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.
npx agentmods add commands/othmanadi/openui-forge/openui-componentgit clone --depth 1 https://github.com/OthmanAdi/openui-forgeWhat 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 | $0.00013 | $0.00478 |
| Opus 5 | $0.00006 | $0.00239 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
openui-component 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.
What it actually says
Create a new component and add it to the component library.
Step 1 — Gather requirements:
Ask the user:
- What does this component display or do?
- What props does it need? (or let the agent infer from the description)
Step 2 — Research patterns:
Read references/component-patterns.md for production examples that match the use case. Look for similar component types (data display, input, layout, feedback) and follow the same structural conventions.
Step 3 — Generate the component:
Use templates/component.tsx.template as the base structure. Create the component using defineComponent from @openuidev/react-lang:
import { defineComponent } from "@openuidev/react-lang";
import { z } from "zod";
export const ${NAME} = defineComponent({
name: "${NAME}",
description: "${DESCRIPTION}",
props: z.object({
// props here
}),
component: ({ props }) => (
// JSX here
),
});
CRITICAL design rules (these directly affect LLM generation quality):
.describe()on EVERY Zod prop — this is the LLM's only documentation for what to put in each field- Flat schemas — avoid nesting deeper than 2 levels
- Specific types — use
z.enum(["sm", "md", "lg"])overz.string()when values are constrained - Clear, unique names — the LLM picks components by name + description alone
- Use
reffrom other DefinedComponents for nested component references - Keep the total library under 30 components — more = more prompt tokens = worse LLM output
Step 4 — Add to the library:
Find the existing createLibrary call in the project. Add the new component import and place it in the appropriate componentGroups group. If no suitable group exists, create one.
Step 5 — Regenerate the system prompt:
Remind the user to run /openui:prompt to regenerate the system prompt so the LLM knows about the new component. This step is mandatory — the LLM cannot use components it does not see in the system prompt.
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.
- 2d ago First seen · 53 lines · 13 tokens per session scan A a7d98e692262
openui-component is a command published in the GitHub repository OthmanAdi/openui-forge (22 stars, last pushed 29d ago), licensed MIT. It adds 13 tokens to every session and 478 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.
Other commands, from other repositories
billing
This API allows you to query billing related objects.
object
Command "object" from scaleway/scaleway-cli, covering documentation for scw object, manage s3 buckets, create an s3 bucket, delete an s3 bucket and get information about an s3 bucket.
account
This API allows you to manage your Scaleway Projects.
alias
This namespace allows you to manage your aliases Aliases are store in cli config file, Default path for this configuration file is based on the following priority order.
feedback
Command "feedback" from scaleway/scaleway-cli, covering documentation for scw feedback, send a bug-report and send a feature request.
canvas
Canvas LMS CLI - Interact with Canvas from the command line.