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 humanity4ai/project_human --skill cognitive-accessibilitygit clone --depth 1 https://github.com/humanity4ai/project_humanWrote 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/humanity4ai/project_human/cognitive-accessibility)<a href="https://agentmods.dev/skills/humanity4ai/project_human/cognitive-accessibility"><img src="https://agentmods.dev/badge/skills/humanity4ai/project_human/cognitive-accessibility/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/humanity4ai/project_human/cognitive-accessibility"><img src="https://agentmods.dev/badge/skills/humanity4ai/project_human/cognitive-accessibility.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 | $0.00057 | $0.01284 |
| Opus 5.5 | $0.00023 | $0.00514 |
| Sonnet 5.5 | $0.00011 | $0.00257 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
cognitive-accessibility 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 1mo 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Accessibility
Purpose
Improves content and workflows for users with varied attention, memory, and executive function profiles. Applies cognitive load theory (Sweller, 1988), chunking strategies, and clear information architecture.
When to Use
- "Simplify this content"
- "Reduce cognitive load"
- "Make this more readable"
- "Chunk this information"
- "Help users with focus issues"
- "Improve accessibility for ADHD"
- "Simplify the user flow"
Boundaries
Always
- Use clear, simple language
- Chunk information into small pieces
- Provide clear signposting
- Include recovery options
Ask First
- Confirm before major restructuring
- Check cultural context
Never
- Never use jargon without explanation
- Never create complex multi-step flows without breaks
Principles
This skill is grounded in the Humanity4AI core principles and the following skill-specific principles:
- Cognitive load is a spectrum. Users have varying levels of working memory, attention, and executive function. Recommendations must be framed as considerations, not absolute requirements.
- Simplicity is not condescension. Clear, simple language and structured layouts respect all users. Avoid framing simplification as "dumbing down".
- Explicit uncertainty over false certainty. Acknowledge when a recommendation may not apply to all users or contexts.
- Inclusive design benefits everyone. Cognitive accessibility improvements (chunked content, clear headings, reduced distractions) improve usability for all users.
- Safety boundaries apply. Do not make medical or clinical claims about cognitive conditions such as ADHD or dyslexia.
Instructions
Step 1: Assess Load
Analyze content for:
- Sentence length and complexity
- Jargon and technical terms
- Multi-step processes
- Information density
Step 2: Identify Friction
Find:
- Ambiguous instructions
- Missing progress indicators
- No way to save progress
- Dense paragraphs
Step 3: Recommend Changes
What ships with it
11 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.
- references/checklist.md 524 B
- references/examples.md 471 B
- references/load-theory.md 486 B
- references/measurement.md 337 B
- references/patterns.md 755 B
- references/quick-reference.md 230 B
- references/simplification.md 380 B
- references/standards.md 764 B
- rubric.md 2.4 KB
- scenarios/scenarios.yaml 3.1 KB
- skill.yaml 794 B
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.
- 1mo ago First seen · 199 lines · 57 tokens per session scan A 3640f099865a
cognitive-accessibility is a skill published in the GitHub repository humanity4ai/project_human (5 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,284 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
ai-interface-reviewer
Audit AI-powered interfaces against the uxuiprinciples Part V taxonomy — 44 principles covering transparency, trust calibration, human override, consent, agentic workflows, and conversational design. Returns structured findings with severity and remediation. API key optional — enriched output requires…
accessible-forms
Labels, errors, grouping, and autofill for mobile forms. Use this when building any screen that collects user input — login, signup, checkout, profile editing.
input-validation-a11y
Announcing validation results, shaping error messages, and recovering focus. Use this when implementing client-side validation or async server-side errors in forms.
wcag-2-2-for-mobile
WCAG 2.2 success criteria translated to mobile platforms — gestures, inputs, orientation, focus, and target size. Use this when scoping accessibility acceptance criteria for a mobile feature.
switch-and-voice-control
Supporting iOS Switch Control + Voice Control, Android Switch Access + Voice Access, and AssistiveTouch. Use this when building any interactive UI, especially custom gestures, drag-and-drop, or non-standard controls.
reduce-motion
Detecting and honoring the user's reduce motion preference on iOS, Android, Flutter, and React Native. Use this when building transitions, parallax, hero animations, or autoplay.