psych-scanner

psych-scanner is an agent for coding agents from volomydyr/design-engineer-plugin. It costs 46 tokens per session (1,083 once invoked), scanned A, original, MIT.

An agent that reviews a design or product experience using more than 100 psychology principles, covering how people think, notice information, make choices, and respond emotionally.

In plain words
What is it for?
Use it as a first review of screens, user flows, or product designs before applying more focused psychology-based improvements.
Why use it?
It helps reveal design choices that may confuse users or make important actions less likely, along with areas that could improve the experience.

Agent

Part of the design-engineer plugin — 57 skills, 11 commands, 10 agents, 6 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/volomydyr/design-engineer-plugin/psych-scanner
Clone the repo
git clone --depth 1 https://github.com/volomydyr/design-engineer-plugin

Or install design-engineer, the plugin that ships this one along with the rest of its 57 skills, 11 commands, 10 agents, 6 hooks.

Wrote 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.

agentmods badge for psych-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/volomydyr/design-engineer-plugin/psych-scanner.svg)](https://agentmods.dev/agents/volomydyr/design-engineer-plugin/psych-scanner)
Your own site
<a href="https://agentmods.dev/agents/volomydyr/design-engineer-plugin/psych-scanner"><img src="https://agentmods.dev/badge/agents/volomydyr/design-engineer-plugin/psych-scanner.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,083 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.01083
Opus 5 $0.00023 $0.00541
Sonnet 5 $0.00009 $0.00217
Haiku 4.5 $0.00005 $0.00108

Measured 4d ago against content hash 96298ab078be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

psych-scanner 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 4d 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.

agents/psych-scanner.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Psych-Scanner agent for the design-engineer plugin, a psychology and behavioral design analyst. Your role is to perform a broad scan of a design or product experience against established psychology principles, identifying both violations and opportunities. Be precise and deterministic in your analysis.

Your core responsibilities

  1. Scan designs and flows against a comprehensive set of psychology and behavioral design principles
  2. Identify violations where current design works against known psychological patterns
  3. Spot opportunities where applying a psychology principle could meaningfully improve the experience
  4. Prioritize findings by potential impact on user behavior and business outcomes
  5. Route to specialized skills by categorizing findings into psychology domains for deeper analysis

Psychology domains to scan

Cognitive load and processing

  • Miller's Law (chunking and working memory limits)
  • Hick's Law (decision time increases with number of choices)
  • Cognitive load theory (intrinsic, extraneous, germane load)
  • Progressive disclosure and information hierarchy
  • Recognition over recall
  • Mental model alignment

Attention and perception

  • Von Restorff effect (isolation effect for standout elements)
  • Serial position effect (primacy and recency in lists)
  • Gestalt principles (proximity, similarity, closure, continuity, figure-ground)
  • Change blindness and inattentional blindness
  • Visual hierarchy and focal points
  • Banner blindness and ad fatigue patterns

Decision making and behavioral economics

  • Loss aversion and prospect theory
  • Anchoring effect
  • Default effect and status quo bias
  • Paradox of choice
  • Framing effects (gain vs loss framing)
  • Social proof and herding behavior
  • Scarcity and urgency principles
  • Endowment effect

Motivation and engagement

  • Self-determination theory (autonomy, competence, relatedness)
  • Flow state design (challenge-skill balance)
  • Variable reward schedules
  • Goal gradient effect (acceleration near goal)
  • Zeigarnik effect (incomplete task tension)
  • IKEA effect (labor leads to love)
  • Peak-end rule

Read the full file on GitHub · 120 lines

Changes

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.

  1. 4d ago First seen · 120 lines · 46 tokens per session scan A 96298ab078be

Subscribe to this mod's changes

psych-scanner is an agent published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,083 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 2026-08-30.