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 oborchers/fractional-cto --skill form-designgit clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/form-design)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/form-design"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/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/oborchers/fractional-cto/form-design"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/form-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 | $0.00061 | $0.00876 |
| Opus 5.5 | $0.00024 | $0.00350 |
| Sonnet 5.5 | $0.00012 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00088 |
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 5d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forms Should Feel Like Conversations, Not Paperwork
Luke Wroblewski's landmark study established the baseline: inline validation produces a 22% increase in success rates, 42% faster completion, and 47% fewer eye fixations compared to submit-time validation.
Validation Strategy: Reward Early, Punish Late
The optimal strategy is to validate after the user leaves a field (on blur), never while typing.
Rules:
- Show green checkmarks for correct inputs immediately on blur
- Delay error messages until the user has finished input and moved on
- Never show errors before the user has typed anything — premature validation causes longer completion times and higher error rates
- Premature validation forces constant switching between "completion mode" and "revision mode"
Auto-Save vs. Explicit Save
Start with explicit save as the default. Never mix auto-save and explicit save in a single form.
| Control Type | Save Behavior |
|---|---|
| Toggle switches | Save immediately (imperative controls, like flipping a light switch) |
| Text inputs, radio buttons, checkboxes | Explicit save via button |
If auto-save is used for text inputs:
- Save on blur AND 3 seconds after the last keystroke
- Never auto-save data with financial, security, or privacy implications
Counterintuitive finding: Even with auto-save, keep the Save button. Users who have spent years learning that explicit saves are required experience genuine anxiety when the button disappears. The Save button provides psychological reassurance even when it does nothing the system wouldn't do automatically.
Error Messages: The "Fix It" Test
Every error message must tell the user what went wrong AND how to fix it.
| Bad | Good |
|---|---|
| "Invalid password" | "Insert a password of at least 8 characters" |
| "Error in field" | "Email must include an @ symbol" |
| "Validation failed" | "Phone number must be 10 digits, e.g. 555-123-4567" |
Placement rules:
- Place errors near the offending field, not just at the top of the form
- Use red borders and explanatory text
- The red-for-errors convention is universal — do not reinvent it
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 87 lines · 61 tokens per session scan A a8da62caea64
form-design is a skill published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 876 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 2026-10-13.
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.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.