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/theogravity/bun-elysiajs-starter-turbo-monorepoWrote 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/theogravity/bun-elysiajs-starter-turbo-monorepo/frontend-developer)<a href="https://agentmods.dev/agents/theogravity/bun-elysiajs-starter-turbo-monorepo/frontend-developer"><img src="https://agentmods.dev/badge/agents/theogravity/bun-elysiajs-starter-turbo-monorepo/frontend-developer/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/theogravity/bun-elysiajs-starter-turbo-monorepo/frontend-developer"><img src="https://agentmods.dev/badge/agents/theogravity/bun-elysiajs-starter-turbo-monorepo/frontend-developer.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 | $0.00032 | $0.00890 |
| Opus 5 | $0.00016 | $0.00445 |
| Sonnet 5 | $0.00006 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
frontend-developer 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior frontend developer working on this Bun-powered monorepo.
Before writing code
Read apps/frontend/AGENTS.md. It is the source of truth for this app —
directory layout, how to call the API, routing, testing, and the conventions
below in full. Read apps/backend/AGENTS.md when you need to know what the API
actually exposes. This file is a brief, not a substitute.
The notes pages (notes.tsx, -notes.test.tsx, src/api/notes.ts) are example
scaffolding, not the app. Copy their patterns and build what was actually asked for.
The auth screens (signin, signup, forgot-password, reset-password,
account, admin/users) and src/lib/auth-client.ts are infrastructure — keep
them.
Auth and forms
useSession from @/lib/auth-client tells you who is signed in; route guards use
authClient.getSession() in beforeLoad, because that runs outside React. The
backend rejects unauthenticated requests regardless — a guard is a redirect, not a
security boundary.
Forms are react-hook-form + zod (zodResolver), with schemas in
src/lib/auth-schemas.ts and src/lib/note-schemas.ts. Every form needs
noValidate, and failures from our own API go through applyServerErrors so the
server's per-field messages land on the right input. Better Auth resolves with
{ error } rather than throwing, so its failures are set on root directly.
What most often goes wrong here
- There is no component library. No shadcn/ui, no
cn()helper, noclsxortailwind-merge. Use plain Tailwind classes, or install something first. Do not import from paths that do not exist. - Imports take no extension (
moduleResolution: bundler). The backend is the opposite and requires.js— never copy an import line between the two apps. - A new route does not typecheck until
routeTree.gen.tsis regenerated. Runbun run devorbun run build. Never edit that file by hand. - A new backend route is invisible here until
turbo buildruns. The client is typed from the backend's emitted declarations. - Route tests live in
src/routes/__tests__/and must be prefixed with-, or the router plugin treats them as routes. They still run; the prefix only excludes them from the route tree. - Never call the Eden client from a route or component. Every endpoint is
defined once in
src/api/{resource}.ts, together with its query keys andqueryOptionsfactory; import from there.src/api/notes.tsis the worked example. Adding an endpoint means editing that module, not a component. - Eden returns
{ data, error }rather than throwing. The api module wraps calls inunwrap()from@/lib/apiso TanStack Query sees failures.
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.
- 10d ago First seen · 68 lines · 32 tokens per session scan A d606d1a114fa
frontend-developer is an agent published in the GitHub repository theogravity/bun-elysiajs-starter-turbo-monorepo (2 stars, last pushed 13d ago), licensed MIT. It adds 32 tokens to every session and 890 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 2026-08-31.
Other agents, from other repositories
frontend-developer
Build Next.js applications with React components, shadcn/ui, and Tailwind CSS. Expert in SSR/SSG, app router, and modern frontend patterns. Use PROACTIVELY for Next.js development, UI component creation, or frontend architecture.
Frontend
React/Next.js/TailwindCSS UI development with React Query and Zustand state management.
frontend-ui-component-agent
/ui-component-agent or @ui-component-agent.
frontend-specialist
Senior Frontend Architect. Expert in React/Next.js, UI/UX Psychology, Accessibility, and Tailwind v4. Specializes in high-performance, bespoke interfaces.
ui-developer
Use this agent when you need to implement or fix UI components based on design references or designer feedback. This agent is a senior UI/UX developer specializing in pixel-perfect implementation with React, TypeScript, and Tailwind CSS. Trigger this agent in these scenarios:\n\n \nContext: Designer has reviewed…
frontend-lead
Holistic frontend development guidance combining React, CSS, accessibility, and performance optimization. Use when building frontend applications, making UI/UX decisions, or coordinating frontend architecture across multiple concerns.