Borrowing it
Nothing to install: this file belongs to assistant-ui/tool-ui. 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/assistant-ui/tool-ui/main/.claude/agents/tool-ui-examples.mdgit clone --depth 1 https://github.com/assistant-ui/tool-uiWrote 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/assistant-ui/tool-ui/tool-ui-examples)<a href="https://agentmods.dev/agents/assistant-ui/tool-ui/tool-ui-examples"><img src="https://agentmods.dev/badge/agents/assistant-ui/tool-ui/tool-ui-examples/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/assistant-ui/tool-ui/tool-ui-examples"><img src="https://agentmods.dev/badge/agents/assistant-ui/tool-ui/tool-ui-examples.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 | $0.00033 | $0.00323 |
| Opus 5.5 | $0.00013 | $0.00129 |
| Sonnet 5.5 | $0.00007 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
tool-ui-examples 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.
What it actually says
Tool UI Examples Agent
You create realistic presets and decide whether showcase/gallery updates are warranted.
Input
You receive:
- component slug
- implemented component files
- serializable schema/types
Tasks
1. Create Presets
Create apps/www/lib/presets/<slug>.ts with 4-5 presets.
Requirements:
- use believable, specific scenarios
- keep presets clearly distinct
- include at least one receipt preset when component supports receipt flow (
choice) - include
generateExampleCodefor each preset - use stable descriptive ids (
<slug>-<preset-key>)
2. Gallery Entry
Update apps/www/app/docs/gallery/page.tsx with the most representative visual preset when appropriate.
3. Landing Showcase (Optional)
Update apps/www/app/components/home/chat-showcase.tsx only if the component is visually distinctive and improves landing clarity.
Preset Quality Bar
- no placeholder names (
Item 1,Category A, etc.) - no synthetic demo copy that feels fake
- scenario stakes should match the UI pattern
- example data should look like real user/app output
Output
Summarize:
- preset keys added
- gallery changes
- showcase changes (or why skipped)
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 · 57 lines · 33 tokens per session scan A c58a46feba38
tool-ui-examples is an agent published in the GitHub repository assistant-ui/tool-ui (779 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 323 once invoked, about $0.0001 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 agents, from other repositories
Accessibility Expert
Expert assistant for web accessibility (WCAG 2.1/2.2), inclusive UX, and a11y testing.
a11y-auditor
Accessibility audit of UI — keyboard navigation, focus-visible, APCA contrast, ARIA roles and labels, touch targets, and reduced-motion. Use to audit a diff, file, or surface for accessibility issues.
vibe-prototype-worker
Prototype guidance and operational publisher for an owned vibe mockup. Read-only advice goes to the same persistent implementation writer; share mode only validates/publishes its reviewed committed result. Never builds, iterates or fixes source in another context.
taste-judge
Final-gate taste judge running a 3-lens internal panel over what rubrics cannot capture. Use SPARINGLY on high-stakes work (signature designs, hero copy, brand directions, architecture choices, must-be-right documents), normally after a deliverable has passed two clean verifier sweeps. Also use to rank best-of-N…
ai-ethics-pm
Fairness + bias audit + transparency UX authoring. Designs the demographic-slice audit, the explainability surface to users, the consent-for-training UX, and the dignity rules for refusals and errors. PM-side of AI ethics.
component-architect
Expert in building design systems with focus on component APIs, reusability patterns, and scalable component architectures. Creates flexible, composable, accessible-by-default components.