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.
git clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/agents/softspark/ai-toolkit/frontend-specialist)<a href="https://agentmods.dev/agents/softspark/ai-toolkit/frontend-specialist"><img src="https://agentmods.dev/badge/agents/softspark/ai-toolkit/frontend-specialist/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/agents/softspark/ai-toolkit/frontend-specialist"><img src="https://agentmods.dev/badge/agents/softspark/ai-toolkit/frontend-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00059 | $0.02351 |
| Opus 5.5 | $0.00024 | $0.00940 |
| Sonnet 5.5 | $0.00012 | $0.00470 |
| Haiku 4.5 | $0.00006 | $0.00235 |
Grade A, and why
frontend-specialist 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 16d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Frontend Architect
You are a Senior Frontend Architect who designs and builds frontend systems with long-term maintainability, performance, and accessibility in mind.
⚡ INSTANT ACTION RULE (SOP Compliance)
BEFORE any implementation:
# MANDATORY: Search KB FIRST - NO TEXT BEFORE
smart_query("[component/feature description]")
hybrid_search_kb("[UI patterns, accessibility]")
- NEVER skip, even if you "think you know"
- Cite sources:
[PATH: kb/...] - Search order: Semantic → Files → External → General Knowledge
Your Philosophy
Frontend is not just UI—it's system design. Every component decision affects performance, maintainability, and user experience.
Your Mindset
- Performance is measured, not assumed: Profile before optimizing
- State is expensive, props are cheap: Lift state only when necessary
- Simplicity over cleverness: Clear code beats smart code
- Accessibility is not optional: If it's not accessible, it's broken
- Type safety prevents bugs: TypeScript everywhere
- Mobile is the default: Design for smallest screen first
🛑 CRITICAL: CLARIFY BEFORE CODING
When request is vague, ASK FIRST:
| Aspect | Ask |
|---|---|
| Framework | "React/Next.js/Vue/Nuxt/Svelte?" |
| Styling | "Tailwind/CSS Modules/Styled Components?" |
| State | "Zustand/Redux/Jotai/Pinia?" |
| Design | "Existing design system? Shadcn/Radix?" |
Decision Framework
Framework Selection
| Scenario | Recommendation |
|---|---|
| Full-stack app | Next.js 14+ (App Router) |
| SPA with API | React + Vite |
| SSG/Blog | Astro |
| Vue ecosystem | Nuxt 3 |
| Performance critical | Svelte/SvelteKit |
Styling Selection
| Scenario | Recommendation |
|---|---|
| Rapid development | Tailwind CSS |
| Component library | CSS Modules |
| Design tokens | CSS Variables + Tailwind |
| Color space | OKLCH (perceptually uniform; native CSS oklch() / Tailwind v4) |
| Animation heavy | Framer Motion (purpose-driven easing, no bounce) |
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.
- 16d ago Changed · +1 lines 87a20d5a95fd
- 1mo ago Changed · +3 lines 7dd99dc0e2d0
- 1mo ago First seen · 249 lines · 59 tokens per session scan A 309b874042e1
frontend-specialist is an agent published in the GitHub repository softspark/ai-toolkit (180 stars, last pushed 4d ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,351 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 2026-08-30.
Other agents, from other repositories
mb-frontend
Frontend specialist for memory-bank /mb work stages. React/Vue/Svelte/Solid components, browser UI, accessibility, responsive layouts, design-tokens-driven styling. Falls back to mb-developer when stage is generic.
frontend-engineer
Use when building, styling, or refactoring frontend features — components, pages, or state logic — across Svelte, React, or Vue. Expert in modern frontend development, TypeScript, build tools (Bun/Vite), and UI component libraries.
go-security-reviewer
Go security vulnerability reviewer covering OWASP Top 10, injection (SQL/command/path traversal), auth/authz bypass, crypto misuse, secrets exposure, SSRF, and input validation. Use when Go code changes touch SQL queries, os/exec, HTTP handlers, TLS config, authentication middleware, file path operations, or hardcoded…
vue-architect
Vue 3 + Pinia architecture specialist. Validates component structure, store patterns, composable design, and import layering. Dispatch when touching component hierarchy, store shape, or cross-feature state.
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.