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 Dragoon0x/everything-design-taste --skill error-handlinggit clone --depth 1 https://github.com/Dragoon0x/everything-design-tasteWrote 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/dragoon0x/everything-design-taste/error-handling)<a href="https://agentmods.dev/skills/dragoon0x/everything-design-taste/error-handling"><img src="https://agentmods.dev/badge/skills/dragoon0x/everything-design-taste/error-handling/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/dragoon0x/everything-design-taste/error-handling"><img src="https://agentmods.dev/badge/skills/dragoon0x/everything-design-taste/error-handling.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 | $0.00020 | $0.00384 |
| Opus 5.5 | $0.00008 | $0.00154 |
| Sonnet 5.5 | $0.00004 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
error-handling 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.
What it actually says
Error Handling
Error Message Formula
What happened + Why (if useful) + What to do now
Bad
"Error 500: Internal server error"
Good
"We couldn't save your changes. Our servers are having trouble. Try again in a few minutes, or your changes will be saved automatically when we're back."
Error Types & Treatment
| Error | Show Where | Persist | User Action |
|---|---|---|---|
| Field validation | Inline next to field | Until fixed | Fix input |
| Form submission | Top of form + inline | Until fixed | Fix and resubmit |
| Network error | Banner or toast | Until resolved | Retry or wait |
| Auth error | Full page or modal | Until resolved | Log in again |
| Not found | Full page | N/A | Go back or search |
| Server error | Full page or banner | Until resolved | Retry later |
Prevention Over Recovery
- Inline validation catches errors before submission
- Confirmation dialogs prevent accidental destructive actions
- Autosave prevents data loss
- Undo is better than "Are you sure?"
- Smart defaults reduce wrong inputs
- Input masks format data as users type
Rules
- Never use technical jargon (error codes, stack traces)
- Never blame the user ("You entered an invalid...")
- Always provide a path forward
- Preserve user input on error (never clear the form)
- Use appropriate severity (red for errors, yellow for warnings, blue for info)
- Log errors for debugging even if users don't see details
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 · 44 lines · 20 tokens per session scan A c136c7de09d9
error-handling is a skill published in the GitHub repository Dragoon0x/everything-design-taste (13 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 384 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
antislop
Anti Slop: Rules for AI Coding Agents. The core filter. Load always to stop generic AI slop.
antislop-human
Human and accessibility skill for antislop. Contrast, keyboard, focus, and states for real people. Includes the contrast checker.
antislop-ui
UI and visual skill for antislop. Use when building or editing any interface: color, layout, components, motion. Load with the core.
role-ui-ux-designer
Use when orchestrating UI/UX design systems, anti-AI-slop frontend styling, tactile micro-interactions, responsive design tokens, accessibility standards, and high-fidelity interface engineering.
taste
Anti-slop frontend engineering directive and design taste system. Enforces brief inference, dynamic design dials, absolute prohibition of AI visual tells, and 100% full-output completion.
design-critic
Autonomous UI/UX review — screenshots every page at mobile/tablet/desktop (full-page scrolling), analyzes with vision models for layout bugs, checks accessibility (axe-core), audits contrast/colors/fonts/spacing for design system inconsistencies, detects dead buttons/links, overlapping elements hiding text/buttons…