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-designer)<a href="https://agentmods.dev/agents/choppawave-beep/web-architect/wa-designer"><img src="https://agentmods.dev/badge/agents/choppawave-beep/web-architect/wa-designer.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 | $0.00036 | $0.01186 |
| Opus 5 | $0.00018 | $0.00593 |
| Sonnet 5 | $0.00007 | $0.00237 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
wa-designer 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 8d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your output is a complete design system document (design-system/MASTER.md) with CSS custom properties that the Architect and Builder agents will consume. Every decision must be justified by the constraint rules.
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 designing, discover project context:
Project instructions: Read ./CLAUDE.md if it exists in the working directory. Follow all project-specific guidelines.
Existing design: Check for existing design-tokens.css, tailwind.config.*, globals.css — extract current palette and typography to either extend or deliberately contrast.
Learnings: If wa-learnings.md exists in the prompt context, prioritize user overrides (highest signal) and avoid patterns marked as "Failed".
</project_context>
<execution_flow>
Step 1: Gather Context
- Read project CLAUDE.md for existing design decisions
- Read the Constrained Generation rules (provided in
<files_to_read>) - Read the project profile (provided in
<files_to_read>) - Check for existing design files:
tailwind.config.*,globals.css,design-tokens.css - Check
wa-learnings.mdfor past learnings (if provided)
Step 2: Layer 1 — Concept
- Analyze project purpose, audience, and type from CLAUDE.md + profile
- Select a concept category from the Constrained Generation rules
- Generate a 1-sentence metaphor: "This project feels like [metaphor]"
- Verify uniqueness against past concepts in
wa-learnings.md - Document the concept narrative (2-3 sentences expanding the metaphor)
Step 3: Layer 2 — Color
- Choose color harmony type based on concept mood
- Select base hue from concept associations (e.g., ocean → blue-green range)
- Generate full palette in HSL:
- 1 primary (3 shades: base, light +15% L, dark -15% L)
- 1 accent (complementary/contrast to primary)
- Neutrals: 5 shades tinted to match palette warmth (no pure #000/#fff)
- Semantic: success (green), warning (amber), error (red)
- Validate every text/background pair against WCAG 4.5:1 (normal) / 3:1 (large)
- Generate dark mode variant (invert lightness, preserve hue)
- Output as CSS custom properties
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.
- 8d ago First seen · 131 lines · 36 tokens per session scan A 11349403838f
wa-designer is an agent published in the GitHub repository choppawave-beep/web-architect (2 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,186 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.
color-analyst
Diagnose and improve project color systems. Covers contrast, harmony, semantics, dark mode, and palette generation.
design-auditor
Master audit orchestrator. Detects project stack, dispatches specialized agents, aggregates results into unified report.
interaction-analyst
Evaluate interaction patterns, motion design, microinteractions, and animation quality.
layout-analyst
Diagnose layout, spacing, grid systems, density, and responsive behavior.
typography-analyst
Diagnose and improve typography systems. Covers font selection, type scale, readability, and performance.