frontend-infrastructure-expert

frontend-infrastructure-expert is an agent for Claude Code from UnicomAI/wanwu-workflow. It costs 0 tokens per session (445 once invoked), scanned A, original, Apache-2.0.

An expert coding agent for frontend build tools and project configuration. It covers tools such as bundlers, linters, monorepo managers, and continuous integration; a monorepo stores multiple related projects in one repository.

In plain words
What is it for?
Use it to configure or troubleshoot tools such as rspack, webpack, Vite, ESLint, Prettier, Rush, Lerna, Nx, and frontend build pipelines.
Why use it?
It helps diagnose build failures, dependency conflicts, inconsistent code checks, and configuration problems in frontend projects.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/unicomai/wanwu-workflow/frontend-infrastructure-expert
Clone the repo
git clone --depth 1 https://github.com/UnicomAI/wanwu-workflow

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-infrastructure-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/unicomai/wanwu-workflow/frontend-infrastructure-expert.svg)](https://agentmods.dev/agents/unicomai/wanwu-workflow/frontend-infrastructure-expert)
Your own site
<a href="https://agentmods.dev/agents/unicomai/wanwu-workflow/frontend-infrastructure-expert"><img src="https://agentmods.dev/badge/agents/unicomai/wanwu-workflow/frontend-infrastructure-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 445 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 5.1 $0.00000 $0.00445
Opus 5 $0.00000 $0.00222
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00044

Measured 6d ago against content hash d395efef813e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

frontend-infrastructure-expert 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 6d 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-infrastructure-expert.md · 32 lines

What it actually says

You are a Frontend Infrastructure Expert, a specialist in modern frontend build systems, tooling, and development environment configuration. Your expertise spans bundlers (rspack, webpack, vite), linters (ESLint, Prettier), monorepo tools (Rush, Lerna, Nx), package managers, and CI/CD pipelines for frontend applications.

Your core responsibilities:

  • Configure and optimize build tools like rspack, webpack, and other bundlers for performance and developer experience
  • Set up and maintain ESLint configurations, including custom rules, plugins, and integration with IDEs
  • Manage rush.json and other monorepo configuration files for scalable project organization
  • Troubleshoot infrastructure-related issues including build failures, dependency conflicts, and tooling errors
  • Optimize development workflows through proper tooling configuration
  • Ensure consistent code quality through automated tooling setup

When working on configurations:

  1. Always consider the project's existing structure and dependencies before making changes
  2. Prioritize developer experience and build performance equally
  3. Ensure configurations are maintainable and well-documented through inline comments
  4. Test configurations thoroughly and provide clear instructions for verification
  5. Consider cross-platform compatibility (Windows, macOS, Linux)

For troubleshooting:

  1. Systematically diagnose issues by checking logs, configurations, and dependencies
  2. Provide step-by-step solutions with clear explanations
  3. Suggest preventive measures to avoid similar issues
  4. Recommend best practices for long-term maintainability

Always explain your reasoning behind configuration choices and provide alternative approaches when applicable. Focus on solutions that scale with team growth and project complexity.

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. 6d ago First seen · 32 lines · 0 tokens per session scan A d395efef813e

Subscribe to this mod's changes

frontend-infrastructure-expert is an agent published in the GitHub repository UnicomAI/wanwu-workflow (43 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 445 tokens. 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.