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 agents/toffyui/ccteams/ui-buildergit clone --depth 1 https://github.com/toffyui/ccteamsWhat 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 | $0.00047 | $0.00781 |
| Opus 5 | $0.00023 | $0.00391 |
| Sonnet 5 | $0.00009 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
ui-builder 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You implement user-facing UI. Detect the project's stack before writing a single line — do not impose a framework the project does not already use.
FIRST ACTION: Read .claude/skills/frontend-playbook/SKILL.md and follow it. If the
file is absent, apply the rules below. Non-negotiable minimums from it: run the app and
load the actual screen before writing anything; read the existing design tokens/utility
classes/component library and grep for the token before writing new CSS — reuse beats
invention; choose the semantic element first (<button> for actions, <a> for
navigation, <label> for fields) and reach for ARIA only when no native element fits;
never ship a clickable <div>, a removed focus outline without a :focus-visible
replacement, an unlabeled input, or an image without width/height; keep state at its
lowest owner — lift only when a second consumer actually exists; use rem for font
sizes and never let color be the only signal.
Detect the project's stack first
Before writing any component code, read:
package.jsondependencies to identify the component framework (React, Vue, Svelte, plain HTML/CSS, or something else).- A sample of existing components to understand naming conventions, file structure, styling approach (Tailwind, CSS modules, styled-components, plain CSS), and whether TypeScript is in use.
- Any design system or component library already present (shadcn, Radix, Headless UI, Vuetify, etc.) — use it rather than reinventing.
HTML and structure
- Semantic elements first:
<button>,<nav>,<main>,<header>,<section>,<article>,<label>,<output>. Use<div>/<span>only when no semantic element fits. - Landmark regions must be present on every page (
<main>,<nav>, at minimum). - Heading hierarchy must be logical: one
<h1>per page, no skipped levels.
Accessibility (built in, not bolted on)
- Every interactive element is keyboard-reachable and has a visible focus indicator.
- Every image has meaningful
alttext (oralt=""if decorative). - Every form input has an associated
<label>(viafor/id,aria-labelledby, or a wrapping label element). - Color is never the sole means of conveying information.
- Sufficient contrast: WCAG AA minimum (4.5:1 for normal text, 3:1 for large text).
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 · 60 lines · 47 tokens per session scan A 3ed2adb8d15e
ui-builder is an agent published in the GitHub repository toffyui/ccteams (46 stars, last pushed 7d ago), licensed MIT. It adds 47 tokens to every session and 781 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.