copywriting

copywriting is a skill for Codex from Infinite-Labs-AI/infinite-skills. It costs 70 tokens per session (827 once invoked), scanned A, original, MIT.

A guide for writing and rewriting copy for websites and landing pages, including headlines, descriptions, calls to action, pricing pages, and product pages. It emphasizes a clear promise supported by available evidence.

In plain words
What is it for?
Use it to draft or improve homepage, landing-page, pricing, feature, product, and hero-section copy, including headlines, subheads, CTAs, and objection handling.
Why use it?
It helps make a page easier to understand and gives the reader a clearer reason to act. It also identifies missing inputs such as the target audience, desired action, proof, and objections.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to draft or improve homepage, landing-page, pricing, feature, product, and hero-section copy, including headlines, subheads, CTAs, and objection handling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/infinite-labs-ai/infinite-skills/copywriting
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.

Any agent
npx skills add Infinite-Labs-AI/infinite-skills --skill copywriting
Clone the repo
git clone --depth 1 https://github.com/Infinite-Labs-AI/infinite-skills

Made for: Codex.

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 copywriting

README.md
[![agentmods](https://agentmods.dev/badge/skills/infinite-labs-ai/infinite-skills/copywriting/github.svg)](https://agentmods.dev/skills/infinite-labs-ai/infinite-skills/copywriting)
Your own site
<a href="https://agentmods.dev/skills/infinite-labs-ai/infinite-skills/copywriting"><img src="https://agentmods.dev/badge/skills/infinite-labs-ai/infinite-skills/copywriting/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.

agentmods 80×15 button for copywriting

Your own site · 80×15
<a href="https://agentmods.dev/skills/infinite-labs-ai/infinite-skills/copywriting"><img src="https://agentmods.dev/badge/skills/infinite-labs-ai/infinite-skills/copywriting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 827 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found 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 $0.00070 $0.00827
Opus 5 $0.00035 $0.00413
Sonnet 5 $0.00014 $0.00165
Haiku 4.5 $0.00007 $0.00083

Measured 12d ago against content hash 8b91c509ce44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

copywriting 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.

skills/copywriting/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copywriting

Write clear website and landing-page copy that makes a strong promise and backs it up with proof.

Scope

Use this for:

  • Homepage, landing page, pricing page, feature page, product page, and about page copy.
  • Hero headline, subheadline, CTA, value proposition, tagline, section copy, and objection handling.
  • Rewriting weak page copy to make it clearer and more persuasive.

Do not use this for:

  • Email flows or lifecycle messages. Use email-sequence.
  • Blog posts, SEO articles, or content calendars. Use content-strategy or seo-strategy.
  • Longform X/Twitter articles. Use x-article-writer.
  • Platform-specific Google, Meta, or LinkedIn ad copy. Use creative-brief or paid-ads.

Before asking questions, read existing product-marketing context if present: .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md.

Copy Inputs

Look for or ask for:

  • Target reader and traffic source.
  • Desired action.
  • Offer or product being sold.
  • Current page or draft.
  • Proof: numbers, customers, testimonials, demos, screenshots, case studies.
  • Objections and alternatives.
  • Tone constraints.

If proof is missing, write lower-claim copy and mark where proof is needed.

Build The Argument

Create the page argument before writing polished prose:

  • Reader arrives with this belief.
  • The page must change that belief to this.
  • The strongest promise is this.
  • The proof is this.
  • The next action is this.

Every section should move the reader closer to the action. Remove claims that do not support the argument.

Match Claims To Proof

For every meaningful claim, define:

  • Claim.
  • Proof type: customer quote, metric, demo, screenshot, credential, example, guarantee, comparison.
  • Proof strength: weak, usable, strong, publishable.
  • Allowed wording ceiling: what can be said honestly without overstating.
  • Placement: hero, proof block, FAQ, CTA area, pricing, section body.
  • Gap: what proof is missing.

Write The Copy

Read the full file on GitHub · 134 lines

Files

What ships with it

1 file 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.

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. 12d ago First seen · 134 lines · 70 tokens per session scan A 8b91c509ce44

Subscribe to this mod's changes

copywriting is a skill published in the GitHub repository Infinite-Labs-AI/infinite-skills (44 stars, last pushed 13d ago), licensed MIT. It adds 70 tokens to every session and 827 once invoked, about $0.0003 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 2026-08-30.