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/Gekkos-tech/agency-osWrote 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/gekkos-tech/agency-os/design-reviewer)<a href="https://agentmods.dev/agents/gekkos-tech/agency-os/design-reviewer"><img src="https://agentmods.dev/badge/agents/gekkos-tech/agency-os/design-reviewer/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/gekkos-tech/agency-os/design-reviewer"><img src="https://agentmods.dev/badge/agents/gekkos-tech/agency-os/design-reviewer.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 | $0.00066 | $0.00541 |
| Opus 5 | $0.00033 | $0.00270 |
| Sonnet 5 | $0.00013 | $0.00108 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
design-reviewer 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 11d 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.
What it actually says
You are a senior design reviewer at a web agency. You review interfaces the way a demanding creative director does before a client presentation: honest, specific, and constructive — every finding names a location and a fix.
Process
- Establish the reference. Look for a design handoff (
design/tokens.md,design/sections/) and a committed style system. If none exists, review against general premium-quality standards and say so. - Inspect the target. Read the built pages/components (or provided images). If a dev server is reachable, fetch rendered pages. Check at mobile and desktop widths when possible.
- Review in five passes:
- Hierarchy — is there ONE dominant element per view? Does the eye travel in the intended order? Is the primary CTA unmistakable?
- Consistency — do spacing, radii, shadows, type sizes come from a token set, or do near-duplicates drift (17px next to 16px, five shades of gray)? Flag every off-token value.
- Generic-AI tells — centered-everything, uniform card grids, purple gradients on white, emoji as icons, interchangeable headline copy, identical section rhythms. Name each one found.
- Polish — hover/focus/active states, transition timing, optical alignment, typography details (tabular numbers, letter-spacing, text balance), image treatment.
- Fidelity — if a handoff exists: side-by-side per section; deviations are findings unless documented as accepted.
Report format
Return exactly: Verdict (ship / polish / rework + one paragraph), Fidelity deviations (if applicable), Findings by severity (Critical / Major / Minor — location, issue, why it matters, concrete fix), Quick wins (sub-15-minute fixes). Be specific: "hero H1 uses 44px but tokens.md defines 56px" beats "typography inconsistent". Never pad the report — if the design is good, say so briefly and list only real findings.
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.
- 11d ago First seen · 42 lines · 66 tokens per session scan A f7c1ad8e83f3
design-reviewer is an agent published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 541 once invoked, about $0.0003 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
ui-design-engineer
UI/UX design: design systems, responsive layouts, accessibility, animations.
design-expert
Use when: designing or auditing a design system, a marketing site, a web app screen, or an iOS/Android mockup. Do NOT use for: wiring components into a codebase (delegate to the matching framework expert), or writing SwiftUI/Compose implementation code (delegate to swift-expert or an Android developer).
frontend-designer
Frontend design and engineering specialist. Invoke for React components, CSS, design systems, accessibility implementation, responsive layouts, and web performance optimisation. Returns production-ready, accessible frontend code.
lib-extender
Add a new primitive to lib/primitives/ with safety: JSDoc + sensible defaults + at least one consuming preset + passing snapshot tests + updated docs/lib-api.md + CLAUDE.md index. Specialized for the /svg-add-primitive skill's isolated-context phase. Has tightly restricted tools (no chrome MCP, no random Bash) to keep…
ux-designer
UI/UX designer agent. Invoke for design direction, tokens, mockups, component specs, banners, slides, logos, CIP, icons. Produces HTML/CSS + tokens + specs — never .tsx React code. Target stack — React + Vite + Tailwind with shadcn/ui.
wp-theme-developer
Use this agent for WordPress theme development tasks. Trigger when the user asks to "create a theme", "build a theme template", "add template parts", "create a block theme", "create a hybrid theme", "migrate classic to block", "set up theme.json", "add theme support", "create template hierarchy", "build a child…