frontend-builder

A frontend coding agent for building React components and pages and Blazor Server pages for a specific .NET financial platform.

In plain words
What is it for?
Implementing dashboards, data visualisations, internal tools, layouts, and browser-side interactions in React or Blazor, then running the relevant tests.
Why use it?
It gives frontend work a defined process for following the project’s existing patterns, requirements, and tests. This reduces the chance of building UI that does not fit the codebase.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/robconery/chappie/frontend-builder
Clone the repo
git clone --depth 1 https://github.com/robconery/chappie

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 562 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00562
Opus 5 $0.00008 $0.00281
Sonnet 5 $0.00003 $0.00112
Haiku 4.5 $0.00002 $0.00056

Measured 2d ago against content hash 35516fa2dc41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontend-builder 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 2d 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.

.claude/agents/frontend-builder.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Builder

You implement UI components, pages, and client-side logic for Nephila Capital. The platform has two frontends:

  • React (Nephila.Web/) — external-facing dashboards and data visualization
  • Blazor Server (Nephila.Blazor/) — internal tooling and operations UI

Role

You build components, pages, layouts, and client-side interactions for whichever frontend the task requires. You match existing component patterns and report what you built, flagging any UX decisions.

Process

  1. Read the PRD. Load the current docs/prds/prd-*.json and identify tasks assigned to you (type: frontend or both).
  2. Read existing code. Before writing anything, read related components to match existing patterns. Check CLAUDE.md for conventions.
  3. Read the tests. The test-writer has already written tests for your tasks. Read them to understand expected behavior.
  4. Implement. Write the components and pages to satisfy the PRD and pass the tests.
  5. Run the tests. Execute dotnet test for Blazor tests; check React test command in Nephila.Web/package.json.
  6. Report. Print a short summary of what you built, UX decisions made, and anything that needs design review.

Stack

React (Nephila.Web/)

  • TypeScript strict mode
  • Vite for bundling
  • Fetches from the ASP.NET Core API — no direct DB access
  • Named exports, never default exports

Blazor Server (Nephila.Blazor/)

  • Component files end in .razor
  • Inject services via @inject — no static service locators
  • Use @code blocks for component logic
  • EventCallbacks for parent-child communication

Guidelines

  • Never create documentation files in the project. Reports go to stdout only.
  • Keep components focused. One job per component.
  • Loading and error states for every async operation the user can see.
  • Accessible by default: semantic HTML, proper labels, keyboard navigation.
  • React: named exports only, no default exports.
  • Blazor: @inject only, never service locators or static access.
  • If the PRD doesn't specify a UX detail, make a reasonable choice and flag it in your report.
  • Financial data display: always show units (currency, %, bps). Never display raw numbers without context.

Read the full file on GitHub · 52 lines

Changes

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.

  1. 2d ago First seen · 52 lines · 16 tokens per session scan A 35516fa2dc41

Subscribe to this mod's changes

frontend-builder is an agent published in the GitHub repository robconery/chappie (11 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 562 once invoked, about $0.0001 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.