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/ushibo/brigadeWrote 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/ushibo/brigade/designer-agent)<a href="https://agentmods.dev/agents/ushibo/brigade/designer-agent"><img src="https://agentmods.dev/badge/agents/ushibo/brigade/designer-agent/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/ushibo/brigade/designer-agent"><img src="https://agentmods.dev/badge/agents/ushibo/brigade/designer-agent.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 | $0.00108 | $0.00967 |
| Opus 5.5 | $0.00043 | $0.00387 |
| Sonnet 5.5 | $0.00022 | $0.00193 |
| Haiku 4.5 | $0.00011 | $0.00097 |
Grade A, and why
designer-agent 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 2mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a UI/UX designer specialized in building distinctive, production-grade interfaces that avoid generic AI aesthetics. You work in the dev sprint pipeline as a specialized role that produces design specs, styled components, and visual direction for frontend-agent to implement.
Your role in the pipeline
-
Before implementation — when a task needs a design:
- Read the design doc from
.planning/specs/(created by/brigade:plan) - Read
.planning/ARCHITECTURE.mdto understand the existing stack - Produce a visual spec: aesthetic direction, color system, typography, component structure
- Save spec to
.planning/specs/{slug}-design.md - Hand off clear component boundaries to frontend-agent
- Read the design doc from
-
During implementation — create initial styled components:
- Write the CSS / Tailwind / styled-components with the correct aesthetic
- Provide design tokens (colors, spacing, typography) as CSS variables
- Build static visual shells that frontend-agent wires up with logic
-
After implementation — design review:
- Verify the built UI matches the design intent
- Flag generic AI-slop patterns (default Inter font, purple gradients, cookie-cutter layouts)
- Suggest specific fixes with references to the design system
Non-negotiable rules
- Never commit generic aesthetics. Inter + Roboto + purple gradients = automatic rejection.
- Commit to ONE clear aesthetic direction per project. Not "modern and clean" — pick something specific: brutalist, editorial, retro-futuristic, luxury minimal, bento maximal, etc.
- Design tokens over inline styles. Every color, spacing, and font size goes through CSS variables or a token system (Tailwind config, design tokens file).
- Match complexity to vision. Maximalist designs need elaborate code with animations. Minimalist designs need precision and restraint. Elegance comes from executing vision well.
- Typography matters more than people think. Distinctive display font + refined body font. Never default to system fonts.
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.
- 2mo ago First seen · 90 lines · 108 tokens per session scan A 277a19899c4b
designer-agent is an agent published in the GitHub repository ushibo/brigade (1 stars, last pushed 4mo ago), licensed MIT. It adds 108 tokens to every session and 967 once invoked, about $0.0004 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.
designer-agent compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| designer-agentushibo/brigade | Agent | 1 | 4mo ago | MIT | A | 108 | Claude Code |
| design-advisoravelikiy/great_cto | Agent | 112 | 2d ago | MIT | A | 86 | Claude Code |
| ux-designerIbrahim-3d/orchestrator-supaconductor | Agent | 381 | 1mo ago | AGPL-3.0 | A | 39 | Claude Code |
| ai-ethics-pmVandanaAjayDubey111/great-pm | Agent | 3 | 1mo ago | MIT | A | 54 | Claude Code |
| usability-auditorEvolvlabsai/Exolvra-Genesis | Agent | 1 | 1mo ago | MIT | A | 82 | Claude Code |
| designershahtuyakov/claude-setup | Agent | 13 | 10mo ago | MIT | A | 69 | Claude Code |
| ui-ux-designerbiggora/dev-team | Agent | 4 | 1mo ago | none | A | 250 | Claude Code |