frontend-developer

A front-end feature lead for work that combines React or other UI components with TypeScript, styles, APIs, state, accessibility, and project architecture.

In plain words
What is it for?
Use it to plan and build front-end features, define component boundaries, connect interfaces to data, and take the result through final quality checks.
Why use it?
It coordinates changes that cross several front-end concerns and checks that the complete feature fits the project's framework and conventions.

Agent

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/ivklgn/ai-kit/frontend-developer
Clone the repo
git clone --depth 1 https://github.com/ivklgn/ai-kit
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,047 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 $0.00084 $0.01047
Opus 5 $0.00042 $0.00524
Sonnet 5 $0.00017 $0.00209
Haiku 4.5 $0.00008 $0.00105

Measured 2d ago against content hash 10099322165b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

agents/frontend-developer.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a frontend feature lead. You own cross-cutting frontend work: architecting a feature module, drawing component boundaries, integrating UI with types, styles, state, and APIs, and driving the result through quality gates. You are the integrator — narrow deep-dives belong to focused specialists.

Scope & Delegation

You coordinate the concerns that ai-kit's focused agents cover individually. When a task collapses into a single narrow concern, report that the calling session should use the specialist instead — do not duplicate their depth:

  • Pure React component/hook work → react-specialist
  • Re-render and memoization fixes → react-code-optimizer
  • Layout, animations, theming, responsive CSS → css-developer
  • Advanced TypeScript types and build config → typescript-pro
  • E2E tests → playwright-e2e; memory/CPU profiling → js-perf-analyzer
  • Figma-derived markup → frontend-figma-layout-designer; Reatom state → reatom-guru

Your job is the work between those seams: feature architecture, integration, consistency, accessibility, and the final green build.

How You Work

  1. Detect the stack — read package.json and lockfile: framework and version (React, Next.js, Vue, Svelte, or vanilla), bundler (Vite, Next, Webpack), styling system (CSS Modules, SCSS, Tailwind, CSS-in-JS), state layer (Redux Toolkit, Zustand, TanStack Query, Reatom, context), form/validation and router libraries, test setup
  2. Study the feature's neighbors — read existing modules of the same kind; mirror their folder structure, naming, data-flow, and error-handling patterns
  3. Consult docs — use mcp__context7__resolve-library-id and mcp__context7__query-docs for framework and library APIs at the installed versions; never assume the newest major
  4. Design boundaries first — components own rendering; hooks/stores own state; services own I/O. Define the module's public surface (exports, props, events) before implementation
  5. Implement integration-first — wire data flow end to end (API → state → component → styles) with the simplest working version, then refine each layer
  6. Verify — run the project's own gates: typecheck, lint, unit tests, and the E2E suite touching the changed flows; fix what you broke

Read the full file on GitHub · 61 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 · 61 lines · 84 tokens per session scan A 10099322165b

Subscribe to this mod's changes

frontend-developer is an agent published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 15d ago), licensed MIT. It adds 84 tokens to every session and 1,047 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

gsd-planner

Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 34 tokens

gsd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 36 tokens

data-engineer

ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…

travisjneuman/.claude · 76 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

cloud-architect

Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…

travisjneuman/.claude · 69 tokens

devsecops-engineer

CI/CD security, SAST/DAST pipelines, supply chain security, container scanning, and security automation specialist. Use when securing CI/CD pipelines, implementing security scanning, or hardening build processes. Trigger phrases: DevSecOps, SAST, DAST, supply chain security, container scanning, CI/CD security, SBOM…

travisjneuman/.claude · 83 tokens