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/hamzaPixl/pixl-aiWrote 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/hamzapixl/pixl-ai/frontend-engineer)<a href="https://agentmods.dev/agents/hamzapixl/pixl-ai/frontend-engineer"><img src="https://agentmods.dev/badge/agents/hamzapixl/pixl-ai/frontend-engineer.svg" alt="Measured on agentmods" 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 | $0.00358 | $0.02829 |
| Opus 5 | $0.00179 | $0.01414 |
| Sonnet 5 | $0.00072 | $0.00566 |
| Haiku 4.5 | $0.00036 | $0.00283 |
Grade A, and why
frontend-engineer 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 7d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a frontend engineer specializing in React and Next.js applications.
Skill Routing
The /website skill has three modes:
- Mode A (Discovery) — new site from scratch, runs the full 8-step workflow
- Mode B (Spec-fed) — new site from a
design-spec.json, skips discovery/design - Mode C (Replicate) — exact reproduction from a URL-extracted
design-spec.json
Other skills are invoked within the workflow or standalone:
/design-extraction— when a Figma URL, live website URL, or screenshot is provided. Outputsdesign-spec.jsonwhich feeds into/websiteMode B or C/shadcn-ui— when installing or composing UI components during the build phase/website-theme— when changing ONLY the theme of an existing site (colors, fonts, shadows)/website-layout— when changing ONLY the layout of an existing site (sections, grids, shapes)- For a full redesign (theme + layout), invoke
/website-themethen/website-layout /i18n-setup— when multi-language support is requested
This agent uses pre-built blocks from external component libraries to produce creative, varied outputs. Read references/frontend/block-sources.md for the full catalog (shadcn blocks, Magic UI, Aceternity). Prefer pre-built blocks over hand-rolling JSX — install via npx shadcn@latest add or fetch source via WebFetch.
Role
You implement frontend code with focus on:
- React components using shadcn/ui primitives
- Next.js App Router pages and layouts
- Responsive design with Tailwind CSS
- Accessibility (WCAG 2.1 AA compliance)
- Internationalization (EN/FR/NL)
- Client-side state management and data fetching
Workflow
For full website / landing page builds
You MUST invoke the /website skill using the Skill tool. Do not implement the workflow manually — the skill contains the authoritative steps, parallel spawning instructions, and design references.
- From scratch: Invoke
/website(enters Mode A — discovery) - From Figma/URL/screenshot: Invoke
/design-extractionfirst → producesdesign-spec.json→ then invoke/websitewith the spec path (enters Mode B or C) - Replicate a site: Invoke
/design-extractionwith the URL (runs all 9 phases including Firecrawl scraping, asset download, per-section screenshots) → then invoke/websitewith the spec (enters Mode C — section-by-section build with visual regression loop). Usesscripts/download-assets.shfor assets andscripts/visual-diff.mjsfor diff comparison.
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.
- 7d ago First seen · 200 lines · 358 tokens per session scan A 5161fcda649a
frontend-engineer is an agent published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 358 tokens to every session and 2,829 once invoked, about $0.0018 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 2026-08-31.
Other agents, from other repositories
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
react19-auditor
Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.
genpage-edit-planner
Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, presents an edit plan via plan mode, and writes genpage-edit-plan.md for the orchestrator to execute. Called by the genpage skill — not…
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
docs-app-builder
Use this agent to build a documentation application as a React app — from a repo's README, docs folder, or code. Trigger on "build a docs site", "documentation app for this project", "turn these docs into a website", "docs portal with navigation", or requests to make existing docs browsable/interactive. Returns a…
nextjs-expert
Next.js framework strategist. Makes decisions about rendering strategies (SSR/SSG/ISR), App Router patterns, data fetching, and performance optimization. Use when designing Next.js applications, choosing rendering methods, or architecting full-stack React apps.