form-cro

form-cro is a skill for Claude Code from seite-sh/seite. It costs 97 tokens per session (2,453 once invoked), scanned A, a copy of form-cro, MIT.

A framework for improving forms that collect information without creating an account, such as contact, lead, application, survey, demo-request, quote, or checkout forms.

In plain words
What is it for?
Use it to evaluate the form type, completion and abandonment data, mobile and desktop behaviour, required business information, and which fields can be removed or collected later.
Why use it?
It helps identify unnecessary fields and other sources of friction that cause people to abandon a form before submitting it.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Install

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.

agentmods
npx agentmods add skills/seite-sh/seite/form-cro
Any agent
npx skills add seite-sh/seite --skill form-cro
Clone the repo
git clone --depth 1 https://github.com/seite-sh/seite

Made for: Claude Code.

Wrote 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.

agentmods badge for form-cro

README.md
[![agentmods](https://agentmods.dev/badge/skills/seite-sh/seite/form-cro.svg)](https://agentmods.dev/skills/seite-sh/seite/form-cro)
Your own site
<a href="https://agentmods.dev/skills/seite-sh/seite/form-cro"><img src="https://agentmods.dev/badge/skills/seite-sh/seite/form-cro.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 91% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.02453
Opus 5 $0.00048 $0.01226
Sonnet 5 $0.00019 $0.00491
Haiku 4.5 $0.00010 $0.00245

Measured 6d ago against content hash a4f096c027b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

form-cro 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 6d 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.

Origin

This is a copy

91% identical to form-cro — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

seite-sh/.claude/skills/form-cro/SKILL.md · 429 lines

How it starts

The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Form CRO

You are an expert in form optimization. Your goal is to maximize form completion rates while capturing the data that matters.

Initial Assessment

Check for product marketing context first: If .claude/product-marketing-context.md exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Before providing recommendations, identify:

  1. Form Type

    • Lead capture (gated content, newsletter)
    • Contact form
    • Demo/sales request
    • Application form
    • Survey/feedback
    • Checkout form
    • Quote request
  2. Current State

    • How many fields?
    • What's the current completion rate?
    • Mobile vs. desktop split?
    • Where do users abandon?
  3. Business Context

    • What happens with form submissions?
    • Which fields are actually used in follow-up?
    • Are there compliance/legal requirements?

Core Principles

1. Every Field Has a Cost

Each field reduces completion rate. Rule of thumb:

  • 3 fields: Baseline
  • 4-6 fields: 10-25% reduction
  • 7+ fields: 25-50%+ reduction

For each field, ask:

  • Is this absolutely necessary before we can help them?
  • Can we get this information another way?
  • Can we ask this later?

2. Value Must Exceed Effort

  • Clear value proposition above form
  • Make what they get obvious
  • Reduce perceived effort (field count, labels)

3. Reduce Cognitive Load

  • One question per field
  • Clear, conversational labels
  • Logical grouping and order
  • Smart defaults where possible

Field-by-Field Optimization

Email Field

  • Single field, no confirmation
  • Inline validation
  • Typo detection (did you mean gmail.com?)
  • Proper mobile keyboard

Name Fields

  • Single "Name" vs. First/Last — test this
  • Single field reduces friction
  • Split needed only if personalization requires it

Phone Number

  • Make optional if possible
  • If required, explain why
  • Auto-format as they type
  • Country code handling

Company/Organization

  • Auto-suggest for faster entry
  • Enrichment after submission (Clearbit, etc.)
  • Consider inferring from email domain

Read the full file on GitHub · 429 lines

Changes

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.

  1. 6d ago First seen · 429 lines · 97 tokens per session scan A a4f096c027b3

Subscribe to this mod's changes

form-cro is a skill published in the GitHub repository seite-sh/seite (20 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 2,453 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to form-cro, differing in 7 lines, and is treated as a copy.