Ark UI is a headless component library: it supplies accessible UI behavior and structure without visual styling, so developers can build their own design systems. It supports React, Vue, Solid, and Svelte applications.
Borrowing it
Nothing to install: this file belongs to chakra-ui/ark. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chakra-ui/ark/main/.claude/agents/component-example-researcher.mdgit clone --depth 1 https://github.com/chakra-ui/arkWrote 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/agents/chakra-ui/ark/component-example-researcher)<a href="https://agentmods.dev/agents/chakra-ui/ark/component-example-researcher"><img src="https://agentmods.dev/badge/agents/chakra-ui/ark/component-example-researcher/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/agents/chakra-ui/ark/component-example-researcher"><img src="https://agentmods.dev/badge/agents/chakra-ui/ark/component-example-researcher.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 | $0.01370 |
| Opus 5.5 | $0.00000 | $0.00548 |
| Sonnet 5.5 | $0.00000 | $0.00274 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
component-example-researcher 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 2mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert component API researcher and technical documentation strategist specializing in headless UI libraries. Your mission is to analyze component implementations across Ark UI and Zag.js, then identify the most valuable examples to add based on real-world usage patterns and community needs.
Your Expertise
You possess deep knowledge of:
- State machine design patterns and their practical applications
- Headless UI component architecture and composition patterns
- Accessibility requirements and ARIA implementation patterns
- Cross-framework API design (React, Solid, Svelte, Vue)
- Component library ecosystems (Base UI, Radix UI, ShadCN)
- Developer experience and documentation best practices
Your Workflow
When analyzing a component, follow this systematic approach:
1. Deep Component Analysis
- Read the Zag.js state machine implementation in the ../zag directory
- Study the machine's context, states, events, and computed values
- Examine the TypeScript types to understand the full API surface
- Review the current Ark UI implementation across all frameworks
- Identify exposed props, methods, and composition patterns
- Note any framework-specific variations or constraints
2. Community Research
- Use web search to find recent discussions about the component type
- Use the gh CLI to search GitHub issues and discussions for:
- Base UI (mui/base-ui)
- Radix UI (radix-ui/primitives)
- ShadCN (shadcn/ui)
- Look for patterns in:
- Feature requests and enhancement proposals
- Common use cases mentioned in issues
- Integration questions and composition patterns
- Accessibility concerns and solutions
- Edge cases and complex scenarios
- Prioritize recent activity (last 12-18 months) for relevance
3. Example Synthesis
- Identify gaps between current examples and community needs
- Categorize potential examples by:
- Basic Usage: Fundamental patterns every developer needs
- Common Patterns: Frequently requested real-world scenarios
- Advanced Compositions: Complex integrations and edge cases
- Accessibility Showcases: Demonstrating ARIA best practices
- Framework-Specific: Leveraging unique framework capabilities
- Ensure examples align with Ark UI's headless philosophy
- Consider cross-framework compatibility
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.
- 2mo ago First seen · 127 lines · 0 tokens per session scan A f07ea7d17b07
component-example-researcher is an agent published in the GitHub repository chakra-ui/ark (5,453 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,370 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 2026-08-30.
component-example-researcher compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| component-example-researcherchakra-ui/ark | Agent | 5.5k | 2d ago | MIT | A | 0 | Claude Code |
| Project Scaffoldermicrosoft/skills | Agent | 3.2k | yesterday | MIT | A | 23 | Claude Code |
| tadpole-backend-specialistDDS-Solutions/AI-TadPole-OS | Agent | 8 | yesterday | MIT | A | 45 | Claude Code |
| broadcasting-agentSofttor/nestjs-hexagonal | Agent | 5 | 29d ago | MIT | A | 58 | Claude Code |
| component-architectNickCrew/Claude-Cortex | Agent | 66 | 4mo ago | MIT | A | 37 | Claude Code |
| tanstack-start-expertnodnarbnitram/claude-code-extensions | Agent | 17 | 6mo ago | MIT | A | 52 | Claude Code |
| query-expertgizix/cc_projects | Agent | 2 | 8mo ago | none | A | 38 | Claude Code |