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 skills add toffyui/ccteams --skill frontend-playbookgit clone --depth 1 https://github.com/toffyui/ccteamsWrote 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/toffyui/ccteams/frontend-playbook)<a href="https://agentmods.dev/skills/toffyui/ccteams/frontend-playbook"><img src="https://agentmods.dev/badge/skills/toffyui/ccteams/frontend-playbook/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/toffyui/ccteams/frontend-playbook"><img src="https://agentmods.dev/badge/skills/toffyui/ccteams/frontend-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 202 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 205 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.03654 |
| Opus 5 | $0.00027 | $0.01827 |
| Sonnet 5 | $0.00011 | $0.00731 |
| Haiku 4.5 | $0.00005 | $0.00365 |
Grade A, and why
frontend-playbook 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 9d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend (UI / UX / a11y) Playbook
This is the literal procedure to follow for any user-facing UI change, in any framework (React, Vue, Svelte, plain HTML). The single most expensive class of mistake here is building UI you never watched a human operate — so the loop forces you to run the app and drive it by keyboard before you declare anything done. The second is inventing CSS/components that already exist in the project — so the loop forces you to read the design system before you add to it.
Operating loop
- Reproduce the current UI state first. Run the app (
npm run dev/pnpm dev/ the project's start script) and open the actual screen you are changing before writing anything. A screenshot or a description is not the screen; render it. If you cannot run it, STOP and report what's missing (start command, env, seed data) rather than editing blind. - Detect the stack from evidence, not assumption. Read
package.jsondependencies for the framework (React/Vue/Svelte/none) and the styling system (Tailwind, CSS Modules, styled-components, vanilla CSS, atailwind.config, atokens.*file, atheme.*). Note whether TypeScript is in use. Do not introduce a framework or styling approach the project does not already use. - Read the design tokens and component library BEFORE writing CSS. Find
the existing spacing scale, color tokens, typography scale, breakpoints, and
any component primitives (a
Button,<ui/>, shadcn, Radix, Headless UI, Vuetify).grepthe codebase for the class/token you're about to invent — it usually already exists under a different name. New CSS is a last resort, justified in your report. - Read two sibling components and mirror their markup structure, naming, class conventions, and file placement. Do not introduce a second convention in a codebase that already has one.
- Choose the semantic element before any styling (decision tree A). Pick
the native element whose behavior you want (
<button>,<a>,<nav>,<label>,<dialog>,<details>); reach for ARIA only when no native element fits. - Colocate state at its lowest owner (decision tree B). Do not lift state or hoist a value into a store/context until a second consumer actually exists.
- Reuse before you write (decision tree C). An existing token/utility/ component beats new CSS every time.
- Run the verification recipe (below) and report real output. The keyboard-only walkthrough and the 320/768/1280 resize are not optional — they are where UI bugs actually live.
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.
- 9d ago First seen · 241 lines · 54 tokens per session scan A b9c5c1a0d76d
frontend-playbook is a skill published in the GitHub repository toffyui/ccteams (48 stars, last pushed 9d ago), licensed MIT. It adds 54 tokens to every session and 3,654 once invoked, about $0.0003 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 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…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.