"><img src="https://agentmods.dev/badge/rules/vercel/ai-elements/ultracite.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 | $0.03481 | $0.03481 |
| Opus 5.5 | $0.01392 | $0.01392 |
| Sonnet 5.5 | $0.00696 | $0.00696 |
| Haiku 4.5 | $0.00348 | $0.00348 |
Grade A, and why
ultracite 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 1mo 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 1mo ago First seen · 333 lines · 3,481 tokens per session scan A a7fac75b8f46
ultracite is a cursor rule published in the GitHub repository vercel/ai-elements (2,493 stars, last pushed 2d ago), with no licence file. It adds 3,481 tokens to every session, about $0.0139 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
cursorrules
You are using StyleSeed, a design-method engine whose goal is to make expert design judgment repeatable by coding agents, not to replace designers with aesthetic preferences. Preserve approved project choices; report unsupported choices instead of silently restyling the project's design system. PRODUCT-PRINCIPLES.md…
release-lanes
Promote Plate beta releases, sync main back to next and verify published npm/GitHub state with release authority.
changeset
Write and verify package release changesets, registry changelog entries, and the PR’s managed auto-release choice. Use before deciding whether a package edit needs a changeset, including skipping one.
verify
Verify Plate packages, browser editor behavior, CLI artifacts, collaboration and tests at their actual owners. Load before selecting, changing or waiving proof, writing tests or claiming a fix works.
maintainer
Triage public Plate and Slate issues, PRs and security queues, route local work and preserve exact public proof and publication authority.
sync-shadcn
Sync upstream shadcn docs or registry protocol into Plate with exact source ranges, preserved forks, accepted apply rows and complete baseline accounting.