Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/usetheokit/theokitnpx agentmods add skills/usetheokit/theokit/theokit-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/skills/usetheokit/theokit/theokit-ui)<a href="https://agentmods.dev/skills/usetheokit/theokit/theokit-ui"><img src="https://agentmods.dev/badge/skills/usetheokit/theokit/theokit-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/skills/usetheokit/theokit/theokit-ui"><img src="https://agentmods.dev/badge/skills/usetheokit/theokit/theokit-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.01955 |
| Opus 5.5 | $0.00022 | $0.00782 |
| Sonnet 5.5 | $0.00011 | $0.00391 |
| Haiku 4.5 | $0.00005 | $0.00196 |
Grade A, and why
theokit-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 1mo 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@theokit/ui — AI-native Component Library (AI-agent surfaces)
@theokit/ui is an optional peer dependency. If installed, it provides ready-made AI components for chat + coding-agent surfaces (chat thread, agent events, tool calls, diff viewer, build logs), plus theming. Never build custom equivalents of components it provides. Generic primitives (Button, Input, Card, CodeBlock, PageShell, Sidebar, Avatar, Alert, etc.) live in @usetheo/ui, which @theokit/ui depends on — import those from @usetheo/ui.
Read the catalogue before writing markup
@theokit/ui ships llms.txt — a file written for an agent to read, at
node_modules/@theokit/ui/llms.txt. It lists every component with its purpose and, in a
"Which package has what" table, routes each need to the right package. Read it before building a
sidebar, a table, a select, a badge or an empty state by hand.
That is not a style preference. A real app built on this scaffold hand-wrote ~600 lines of markup — navigation, queue rows, filters, status badges, empty states, a composer — and every one of them already existed in the two packages the scaffold had installed (usetheokit/theokit#471). The components were there; nothing pointed at them.
@usetheo/ui has no llms.txt; its surface is in its own README and its type definitions.
Package Identity
@theokit/ui provides the AI-agent-surface components. (The version this project uses is in
package.json; a number written here goes stale the first time anyone upgrades, and this one
said 1.0.0 while npm served 1.5.1.) Its generic foundation was split into @usetheo/ui in the 2026-07-03 AI-exclusive pivot; @theokit/ui depends on @usetheo/ui, so installing @theokit/ui pulls the foundation transitively.
# Install from npm (preferred)
npm install @theokit/ui
# Or from local tarball (when using source repo)
cd ../theokit-ui && npm pack # produces theokit-ui-X.Y.Z.tgz
cd ../my-app && npm install ../theokit-ui/theokit-ui-X.Y.Z.tgz
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.
- 1mo ago Changed d851de667187
- 1mo ago First seen · 184 lines · 54 tokens per session scan A 526db320059f
theokit-ui is a skill published in the GitHub repository usetheokit/theokit (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,955 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
continuum-llm-providers
Pick the right LLM provider, configure structured outputs, control context-window compression, and use the LLMClient directly. Provider routing is by model-string prefix; LiteLLM has been removed. Also covers Smart Gateway integration for multi-provider routing. Invoke when the user asks about "switch to Claude"…
continuum-handoffs
Build agent-to-agent transitions with Continuum's Handoff system — triage routing, history summarization modes (FULL/SUMMARY/RECENTN/HYBRID), cycle detection, depth tracking, return-to-parent. Invoke when the user asks "route customer requests to specialists", "agent that can transfer to another", "summarize history…
continuum-observability
Trace agent runs with Langfuse, decorate functions with @observe, collect latency/token/error metrics, and report errors. Invoke when the user asks about "see what the LLM was prompted with", "Langfuse traces", "track latency", "metrics dashboard", "error reporting", or "instrument my function".
continuum-temporal
Build durable agent workflows with Temporal — sequential/parallel/loop/conditional steps, human-in-the-loop approval gates, custom workflows and activities. Invoke when the user asks "long-running workflow", "approval gate", "human in the loop", "retry on failure", "workflow survives restart", or anything…
continuum-testing
Write tests for Continuum agents — mock LLM and memory clients via the DI Container, use fakeredis for sessions, snapshot agent responses, and run pytest-asyncio. Invoke when the user asks "test my agent", "mock the LLM", "fakeredis", "container injection", "pytest", or wants their CI to validate agent behavior…