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 Owl-Listener/inclusive-design-skills --skill contextual-help-designgit clone --depth 1 https://github.com/Owl-Listener/inclusive-design-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/owl-listener/inclusive-design-skills/contextual-help-design)<a href="https://agentmods.dev/skills/owl-listener/inclusive-design-skills/contextual-help-design"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/contextual-help-design/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/owl-listener/inclusive-design-skills/contextual-help-design"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/contextual-help-design.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 | $0.00071 | $0.00514 |
| Opus 5 | $0.00036 | $0.00257 |
| Sonnet 5 | $0.00014 | $0.00103 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
contextual-help-design 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.
This is a copy
100% identical to contextual-help-design — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contextual Help Design
Design help that meets people where they are — on the screen they're stuck on, in language they understand, without requiring them to remember how they got there.
Core Principle
If a user gets stuck, they should be able to get help without leaving the screen they're on.
Design Patterns
Inline Help
- Tooltip or info icon next to fields that need explanation
- Examples shown next to input fields ("e.g., 15/03/2026")
- Help text visible by default for complex fields
- Inline definitions for specialist terms (underline + tooltip)
- "What's this?" links for uncommon concepts
Guided Tasks
- Step-by-step wizard as an alternative to complex forms
- Examples of completed tasks (filled-in sample forms)
- Templates or pre-built options alongside "start from scratch"
- Progress-aware hints that change based on where the user is
Escalation Path
- Self-service help (search, FAQ) as first option
- Chat or messaging as second option
- Phone or video as third option
- Never require users to re-explain when escalating between channels
- Show estimated wait times for human support
- Never require a reference number to get help
Error Recovery Support
- Error messages include: what happened + why + what to do next
- Link directly to the field or step that needs fixing
- Offer alternative paths when primary fails
- For complex errors: offer human support directly
Help Content Rules
- Write at grade 4–6 reading level
- Use the same terminology as the interface (not different words)
- One instruction per step
- Include images or diagrams for spatial or procedural instructions
- Make help searchable
- Test help content with people who have the actual problem
Assessment Questions
- Can users get help without navigating away from their task?
- Is help written in plain language that matches the interface?
- Can users reach a human within 2 clicks when self-service fails?
- Do help resources exist for the moments where users actually get stuck (not just the moments you anticipated)?
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 · 62 lines · 71 tokens per session scan A ca49b0b26c01
contextual-help-design is a skill published in the GitHub repository Owl-Listener/inclusive-design-skills (98 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 514 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to contextual-help-design, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.