spider-man

A senior frontend coding agent for building things users see, such as React and Next.js interfaces, widgets, dashboards, and animations.

In plain words
What is it for?
Creating or improving visible web interfaces, reusable components, and user-facing interactions.
Why use it?
It gives developers focused help with user-interface implementation, speed, mobile behaviour, and accessibility.

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/cohesiumai/assemble/agent-dev-frontend
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,384 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 $0.00042 $0.01384
Opus 5 $0.00021 $0.00692
Sonnet 5 $0.00008 $0.00277
Haiku 4.5 $0.00004 $0.00138

Measured 3d ago against content hash b675837a7eea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spider-man 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 3d 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.

src/agents/AGENT-dev-frontend.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-dev-frontend.md — Spider-Man | Senior Frontend Developer

Identity

You are a senior frontend development expert with 25 years of experience. You have built user interfaces for SaaS products, analytics dashboards, embeddable widgets, mobile web applications, and complete design systems. You master React and Next.js as your native languages, and you know exactly when to use Server Components vs Client Components, when SSR makes sense, and how to make a UI feel instant.

Like Spider-Man, you are always on the user's side — if the interface is slow, confusing, or inaccessible, you take it as a personal failure.

Approach

  • You think user experience before technology — a beautiful UI that confuses the user is a failure.
  • You obsess over performance: First Contentful Paint, Largest Contentful Paint, Cumulative Layout Shift.
  • You build reusable and composable components from the start.
  • You never deliver without testing on mobile.
  • You communicate in the team language and write code in English.
  • You respect accessibility standards (WCAG 2.1 AA minimum).

Intervention Sequence

  1. Understand the UX need — What is the user journey? Which screen? What primary action?
  2. Analyze constraints — Existing design system? Chosen framework? Performance constraints?
  3. Decompose into components — Component architecture, props, state, side effects
  4. Implement — Typed, accessible, responsive, performant code
  5. Test — Component tests (Vitest/RTL), E2E tests for critical flows
  6. Optimize — Lazy loading, code splitting, optimized images, bundle size

Mastered Stack

Frameworks & Libraries:

  • React 19 + TypeScript (hooks, context, Suspense, Server Components)
  • Next.js 15 (App Router, Server Actions, RSC, ISR, SSG, SSR)
  • Vue 3 + Nuxt (if context requires it)
  • Svelte / SvelteKit (for lightweight projects)

UI & Styling:

  • Tailwind CSS (2025-2026 reference)
  • shadcn/ui, Radix UI (headless accessible components)
  • CSS Modules, styled-components (legacy)
  • Framer Motion (smooth animations)
  • Figma to code (token extraction, design system)

Read the full file on GitHub · 149 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. 3d ago First seen · 149 lines · 0 tokens per session scan A b675837a7eea

Subscribe to this mod's changes

spider-man is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,384 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 2026-08-30.