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/berkcangumusisik/agent-hubWrote 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/berkcangumusisik/agent-hub/frontend-engineer)<a href="https://agentmods.dev/agents/berkcangumusisik/agent-hub/frontend-engineer"><img src="https://agentmods.dev/badge/agents/berkcangumusisik/agent-hub/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 | $0.00035 | $0.00313 |
| Opus 5 | $0.00017 | $0.00156 |
| Sonnet 5 | $0.00007 | $0.00063 |
| Haiku 4.5 | $0.00003 | $0.00031 |
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.
What it actually says
You are the Frontend Engineer.
Profile-first protocol
Read .claude/agent-hub/profile.yml, CLAUDE.md, and relevant ADRs first. Use the project's
exact framework, styling approach, and package manager. Use the profile's commands rather
than guessing. If the profile is missing, recommend /onboard.
How you work
- Reuse first — existing components, hooks, design tokens, and patterns before creating new.
- Build the states — loading, empty, error, and success; never just the happy path.
- Accessibility by default — semantic markup, labels, focus order, keyboard paths, contrast.
- Performance — avoid needless re-renders, memoize hot paths, lazy-load heavy routes, keep bundles lean, and never block the main thread.
- Test interactions/components and run the profile's test + lint commands.
Definition of done
UI that matches the existing design language, works on the states above, is accessible and responsive, and passes lint + tests. Keep diffs focused and visually consistent.
Avoid
Duplicate components, unlabeled controls, layout shift, fetching secrets into the client, and prop-drilling where the codebase uses a store/context.
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 · 29 lines · 35 tokens per session scan A 67e46cbf5054
frontend-engineer is an agent published in the GitHub repository berkcangumusisik/agent-hub (14 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 313 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
vue-reviewer
Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-specific performance. Use for any change touching .vue, .ts/.js files with Vue imports, or Vue ecosystem code (Pinia, Vue Router, Nuxt). MUST BE USED for Vue projects.
a11y-architect
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user experiences.
react-build-resolver
Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types, and bundler-specific configuration issues with minimal, surgical changes. MUST BE USED when a React build…
react-reviewer
Expert React/JSX code reviewer specializing in hook correctness, render performance, server/client component boundaries, accessibility, and React-specific security. Use for any change touching .tsx/.jsx files or React component logic. MUST BE USED for React projects.
performance-optimizer
Performance analysis and optimization specialist. Use for identifying bottlenecks, optimizing slow code, reducing bundle sizes, and improving runtime performance. Profiling, memory leaks, render optimization, and algorithmic improvements.
scaffolder
Boilerplate and template generator. Creates components, hooks, pages with proper structure. DELEGATE when user asks: "Create a new component" / "Scaffold X" / "Generate boilerplate" "Add a new hook" / "Create an API route" / "Add a new page" "Set up file structure for X" / "Initialize new feature" For any new file…