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 dembrandt/dembrandt-skills --skill form-designgit clone --depth 1 https://github.com/dembrandt/dembrandt-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/dembrandt/dembrandt-skills/form-design)<a href="https://agentmods.dev/skills/dembrandt/dembrandt-skills/form-design"><img src="https://agentmods.dev/badge/skills/dembrandt/dembrandt-skills/form-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/dembrandt/dembrandt-skills/form-design"><img src="https://agentmods.dev/badge/skills/dembrandt/dembrandt-skills/form-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 161 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00028 | $0.01921 |
| Opus 5.5 | $0.00011 | $0.00768 |
| Sonnet 5.5 | $0.00006 | $0.00384 |
| Haiku 4.5 | $0.00003 | $0.00192 |
Grade A, and why
form-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 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Form Design
Forms are where users give the product data. Every unnecessary obstacle between the user and a completed form is a failure. The design goal is to make correct input easy and incorrect input obvious — before the user submits.
The Three Guidance Layers
Each layer serves a distinct purpose. Do not collapse them.
Layer 1 — Helper Text
Explains what to enter. Appears below the input, always visible, in small secondary text.
Email address
[ ]
Use the email you signed up with.
- Write in plain language from the user's perspective
- Keep it to one sentence — if you need more, the field is too complex or misnamed
- Do not repeat the label ("Enter your email" below a label that says "Email" is redundant)
- Helper text is not a replacement for a label — the label is still required
Layer 2 — Placeholder
Shows the format or an example value. Appears inside the input, disappears on typing.
[[email protected] ]
- Use a realistic example, not a description:
+358 40 123 4567notEnter phone number - Never use placeholder as a label — it disappears and leaves the user without context
- Keep it grey (
--color-text-secondary) and lighter than actual input text - Optional — not every field needs a placeholder
Layer 3 — Validation
Confirms whether the input is correct. The most important layer.
Email address
[jane@ ] ← invalid
✗ Enter a valid email address.
Validation timing:
- On blur (leaving the field): default for most fields — validates once the user has finished
- Real-time (on input): use when the format is complex or the error is likely — password strength, IBAN, VAT number, URL, regex-heavy fields
- On submit: catches anything missed, scrolls to the first error
Real-time validation must be forgiving at the start — do not show an error the instant the user starts typing. Show it after a short debounce (300–500ms) or after the first character that makes the input definitively wrong.
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 Changed · -35 tokens per session 6e3d60dc8006
- 1mo ago Changed · +10 lines 72396ad38f87
- 2mo ago First seen · 239 lines · 63 tokens per session scan A 10e8aacefe10
form-design is a skill published in the GitHub repository dembrandt/dembrandt-skills (183 stars, last pushed 6d ago), licensed MIT. It adds 28 tokens to every session and 1,921 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 2026-08-30.
form-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| form-designdembrandt/dembrandt-skills | Skill | 183 | 6d ago | MIT | A | 28 | Claude Code |
| design-dnazanwei/design-dna | Skill | 2.1k | 2mo ago | MIT | A | 192 | Claude Code, Codex |
| dbim-brand-identityYashraj00700/indian-gov-ui-skills | Skill | 2 | 3mo ago | MIT | A | 117 | Claude Code, Codex |
| indian-gov-web-uiYashraj00700/indian-gov-ui-skills | Skill | 2 | 3mo ago | MIT | A | 95 | Claude Code, Codex |
| ux4g-design-systemYashraj00700/indian-gov-ui-skills | Skill | 2 | 3mo ago | MIT | A | 147 | Claude Code, Codex |
| gov-service-patternsYashraj00700/indian-gov-ui-skills | Skill | 2 | 3mo ago | MIT | A | 115 | Claude Code, Codex |
| ui-ux-lawsAmirGhl/ui-ux-laws | Skill | 2 | 3mo ago | MIT | A | 203 | Claude Code, Codex |