Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/cognitive-load-analyzerWrote 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/pramoddutta/qaskills/cognitive-load-analyzer)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/cognitive-load-analyzer"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/cognitive-load-analyzer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.09016 |
| Opus 5 | $0.00015 | $0.04508 |
| Sonnet 5 | $0.00006 | $0.01803 |
| Haiku 4.5 | $0.00003 | $0.00902 |
Grade A, and why
Cognitive Load Analyzer 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.
How it starts
The opening of the file, as written. The whole thing — 1,029 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Load Analyzer Skill
You are an expert QA engineer specializing in cognitive load assessment, usability heuristic evaluation, and information architecture analysis. When asked to evaluate interface complexity, measure decision overload, audit visual hierarchy, or analyze task completion paths in a web application, follow these comprehensive instructions to systematically identify and quantify sources of unnecessary cognitive burden.
Core Principles
-
Cognitive Load Is Measurable -- While cognitive load is a psychological phenomenon, its proxies are measurable: number of choices per screen, information density per viewport, navigation depth to complete tasks, consistency of patterns, and visual hierarchy clarity. By quantifying these proxies, you can objectively compare designs and detect regressions.
-
Three Types of Cognitive Load -- Intrinsic load comes from the inherent complexity of the task itself. Extraneous load comes from poor interface design that adds unnecessary complexity. Germane load is the productive mental effort of learning and understanding. The goal is to minimize extraneous load while preserving intrinsic and germane load.
-
Miller's Law Applies to Interfaces -- The human working memory can hold roughly 7 plus or minus 2 items simultaneously. Navigation menus with 15 items, forms with 20 fields, and dashboards with 12 data widgets all exceed cognitive capacity. Chunk information into groups of 5-7 items maximum.
-
Hick's Law Governs Decision Time -- The time to make a decision increases logarithmically with the number of choices. A page with 3 clear options is cognitively easy. A page with 30 options of similar visual weight creates decision paralysis. Reduce choices or create clear visual hierarchy to guide attention.
-
Consistency Reduces Load -- When interface patterns are consistent, users build mental models that reduce the cognitive effort of future interactions. When the same action requires different steps on different pages, users must relearn the interface each time.
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.
- 4d ago First seen · 1,029 lines · 29 tokens per session scan A 562e68ca6a95
Cognitive Load Analyzer is a skill published in the GitHub repository PramodDutta/qaskills (218 stars, last pushed 8d ago), licensed MIT. It adds 29 tokens to every session and 9,016 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
carrier-product-review
A product-review guide for telecommunications products such as mobile apps, service plans, billing systems, and customer or business platforms.
Form UX Optimizer
Reviews web forms for usability issues — field ordering, validation messages, error states, and accessibility.
FAQ Generator
Generates a comprehensive FAQ section for any product, API, or documentation page.
design-usabilidade
Use when analyzing user journeys, auditing UX quality, prototyping flows, or designing new pages/features from a product perspective. Triggers on: jornada do usuario, fluxo de agendamento, prototipo, prototipar, experiencia do usuario, UX audit, usabilidade, melhorar conversao, nova pagina, nova feature, redesign…
ux-researcher
!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/design-mindset-and-rules.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults".
interface-auditor
Detect UX antipatterns (smells) in interface descriptions using the uxuiprinciples smell taxonomy. Returns structured findings with matched symptoms, severity, and step-by-step remediation recipes. API key optional — full remediation recipes require uxuiprinciples.com API Access.