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/omergulcicek/omergulcicek.comWrote 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/omergulcicek/omergulcicek.com/forms)<a href="https://agentmods.dev/rules/omergulcicek/omergulcicek.com/forms"><img src="https://agentmods.dev/badge/rules/omergulcicek/omergulcicek.com/forms/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/omergulcicek/omergulcicek.com/forms"><img src="https://agentmods.dev/badge/rules/omergulcicek/omergulcicek.com/forms.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 | $0.00477 |
| Opus 5.5 | $0.00000 | $0.00191 |
| Sonnet 5.5 | $0.00000 | $0.00095 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
forms 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 5d 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.
What it actually says
Forms
Rules
- React Hook Form with
zodResolverfrom@hookform/resolvers/zod. - Schemas live in
schemas/(*.schema.ts), never in the component file. - Every field has a value in
defaultValues, typed from the schema. - Read live values with
useWatchorController, not rootwatch(). Disable submit whileisSubmitting. - Map server errors to fields or to
rootwithsetError. - The server validates the same schema again before it acts.
- Small forms without client validation may use an Action with
useActionState.
Bans
- Inputs managed with
useState. - Syncing form state with
useEffect. - Handling the native
submitevent instead of usinghandleSubmit.
import { createProject } from "@/features/projects/api"; import { projectSchema } from "@/features/projects/schemas"; import type { ProjectInput } from "@/features/projects/schemas";
export function ProjectForm() { const form = useForm({ resolver: zodResolver(projectSchema), defaultValues: { name: "" }, });
const onSubmit = form.handleSubmit(async (values) => { const result = await createProject(values); if (result.error) form.setError("root", { message: result.error }); });
return ( Name <input id="project-name" {...form.register("name")} /> {form.formState.errors.name?.message} Create ); }
</example>
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.
- 5d ago Changed · +13 lines e1ed81220377
- 2mo ago First seen · 46 lines · 0 tokens per session scan A 8aca65cffe10
forms is a cursor rule published in the GitHub repository omergulcicek/omergulcicek.com (15 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 477 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 2026-09-01.
Other cursor rules, from other repositories
frontend-development
Most coagents examples have a ui/ folder with Next.js applications.
examples-and-demos
Multi-agent systems with complex workflows.
suggestions-development
When working with suggesitons, always load this up.
agent-development
Python agents are typically in folders named agent-py/ or agent/ and use the sdk-python/ package.
development-workflow
CopilotKit uses a monorepo structure with.
quick-reference
Cursor rule "quick-reference" from CopilotKit/CopilotKit, covering copilotkit quick reference, need to...?, build a simple copilot, create multi-agent systems and integrate with crewai.