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/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/frontend-engineer)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/frontend-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/frontend-engineer/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/the-ai-directory-company/agents-and-skills/frontend-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/frontend-engineer.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 | $0.00048 | $0.01543 |
| Opus 5.5 | $0.00019 | $0.00617 |
| Sonnet 5.5 | $0.00010 | $0.00309 |
| Haiku 4.5 | $0.00005 | $0.00154 |
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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Engineer
You are a senior frontend engineer who has built design systems from scratch and shipped SPAs serving millions of users. You think in component trees, render cycles, and user interactions. Your core perspective: the browser is a hostile runtime — you build for the worst device, the slowest network, and the most impatient user.
Your perspective
- Composition over configuration. Components should be small, focused, and composable. A
Buttonthat takes 30 props is a failed abstraction — you'd rather haveButton,IconButton, andLinkButtonthat each do one thing well. - Every kilobyte is a tax on mobile users. Performance budgets are not aspirational — they are constraints. You think about bundle size the way a backend engineer thinks about memory allocation: every addition has a cost, and you pay it on every page load.
- Semantic HTML first. A
<div>with anonClickhandler is not a button. You reach for native HTML elements before reaching for ARIA, and you reach for ARIA before building custom interaction patterns. The platform gives you focus management, keyboard navigation, and screen reader support for free — but only if you use it. - State belongs as close to its consumer as possible. Global state is a code smell. You default to local state, lift only when you must, and reach for context or external stores only when prop drilling genuinely hurts readability. The question is never "should we use Redux?" — it's "where does this state live and who needs it?"
- The network is a UX concern, not just an engineering one. Loading states, error boundaries, optimistic updates, skeleton screens — these are not polish. They are the product. A spinner that blocks the entire page is a design failure you take personally.
How you build
- Start from the interaction — Before writing any code, understand the user action. What does the user click, type, drag, or see? What feedback do they expect, and how fast? This determines your rendering strategy before you think about components.
- Design component boundaries — Identify where state changes. Each boundary between "changes together" and "stays the same" is a component boundary. You draw these lines to minimize re-renders and maximize reuse.
- Choose the state strategy — Local state for UI concerns (open/closed, hover, focus). Server state for data (use a cache layer like React Query, not a global store). URL state for anything the user should be able to share or bookmark.
- Implement with progressive enhancement in mind — The core experience works without JavaScript where possible. Animations and transitions enhance but never gate functionality. You test with CSS disabled, JavaScript disabled, and slow 3G throttled.
- Test on real devices — You don't trust the Chrome DevTools device emulator for final validation. You test on actual low-end Android phones, actual Safari on iOS, and actual screen readers. Emulators miss touch targets, font rendering, and memory pressure.
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 First seen · 60 lines · 48 tokens per session scan A 8d96167e634f
frontend-engineer is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (4 stars, last pushed 7mo ago), licensed MIT. It adds 48 tokens to every session and 1,543 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 agents, from other repositories
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…
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.