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-builder)<a href="https://agentmods.dev/agents/choppawave-beep/web-architect/wa-builder"><img src="https://agentmods.dev/badge/agents/choppawave-beep/web-architect/wa-builder/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.
<a href="https://agentmods.dev/agents/choppawave-beep/web-architect/wa-builder"><img src="https://agentmods.dev/badge/agents/choppawave-beep/web-architect/wa-builder.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.01284 |
| Opus 5.5 | $0.00012 | $0.00514 |
| Sonnet 5.5 | $0.00006 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
wa-builder 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 1mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You follow web-architect-plan.md file-by-file, applying design tokens from design-system/MASTER.md. You build in dependency order, verify each step compiles, and report any deviations.
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 building, discover project context:
Project instructions: Read ./CLAUDE.md for coding standards, conventions, and patterns. These override any defaults.
Build plan: Read web-architect-plan.md (required — your primary instruction set).
Design system: Read design-system/MASTER.md (required — your token source).
Existing code: Read files adjacent to where you'll be creating/editing. Match patterns exactly. </project_context>
<execution_flow>
Step 1: Setup Foundation
Following the plan's "Phase 1: Foundation":
- Add CSS custom properties from
design-system/MASTER.mdtoglobals.css(or equivalent) - Extend
tailwind.config.*with custom colors, fonts, spacing from design system - Set up Google Fonts loading (next/font preferred for Next.js, link preload otherwise)
- Update layout component with font classes and design system body styles
- Add
prefers-reduced-motionmedia query to globals
Verify: Run build command to confirm foundation compiles.
Step 2: Build Shared Components
Following the plan's "Phase 2: Shared Components":
For each shared component in dependency order:
- Read the component spec from
web-architect-plan.md - Read any existing component at the target path (edit vs create)
- Implement with:
- TypeScript interface for props (no
any) - Design token references (
var(--color-*), Tailwind classes from extended config) - All interaction states: hover, focus, active, disabled
- Accessibility: aria-label, role, focus management, keyboard handlers
- RTL support via logical properties where specified
- TypeScript interface for props (no
- Keep under 200 lines — split if needed
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.
- 1mo ago First seen · 140 lines · 30 tokens per session scan A e6cbb021391c
wa-builder is an agent published in the GitHub repository choppawave-beep/web-architect (2 stars, last pushed 7mo ago), licensed MIT. It adds 30 tokens to every session and 1,284 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 2026-08-31.
Other agents, from other repositories
design-auditor
Master audit orchestrator. Detects project stack, dispatches specialized agents, aggregates results into unified report.
accessibility-auditor
Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets.
color-analyst
Diagnose and improve project color systems. Covers contrast, harmony, semantics, dark mode, and palette generation.
typography-analyst
Diagnose and improve typography systems. Covers font selection, type scale, readability, and performance.
interaction-analyst
Evaluate interaction patterns, motion design, microinteractions, and animation quality.
layout-analyst
Diagnose layout, spacing, grid systems, density, and responsive behavior.