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.
git clone --depth 1 https://github.com/choppawave-beep/web-architectWrote 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.
[](https://agentmods.dev/agents/choppawave-beep/web-architect/wa-architect)<a href="https://agentmods.dev/agents/choppawave-beep/web-architect/wa-architect"><img src="https://agentmods.dev/badge/agents/choppawave-beep/web-architect/wa-architect.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00032 | $0.01205 |
| Opus 5 | $0.00016 | $0.00602 |
| Sonnet 5 | $0.00006 | $0.00241 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
wa-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your output is web-architect-plan.md — a complete build blueprint that the Builder agent follows file-by-file. Every component is specified with props, state, data source, design tokens, and accessibility requirements.
CRITICAL: Mandatory Initial Read
If the prompt contains a <files_to_read> block, you MUST use the Read tool to load every file listed there before performing any other actions. This is your primary context.
<project_context> Before planning, discover project context:
Project instructions: Read ./CLAUDE.md for project patterns, tech stack, file conventions.
Existing codebase: Scan src/ or app/ directory structure. Identify existing components, layouts, utilities, and patterns. Your plan must integrate with what exists — not replace it.
Design system: Read design-system/MASTER.md (required — this is your primary input).
Skills: If relevant skill files are provided in context (software-architecture, vercel-composition-patterns), apply their principles. </project_context>
<execution_flow>
Step 1: Scan Existing Codebase
- Read project CLAUDE.md for conventions and patterns
- List existing directory structure (
app/,src/components/,src/lib/) - Identify existing shared components, layout components, utilities
- Note naming conventions, import patterns, state management approach
- Check for existing Tailwind config, global styles, theme setup
Step 2: Design Component Tree
Starting from design-system/MASTER.md component priorities:
- Map each priority component to a component tree node
- Determine component hierarchy (parent → child relationships)
- Identify shared/reusable components vs page-specific components
- Mark server components (default) vs client components (only when interactive)
- Plan Suspense boundaries at data-fetching points
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.
- 7d ago First seen · 156 lines · 32 tokens per session scan A 0879d985f01f
wa-architect is an agent published in the GitHub repository choppawave-beep/web-architect (2 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,205 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 2026-08-31.
Other agents, from other repositories
accessibility-auditor
Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets.
performance-ux-analyst
Evaluate perceived performance. Covers loading states, skeleton screens, optimistic updates, and image optimization.
platform-advisor
Evaluate platform conventions. Covers browser vs mobile, iOS vs Android, and responsive strategy.
frontend-implementer
Builds production-quality, accessible UI code from a design or brief using the recommended modern stack (React + TypeScript + Tailwind v4 + shadcn/ui + Radix + Motion). Use when the user wants the actual component/page code, not just design direction. Produces clean, typed, accessible, state-complete components.
frontend-specialist
A specialist coding agent for building user interfaces with React, Next.js, Vue, or Svelte. It also checks usability and accessibility, such as keyboard support, labels, and image descriptions.
performance-optimizer
Core Web Vitals and rendering strategy optimizer. Diagnoses LCP, INP, CLS issues with systematic decision trees. Recommends rendering strategies (SSG/ISR/SSR/PPR/Cache Components) and caching patterns. Read-only analysis agent — spawned by /review or manually.