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 parhamb/design-skills --skill ux-formsgit clone --depth 1 https://github.com/parhamb/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/parhamb/design-skills/ux-forms)<a href="https://agentmods.dev/skills/parhamb/design-skills/ux-forms"><img src="https://agentmods.dev/badge/skills/parhamb/design-skills/ux-forms/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/parhamb/design-skills/ux-forms"><img src="https://agentmods.dev/badge/skills/parhamb/design-skills/ux-forms.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 | $0.00051 | $0.00794 |
| Opus 5.5 | $0.00020 | $0.00318 |
| Sonnet 5.5 | $0.00010 | $0.00159 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
ux-forms 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 2mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forms UX
Forms are where intent turns into action. Every extra field, every ambiguous label, and every delayed error message costs conversions and frustrates users.
Checklist
| Item | Guidance |
|---|---|
| Minimal data collection | Only ask for what is needed right now. Defer optional fields to the profile. |
| Show / hide password | Eye icon on the right side of the password field. Hidden by default. |
| Multiple input methods | Offer voice or camera scan for fields where it genuinely helps (notes, documents). |
| Input suggestions | Autocomplete from history or a curated list to speed up data entry. |
| No repeated input | Pre-fill known data from the existing account. Never ask twice (WCAG 2.2 requires this — 3.3.7 Redundant Entry). |
| Password strength indicator | 4-level strength meter shown as the user types. Requirements listed inline. |
| Auto-format input | Format phone numbers, card numbers, and dates automatically as the user types. |
| Inline validation | Validate on blur (when the user leaves the field), not on final submit. |
| Correct keyboard type | Email field opens email keyboard. Number field opens number pad. URL field opens URL keyboard. |
| Enter key label | Return key shows "Next" to advance focus, or "Done" / "Search" when it submits. |
| Autofill support | Uses platform content type hints so password managers and autofill work correctly. |
| Form progress indicator | Multi-step forms show a step indicator ("Step 2 of 4") and allow going back. |
Keyboard Type Reference
| Input | iOS contentType | Android inputType |
|---|---|---|
| emailAddress | textEmailAddress | |
| Phone | telephoneNumber | phone |
| One-time code | oneTimeCode | — |
| Full name | name | textPersonName |
| Password | password | textPassword |
| New password | newPassword | — |
Patterns
Progressive disclosure: Split long forms into logical steps. No more than 5 to 6 fields per screen. Users abandon forms that look long before they start.
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.
- 2mo ago First seen · 82 lines · 51 tokens per session scan A a77152b9af1f
ux-forms is a skill published in the GitHub repository parhamb/design-skills (25 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 794 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 2026-08-30.
ux-forms compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux-formsparhamb/design-skills | Skill | 25 | 4mo ago | MIT | A | 51 | Claude Code, Codex |
| anti-slop-designsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 34 | Claude Code |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 4d ago | MIT | A | 52 | Codex |
| open-design-setupcompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 67 | Claude Code, Codex |
| frontend-visual-qadaymade/claude-code-skills | Skill | 1.5k | yesterday | MIT | A | 125 | Claude Code, Codex |
| prototype-webnexu-io/html-anything | Skill | 9.4k | 25d ago | Apache-2.0 | A | 24 | Claude Code, Codex |