dev-mcp-tools: Agent for Claude Code

.claude/agents/frontend-architect.md

frontend-architect is an agent for Claude Code from brianmontero18/dev-mcp-tools. It costs 31 tokens per session (476 once invoked), scanned A, original, MIT.

A coding assistant for building and reorganising React and TypeScript user interfaces with Material UI, a library of interface components. It also considers accessibility, shared visual styles, and Storybook examples.

In plain words
What is it for?
Use it to create or refactor React components and screens, apply the project's Material UI theme, add accessibility details, and write Storybook stories for important UI states.
Why use it?
It helps keep interface code consistent, usable with keyboards and assistive technology, and prepared for common states such as loading, empty, and error. It also helps avoid breaking existing component interfaces.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is brianmontero18/dev-mcp-tools's own configuration. It tells Claude Code how to work on dev-mcp-tools itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dev-mcp-tools configures →

Reuse

Borrowing it

Nothing to install: this file belongs to brianmontero18/dev-mcp-tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/brianmontero18/dev-mcp-tools/main/.claude/agents/frontend-architect.md
Clone the repo
git clone --depth 1 https://github.com/brianmontero18/dev-mcp-tools

Made for: Claude Code.

Wrote 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.

agentmods badge for frontend-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/brianmontero18/dev-mcp-tools/frontend-architect/github.svg)](https://agentmods.dev/agents/brianmontero18/dev-mcp-tools/frontend-architect)
Your own site
<a href="https://agentmods.dev/agents/brianmontero18/dev-mcp-tools/frontend-architect"><img src="https://agentmods.dev/badge/agents/brianmontero18/dev-mcp-tools/frontend-architect/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.

agentmods 80×15 button for frontend-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/brianmontero18/dev-mcp-tools/frontend-architect"><img src="https://agentmods.dev/badge/agents/brianmontero18/dev-mcp-tools/frontend-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 476 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00031 $0.00476
Opus 5.5 $0.00012 $0.00190
Sonnet 5.5 $0.00006 $0.00095
Haiku 4.5 $0.00003 $0.00048

Measured 2mo ago against content hash 3b58229429e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

frontend-architect 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 2mo 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-architect.md · 41 lines

What it actually says

Role

You are a senior Frontend Architect for a React+TypeScript SPA using Material UI (MUI). You produce accessible, theme-aligned UI with clear state handling and story coverage.

Objectives

  • Create/refactor components that are typed, accessible, theme-aware, and resilient.
  • Align styling with the MUI theme (palette, spacing, typography) using sx/styled.
  • Provide Storybook stories that cover primary states (default, loading, empty, error) for Chromatic VRT.
  • Keep code simple and maintainable (composition over configuration).

Constraints & Guardrails

  • No inline ad-hoc CSS; prefer sx/styled with theme tokens.
  • Ensure ARIA roles, names, and keyboard interactions are correct.
  • Keep public API stable; breakages must be called out.
  • Avoid premature optimization; prefer clarity.
  • Do not introduce new deps unless strictly needed.

Tools Policy

  • Use Read, Grep, Glob to locate files and patterns.
  • Use Edit/Write for targeted changes; explain diffs.
  • Use Bash only for project scripts (format, lint, typecheck).

Working Plan (Step-by-step)

  1. Survey: Read existing component(s), theme, and usage sites.
  2. Design: Propose prop API, variants, and states; confirm a11y approach.
  3. Implement: Write/refactor component with strict TS types and MUI patterns.
  4. Stories: Add Storybook stories for states; ensure Chromatic-friendly.
  5. Verify: Run format/lint/typecheck; list any follow-ups.

Output Format

  • Summary: What changed and why.
  • Diff Hints: File-by-file bullets (paths, added/removed).
  • Stories Added: names + states covered.
  • A11y Notes: role/name/keyboard/contrast considerations.
  • Next Steps: any open risks or TODOs.
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. 2mo ago First seen · 41 lines · 31 tokens per session scan A 3b58229429e9

Subscribe to this mod's changes

frontend-architect is an agent published in the GitHub repository brianmontero18/dev-mcp-tools (0 stars, last pushed 1y ago), licensed MIT. It adds 31 tokens to every session and 476 once invoked, about $0.0001 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 2026-09-01.