openui-validate

A validation command for an OpenUI application, an app where an AI model generates interactive interface components. It runs ten checks and produces a pass-or-fail report for the integration.

In plain words
What is it for?
Use it to verify dependencies, React compatibility, the component library, component property descriptions, and the other required OpenUI integration checks.
Why use it?
An OpenUI app can fail when packages, React versions, component definitions, property descriptions, or other required pieces are missing or inconsistent. The checklist helps locate those setup problems.

Command

Install

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.

agentmods
npx agentmods add commands/othmanadi/openui-forge/openui-validate
Clone the repo
git clone --depth 1 https://github.com/OthmanAdi/openui-forge
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,374 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.01374
Opus 5 $0.00006 $0.00687
Sonnet 5 $0.00002 $0.00275
Haiku 4.5 $0.00001 $0.00137

Measured 2d ago against content hash 7fe1c0718fa2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openui-validate 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 2d 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.

commands/openui-validate.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate the entire OpenUI integration. Run all 10 checks and output a clear pass/fail report.


Validation checks

Run each check in order. For each one, output PASS or FAIL with details.

Check 1 — Dependencies installed

How: Run npm ls @openuidev/react-lang (or check package.json for @openuidev packages) Pass: All three core packages are installed (@openuidev/react-lang, @openuidev/react-headless, @openuidev/react-ui) Fix if FAIL: npm install @openuidev/react-ui @openuidev/react-headless @openuidev/react-lang

Check 2 — React >= 18.3.1 (19+ recommended)

How: Run npm ls react and check the version Pass: React version is 18.3.1 or higher (peer range is ^18.3.1 || ^19.0.0; 19+ recommended) Fix if FAIL: npm install react@latest react-dom@latest

Check 3 — Component library exists

How: Search for createLibrary calls in the project Pass: At least one createLibrary call found, file path identified Fix if FAIL: Run /openui:component to create components, or /openui:scaffold to set up the library

Check 4 — Zod .describe() on all props

How: In every file containing defineComponent, check that all z.object fields have .describe() calls. Search for Zod field definitions (z.string(), z.number(), z.enum(), z.array(), z.boolean(), z.object()) and verify each has a .describe() chained on it. Pass: Every Zod prop field has a .describe("...") call Fix if FAIL: Add .describe("clear description of what this field contains") to every Zod field. This is critical — it is the LLM's only documentation for each prop.

Check 5 — System prompt exists

How: Search for files named system-prompt.txt in the project. Also check if .prompt() is called on a library instance in the backend. Pass: Either a non-empty system-prompt.txt file exists, or .prompt() is called in the API route Fix if FAIL: Run /openui:prompt

Check 6 — Backend route exists

How: Search for API route files (app/api/chat/route.ts, pages/api/chat.ts, server/*.ts, main.py, cmd/server/main.go, src/main.rs, etc.) Pass: A backend handler that processes chat requests is found Fix if FAIL: Run /openui:integrate

Read the full file on GitHub · 101 lines

Changes

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.

  1. 2d ago First seen · 101 lines · 12 tokens per session scan A 7fe1c0718fa2

Subscribe to this mod's changes

openui-validate is a command published in the GitHub repository OthmanAdi/openui-forge (22 stars, last pushed 29d ago), licensed MIT. It adds 12 tokens to every session and 1,374 once invoked, about $0.0001 per session on Opus 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.