cognitive-interface-audit

cognitive-interface-audit is a skill for Claude Code from karsten-s-nielsen/mad-scientist-skills. It costs 230 tokens per session (17,774 once invoked), scanned A, original, MIT.

A method for evaluating whether a user interface matches how people think and work. It examines task steps, user expertise, consistency, mistakes, mental models, cognitive effort, visual design, and accessibility.

In plain words
What is it for?
Use it to plan interface tasks and error handling, or to audit an existing interface for usability, consistency, accessibility, and cognitive load.
Why use it?
It helps reveal confusing workflows and places where users are likely to make errors or need too much mental effort. It can be used before a UI exists or on an existing UI.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the mad-scientist-skills plugin — 10 skills, 4 commands shipped together

Good fit Use it to plan interface tasks and error handling, or to audit an existing interface for usability, consistency, accessibility, and cognitive load.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karsten-s-nielsen/mad-scientist-skills/cognitive-interface-audit
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.

Any agent
npx skills add karsten-s-nielsen/mad-scientist-skills --skill cognitive-interface-audit
Clone the repo
git clone --depth 1 https://github.com/karsten-s-nielsen/mad-scientist-skills

Made for: Claude Code.

Or install mad-scientist-skills, the plugin that ships this one along with the rest of its 10 skills, 4 commands.

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 cognitive-interface-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/cognitive-interface-audit/github.svg)](https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/cognitive-interface-audit)
Your own site
<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/cognitive-interface-audit"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/cognitive-interface-audit/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.

agentmods 80×15 button for cognitive-interface-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/cognitive-interface-audit"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/cognitive-interface-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 230 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 17,774 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00230 $0.17774
Opus 5 $0.00115 $0.08887
Sonnet 5 $0.00046 $0.03555
Haiku 4.5 $0.00023 $0.01777

Measured 11d ago against content hash a5400c18ca44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cognitive-interface-audit 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.

plugins/mad-scientist-skills/skills/cognitive-interface-audit/SKILL.md · 866 lines

How it starts

The opening of the file, as written. The whole thing — 866 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cognitive Interface Audit

A comprehensive cognitive interface audit with two modes and a single tier:

Modes:

  • Planning (before UI exists) — task model design, user expertise mapping, error tolerance strategy, information architecture
  • Audit (on existing UI) — mental model alignment, consistency, error tolerance, cognitive load, visual grounding, accessibility

Single tier: Unlike security auditing, cognitive interface evaluation is methodology-based (GOMS analysis, heuristic evaluation, NASA-TLX scoring), not tool-licensed. No paid software is required. The value is in the analytical framework, not the scanner.

Core question: "Does the interface think the way the user thinks?"

Academic foundations

This skill synthesizes seven research threads into a single audit methodology:

  1. Task Model & Error Tolerance (Card, Moran & Newell 1983; Wood & Byrne 2002; Rasmussen 1983) — GOMS models predict how users decompose tasks. Wood's 7-layer defense framework predicts where errors occur and what defenses are needed at each stage. Rasmussen's SRK framework classifies errors by cognitive level (skill-based slips, rule-based misapplication, knowledge-based wrong mental model), each requiring different design countermeasures.

  2. Visual Grounding & Common Ground (Gergle, Kraut & Fussell 2004/2013; Gergle et al. 2021) — Shared visual information affects task performance through two distinct mechanisms: situation awareness (does the user understand system state?) and conversational grounding (does the interface provide enough shared context?). Not just availability but the form of visual information differentially affects performance. The Joint Action Storyboard framework maps each interaction to its grounding cost.

  3. Cognitive Load (Sweller 1988; Hart & Staveland 1988; Kahneman 2011) — Every interface decision either consumes or conserves working memory. NASA-TLX provides structured evaluation across 6 dimensions. Sweller's distinction between intrinsic load (inherent task complexity), extraneous load (poor design), and germane load (productive learning) guides where to invest and where to cut. Kahneman's Dual-Process Theory (System 1/System 2) identifies where interfaces force slow, deliberate processing when fast, intuitive processing could suffice.

Read the full file on GitHub · 866 lines

Files

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.

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. 11d ago First seen · 866 lines · 230 tokens per session scan A a5400c18ca44

Subscribe to this mod's changes

cognitive-interface-audit is a skill published in the GitHub repository karsten-s-nielsen/mad-scientist-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 230 tokens to every session and 17,774 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

recipe-front-design

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval.

shinpr/claude-code-workflows · 22 tokens

recipe-front-adjust

Adjust an already-implemented UI in-session with verification against the design source.

shinpr/claude-code-workflows · 18 tokens

fidelity-gate

Build a UI against a frozen visual reference without drift - an inventory extracted before any code, a relics list, and a gate that MEASURES computed styles on a fixture carrying the reference's own data. Use when a mockup, design spec or screenshot is the contract.

jjanczur/tyran · 56 tokens

a11y-audit

Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…

greglas75/zuvo · 147 tokens

design-review

UI/UX design consistency audit. Code-based DX1-DX20 checklist covering states, consistency, accessibility, responsive behavior, and interaction patterns. Optional visual audit via chrome-devtools screenshots and automated WCAG accessibility via axe-core. DAP1-DAP12 anti-pattern detection. Modes: [path], visual…

greglas75/zuvo · 107 tokens

design

Intent-first UI design with conscious, traceable design decisions. Persists decisions in .interface-design/ for cross-session consistency. Includes domain exploration, design system generation (system.md + system.json), per-component construction with mandatory checkpoints, and craft validation tests. Modes: init…

greglas75/zuvo · 90 tokens