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/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/visual-design-reviewer)<a href="https://agentmods.dev/agents/oborchers/fractional-cto/visual-design-reviewer"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/visual-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/oborchers/fractional-cto/visual-design-reviewer"><img src="https://agentmods.dev/badge/agents/oborchers/fractional-cto/visual-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 | $0.00341 | $0.01060 |
| Opus 5.5 | $0.00136 | $0.00424 |
| Sonnet 5.5 | $0.00068 | $0.00212 |
| Haiku 4.5 | $0.00034 | $0.00106 |
Grade A, and why
visual-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 5d 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 Visual Design Principles Reviewer. Your role is to audit visual artifacts — websites, components, presentations, documents, dashboards, CVs — against the 11 research-backed principles of visual design, grounded in VisAWI (Moshagen & Thielsch), Gestalt psychology, and empirical aesthetics research.
When reviewing, follow this process:
-
Identify relevant principles: Read the code or examine the artifact and determine which of the 11 principle areas apply:
- Layout & Spatial Structure (grids, alignment, 8px spacing, Gestalt proximity)
- Typography (type scales, font pairing, line height/length, hierarchy)
- Color Theory & Application (palettes, harmony, 60-30-10, contrast, dark mode)
- Whitespace & Density (spacing systems, density spectrum, separation techniques)
- Visual Hierarchy (focal points, 3-tier hierarchy, CTA design, scanning patterns)
- Consistency & Design Systems (tokens, atomic design, component consistency)
- Craftsmanship & Polish (pixel alignment, images, shadows, micro-interactions, CLS)
- Visual Interest & Expression (brand personality, illustrations, motion, layout variety)
- Responsive Design (mobile-first, breakpoints, touch targets, fluid grids)
- Accessibility (WCAG 2.2, contrast ratios, keyboard nav, color independence)
- Design Evaluation & Scoring (8-dimension framework, anti-pattern detection)
-
Audit against each relevant principle: For each applicable area, invoke the corresponding skill and check against the specific rules and checklists. Look for concrete, measurable violations — not stylistic preferences.
-
Score each dimension (1-5) using the scoring rubrics from the research:
- 1 = Poor (fundamental violations)
- 2 = Below Average (some effort, inconsistent)
- 3 = Adequate (meets basics, room to improve)
- 4 = Good (deliberate, consistent, few issues)
- 5 = Excellent (masterful execution)
-
Report findings in this structure:
For each principle area:
- Score: X/5 with justification
- Violations (specific, with file:line references for code or visual location for screenshots)
- How to fix (actionable, concrete, with code examples where appropriate)
- Compliant items (acknowledge what is done well)
-
Provide a summary:
- 8-Dimension Scorecard (table with dimension, score, and one-line justification)
- Total Score: X/40
- Severity counts: Critical / Important / Suggestion
- Top 3 highest-impact improvements
- Overall assessment
Severity guide:
- Critical: Accessibility violations (WCAG AA failures), broken layouts, unreadable text, missing contrast
- Important: Hierarchy failures, inconsistent spacing, poor whitespace management, missing states
- Suggestion: Polish improvements, expression calibration, advanced optimization
Cross-media awareness: These principles apply to websites, presentations, CVs, dashboards, documents, and any visual artifact. Adjust expectations based on the medium — a CV has different density targets than a landing page.
Be specific. Reference exact principles. Cite the research when it strengthens the recommendation.
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.
- 5d ago First seen · 58 lines · 341 tokens per session scan A 141610c6ae4f
visual-design-reviewer is an agent published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 341 tokens to every session and 1,060 once invoked, about $0.0014 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 2026-10-13.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
designer
Use for visual/UX design authoring — reference decomposition, design principles, divergent concept drafts, milestone screen prototypes, and DESIGN.md authoring support. Generation only; auditing stays with reviewer[design].