assistant-ui-primitives

A guide to building chat interfaces from unstyled, reusable React components, including message threads, text input, messages, attachments, and action buttons. It explains the primitives provided by assistant-ui and how to customize them.

In plain words
What is it for?
Use it when customizing assistant-ui chat components such as message lists, composers, thread controls, and message actions.
Why use it?
It helps developers assemble a chat interface without writing every interaction component from scratch.

Skill for Claude CodeCodex

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 skills/compozy/compozy/assistant-ui-primitives
Any agent
npx skills add compozy/compozy --skill assistant-ui-primitives
Clone the repo
git clone --depth 1 https://github.com/compozy/compozy

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 959 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 $0.00028 $0.00959
Opus 5 $0.00014 $0.00479
Sonnet 5 $0.00006 $0.00192
Haiku 4.5 $0.00003 $0.00096

Measured 3d ago against content hash 963ec1b1e9ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

assistant-ui-primitives 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 3d 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.

.agents/skills/assistant-ui/assistant-ui-primitives/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

assistant-ui Primitives

Always consult assistant-ui.com/llms.txt for latest API.

Composable, unstyled components following Radix UI patterns.

References

Import

import {
  AuiIf,
  ThreadPrimitive,
  ComposerPrimitive,
  MessagePrimitive,
  ActionBarPrimitive,
  BranchPickerPrimitive,
  AttachmentPrimitive,
  ThreadListPrimitive,
  ThreadListItemPrimitive,
} from "@assistant-ui/react";

Primitive Parts

Primitive Key Parts
ThreadPrimitive .Root, .Viewport, .Messages, .Empty, .ScrollToBottom
ComposerPrimitive .Root, .Input, .Send, .Cancel, .Attachments
MessagePrimitive .Root, .Parts/.Content, .If, .Error
ActionBarPrimitive .Copy, .Edit, .Reload, .Speak, .FeedbackPositive, .FeedbackNegative, .ExportMarkdown
BranchPickerPrimitive .Previous, .Next, .Number, .Count

Custom Thread Example

function CustomThread() {
  return (
    <ThreadPrimitive.Root className="flex flex-col h-full">
      <ThreadPrimitive.Empty>
        <div className="flex-1 flex items-center justify-center">
          Start a conversation
        </div>
      </ThreadPrimitive.Empty>

      <ThreadPrimitive.Viewport className="flex-1 overflow-y-auto p-4">
        <ThreadPrimitive.Messages components={{
          UserMessage: CustomUserMessage,
          AssistantMessage: CustomAssistantMessage,
        }} />
      </ThreadPrimitive.Viewport>

      <ComposerPrimitive.Root className="border-t p-4 flex gap-2">
        <ComposerPrimitive.Input className="flex-1 rounded-lg border px-4 py-2" />
        <ComposerPrimitive.Send className="bg-blue-500 text-white px-4 py-2 rounded-lg">
          Send
        </ComposerPrimitive.Send>
      </ComposerPrimitive.Root>
    </ThreadPrimitive.Root>
  );
}

Read the full file on GitHub · 131 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 131 lines · 28 tokens per session scan A 963ec1b1e9ce

Subscribe to this mod's changes

assistant-ui-primitives is a skill published in the GitHub repository compozy/compozy (2,703 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 959 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.

Related

Other skills, from other repositories

chakra-ui-builder

Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…

chakra-ui/chakra-ui · 214 tokens

row-selection

Maintain rowSelection ID state with stable getRowId, single, multi, subrow, and Shift-range rules, selected row models, handler anchors, and manual-pagination semantics. Load when implementing getToggleSelectedHandler, enableRowRangeSelection, selectChildren, deselectParents, or selected IDs that outlive loaded Row…

TanStack/table · 68 tokens

material-ui-tailwind

Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.

mui/material-ui · 67 tokens

r3f-best-practices

React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.

zebbern/claude-code-guide · 74 tokens

wrdn-effect-promise-exit

Replace React/effect-atom mutation handlers that use promise-mode plus try/catch with promiseExit and explicit Exit handling. Use when lint or review flags try/catch around useAtomSet mutation calls, especially UI handlers that set error/busy state after a failed mutation.

UsefulSoftwareCo/executor · 63 tokens

fast-typescript-check

Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…

internet-development/www-sacred · 84 tokens