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.
git clone --depth 1 https://github.com/MohammadShehadeh/agent-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/commands/mohammadshehadeh/agent-skills/new-form)<a href="https://agentmods.dev/commands/mohammadshehadeh/agent-skills/new-form"><img src="https://agentmods.dev/badge/commands/mohammadshehadeh/agent-skills/new-form/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/commands/mohammadshehadeh/agent-skills/new-form"><img src="https://agentmods.dev/badge/commands/mohammadshehadeh/agent-skills/new-form.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 | $0.00034 | $0.00558 |
| Opus 5 | $0.00017 | $0.00279 |
| Sonnet 5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
new-form 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 12d 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
Build a form: $ARGUMENTS
Load the agent-skills-form skill (and agent-skills-conventions for errors/hooks when wiring submit). Work through phases 1–3 as the plan — no markup before confirmation.
1. Decide — form library or not
- 2+ fields, validation, or submit state → RHF + zod (this command).
- Single input (search, inline rename) → plain state or form action; stop and say so if the ask is over-engineered.
- Survey the repo: existing forms, schema location, submit hooks, Field components — extend before inventing.
2. Schema & contract — before markup
- Export a zod schema; derive
type FormValues = z.infer<typeof schema>. - List every field, validation rule, and default value.
- Separate field validation (zod) from submit failures (
ErrorKeyliterals for server/network). - Add submit keys to
constants/error-keys.tsbefore implementation.
Present schema, fields, and error keys — wait for confirmation.
3. Controls & layout
- Pick controls from the chooser in
agent-skills-form→references/forms.md. - Plan
FieldGroup/Field/FieldSetstructure — no rawdiv+space-y-*. 'use client'on the form component leaf only.
4. Build
- Markup: shadcn Field primitives;
data-invalid+aria-invalidtogether;InputGroupfor buttons-in-inputs. - Logic:
useForm+zodResolver, validationmodechosen deliberately (onToucheddefault,onChangeonly when a field needs per-keystroke feedback); double-submit guard via async hook orisSubmitting. - Submit: call service/action returning
Result<T, K>; surface{ ok: false, errorKey }via toast or root error — never hardcoded strings. - Files: kebab-case, colocated with feature; schema in
lib/; no barrelindex.ts.
5. Verify
- All field validation states render correctly.
- Submit: loading, success, and each planned
errorKeypath. - Typecheck/lint pass; narrowed
Result<T, K>at call site.
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.
- 12d ago First seen · 43 lines · 34 tokens per session scan A 4955e694b881
new-form is a command published in the GitHub repository MohammadShehadeh/agent-skills (2 stars, last pushed 28d ago), licensed MIT. It adds 34 tokens to every session and 558 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
design-form
Design a form with the fewest fields that works, clear labels, and errors that help.
frontend-3d
You are an expert in 3D web development using Three.js, React Three Fiber, WebGL, and WebGPU. You create immersive 3D experiences for the web.
frontend-design
Read and follow the instructions in agents/frontend-design/design-all.md. Also read all referenced files in agents/frontend-design/reference/ as needed for the task.
get-component-source
The full TSX source of a component (append " demo" for its usage example).