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.
npx skills add bpodhalicz/designer-claude-skills --skill ux-psychology-reviewgit clone --depth 1 https://github.com/bpodhalicz/designer-claude-skillsWrote 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/skills/bpodhalicz/designer-claude-skills/ux-psychology-review)<a href="https://agentmods.dev/skills/bpodhalicz/designer-claude-skills/ux-psychology-review"><img src="https://agentmods.dev/badge/skills/bpodhalicz/designer-claude-skills/ux-psychology-review/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/skills/bpodhalicz/designer-claude-skills/ux-psychology-review"><img src="https://agentmods.dev/badge/skills/bpodhalicz/designer-claude-skills/ux-psychology-review.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 | $0.00173 | $0.04485 |
| Opus 5 | $0.00086 | $0.02243 |
| Sonnet 5 | $0.00035 | $0.00897 |
| Haiku 4.5 | $0.00017 | $0.00449 |
Grade A, and why
ux-psychology-review 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 12d 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Psychology Review
A working knowledge base of 106 cognitive biases and design principles for reviewing UI/UX work and generating recommendations grounded in named psychology. Adapted from growth.design's "Psychology of Design" framework, which builds on Buster Benson's cognitive bias codex.
What this skill does
Two jobs, often blended:
- Review — Given a design (screenshot, description, flow, or live URL), diagnose which principles it leverages well, which it violates, and which dark patterns it risks.
- Generate — Given a UX problem ("how do we improve activation", "what should the pricing page do"), propose concrete, principle-backed ideas.
Both modes name principles explicitly. A recommendation like "add social proof near the CTA — this leverages the Bandwagon Effect and reduces decision anxiety" is more useful than an unattributed gut call, because the user can challenge it, extend it, or check it against literature.
The framework: 4 stages of user cognition
Buster Benson's codex sorts cognitive biases by the problem the brain is trying to solve. Every time someone interacts with your product, they:
- Filter information — too much input, the brain ignores most of it. (Visual hierarchy, Hick's Law, Cognitive Load, Selective Attention, Banner Blindness…)
- Search for meaning — gaps in the input get filled with assumptions and stories. (Mental Models, Familiarity Bias, Halo Effect, Authority Bias, Confirmation Bias…)
- Act within time pressure — decisions get rushed; shortcuts win. (Loss Aversion, Sunk Cost, Default Effect, Scarcity, Reciprocity…)
- Store what mattered — memory is selective and reconstructive. (Peak-End Rule, Serial Position Effect, Zeigarnik Effect, Spacing Effect…)
Good design respects all four. Bad design fights one or more.
How to work through a request
When reviewing a design
- Get the artifact in front of you. If the user shared a URL, fetch it. If a screenshot, look carefully. If only a description, ask one or two specific questions before guessing — designs are visual, and a vague description leads to vague feedback.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 267 lines · 173 tokens per session scan A 3e4ffa0e7e96
ux-psychology-review is a skill published in the GitHub repository bpodhalicz/designer-claude-skills (8 stars, last pushed 2mo ago), licensed MIT. It adds 173 tokens to every session and 4,485 once invoked, about $0.0009 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 skills, from other repositories
ui-designer
A UI and UX design skill for planning websites, landing pages, product pages and web applications. It can also provide colour, typography and visual-style guidance.
righter
Apply UX content writing principles to review existing UI copy or write new UI copy from scratch. Use this skill whenever someone asks you to: review, audit, critique, or improve UI text, error messages, button labels, tooltips, empty states, onboarding copy, form helper text, or any software interface copy. Also…
vois-tokens
Rules and patterns for building UI with shadcn/ui, Tailwind v4 or StyleX, and Motion against a Vois design token set. Use when building components, pages, or any UI that should conform to the workspace design system. Covers spacing, typography, color tokens, component architecture, animation, accessibility, and modern…
design-rationale
Help designers articulate the cognitive science, behavioral psychology, and platform standards behind their design decisions. Use this skill when a designer needs to explain why they made a decision in a critique, design review, or stakeholder meeting. Also use when auditing a screen for principle alignment, preparing…
vois-patterns
Structural decision trees for container types, form states, table layouts, and page-level patterns. Use before vois-tokens. Routes to righter skill for all microcopy (labels, errors, buttons, helpers). Use when building pages, forms, features, workflows.
refine-live
In-chat fallback for the Timeline Inspector Refine agent. Use when the user runs /refine live, asks to "refine live", "go live", or answer refine jobs — but ONLY when no persistent agent is wired (no npx transitions-refine live). Prefer npx transitions-refine live for run-and-forget (relay spawns agent per click, no…