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/commands/generate-tool-ui.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/commands/assistant-ui/tool-ui/generate-tool-ui)<a href="https://agentmods.dev/commands/assistant-ui/tool-ui/generate-tool-ui"><img src="https://agentmods.dev/badge/commands/assistant-ui/tool-ui/generate-tool-ui/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/commands/assistant-ui/tool-ui/generate-tool-ui"><img src="https://agentmods.dev/badge/commands/assistant-ui/tool-ui/generate-tool-ui.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 | $0.00014 | $0.00548 |
| Opus 5.5 | $0.00006 | $0.00219 |
| Sonnet 5.5 | $0.00003 | $0.00110 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
generate-tool-ui 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Tool UI
Create a new Tool UI component through a maintainer-first workflow.
Arguments
$ARGUMENTS
If no arguments are provided, start with the designer interview. If a component slug is provided, use it as the starting point.
Workflow
This command orchestrates 5 specialized agents in sequence:
designer → implementer → (examples ∥ documenter) → reviewer
Execution Steps
1. Design
Launch tool-ui-designer to interview and produce a concrete design spec:
- component slug + label
- serializable schema shape
- action semantics
- receipt semantics (
choice) - accessibility + state behavior
2. Implement
Launch tool-ui-implementer with the design spec.
Implementation must follow current repo contracts:
- scaffold-first:
pnpm component:new <slug>when creating from scratch - schema contract via
defineToolUiContract+parseSerializableX+safeParseSerializableX - receipt prop is
choice(neverconfirmed/decision) - maintain component directory file contract (including
README.md) - update aggregate exports in
apps/www/components/tool-ui/index.ts
3. Examples + Docs (Parallel)
Launch both in parallel:
tool-ui-examples: presets + gallery/showcase decisionstool-ui-documenter: docs page + registry wiring
4. Review
Launch tool-ui-reviewer as the quality gate.
Hard gates:
pnpm lint:cipnpm typecheckpnpm testpnpm registry:check
5. Report
Return a concise summary:
- files created/updated
- any warnings
- final gate status
Critical Registration Points
The documenter/reviewer must ensure all of these are wired:
| File | Purpose |
|---|---|
apps/www/lib/docs/component-registry.ts |
Component metadata + docs nav categorization |
apps/www/lib/docs/preview-config.tsx |
Interactive preview config + ComponentId coverage |
apps/www/app/docs/_components/preset-selector.tsx |
Examples tab preset mapping |
apps/www/app/docs/{name}/page.tsx |
ComponentDocsTabs docs/examples surface |
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 · 83 lines · 14 tokens per session scan A a3cfd901f625
generate-tool-ui is a command published in the GitHub repository assistant-ui/tool-ui (779 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 548 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 commands, from other repositories
design-context-extract
Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…
design-import
Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…
design-ship
One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…
tokens
Audit or establish the project's 3-layer token spine.
brief
Write or update the project's durable design brief at .ui-craft/brief.md.
critique
Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion before a handoff or presentation.