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 error-prevention-recoverygit 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/error-prevention-recovery)<a href="https://agentmods.dev/skills/owl-listener/inclusive-design-skills/error-prevention-recovery"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/error-prevention-recovery/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/error-prevention-recovery"><img src="https://agentmods.dev/badge/skills/owl-listener/inclusive-design-skills/error-prevention-recovery.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 | $0.00075 | $0.00663 |
| Opus 5 | $0.00037 | $0.00331 |
| Sonnet 5 | $0.00015 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
error-prevention-recovery 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 13d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Prevention and Recovery
Design systems that prevent errors before they happen, and when errors do occur, help people recover without shame, confusion, or lost work.
Prevention Strategies
Forgiving Input
- Accept multiple date formats ("15/03/2026", "15 March 2026", "March 15, 2026")
- Accept multiple phone formats ("(555) 123-4567", "555-123-4567", "5551234567")
- Auto-format as the user types
- Case-insensitive matching
- Trim whitespace automatically
- Show format examples next to fields ("e.g., 15/03/2026")
Smart Defaults
- Pre-select the most common option
- Pre-fill known information (name from account, address from postcode)
- Show the recommended choice for complex decisions
- Default to the safest option for irreversible settings
Progressive Validation
- Validate each field when the user moves to the next (on blur)
- Show success states for correctly completed fields
- Never validate while the user is still typing
- Never clear user input on error — always preserve their work
Minimal Demands
- Only ask for information you strictly need
- Mark optional fields, not required ones (most fields should be required by design — if they aren't needed, remove them)
- Break long forms into steps with clear progress
Error Message Design
Every error message must answer three questions:
- What happened? (specific, not generic)
- Why? (in plain language)
- What do I do now? (a clear, single action)
Examples
Bad: "Invalid input" Good: "Please enter a date in the format DD/MM/YYYY — for example, 15/03/2026"
Bad: "Error 403" Good: "You don't have permission to view this page. Contact your team admin to request access."
Bad: "Password does not meet requirements" Good: "Your password needs at least 8 characters and one number. You have 6 characters."
Error Message Tone
- Never blame the user ("You entered an invalid email")
- State the situation neutrally ("We need a valid email to continue")
- Be specific about what needs to change
- Offer an alternative path when possible
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.
- 13d ago First seen · 72 lines · 75 tokens per session scan A 34f51f51b2ba
error-prevention-recovery is a skill published in the GitHub repository Owl-Listener/inclusive-design-skills (98 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 663 once invoked, about $0.0004 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.
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.