copywriting

copywriting is a skill for Claude Code, Codex from hoangatg/ai-agent-toolkit. It costs 31 tokens per session (708 once invoked), scanned A, original, MIT.

A writing workflow for marketing content such as landing pages, calls to action, email sequences, and conversion-focused copy.

In plain words
What is it for?
It helps structure headlines, supporting text, calls to action, and other promotional content.
Why use it?
It helps turn product details into clear messages that explain value and guide readers toward an action.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps structure headlines, supporting text, calls to action, and other promotional content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hoangatg/ai-agent-toolkit/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 hoangatg/ai-agent-toolkit --skill copywriting
Clone the repo
git clone --depth 1 https://github.com/hoangatg/ai-agent-toolkit

Made for: Claude Code, 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/hoangatg/ai-agent-toolkit/copywriting.svg)](https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/copywriting)
Your own site
<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/copywriting"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/copywriting.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 708 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.
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 $0.00031 $0.00708
Opus 5 $0.00015 $0.00354
Sonnet 5 $0.00006 $0.00142
Haiku 4.5 $0.00003 $0.00071

Measured 4d ago against content hash 334fbc0fd603, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 4d 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.

.agent/skills/copywriting/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copywriting

Words that convert readers into users, users into customers.


1. Copywriting Principles

Principle Application
Benefit over feature "Save 10 hours/week" not "Automated scheduler"
Clear over clever Clarity beats creativity
Specific over vague "10,000+ users" not "Many users"
Active voice "We build" not "It is built by"
Scannable Headers, bullets, short paragraphs

2. Landing Page Framework

AIDA Structure

Section Purpose Example
Attention Hook with pain point "Tired of losing leads?"
Interest Show you understand "We know sales teams waste 5h/day on..."
Desire Show the solution "Automate follow-ups, close 3x more"
Action Clear CTA "Start free trial →"

Above the Fold

Element Must Have
Headline Clear value proposition
Subheadline Support with detail
CTA One primary action
Social proof Logos, numbers, or testimonial
Visual Product screenshot or demo

3. CTA Design

CTA Principles

Principle Application
Action-oriented "Start building" not "Submit"
Value-focused "Get my free report" not "Download"
Urgency "Limited spots" or "Today only"
One CTA per section Don't overwhelm with choices

4. Email Sequences

Welcome Sequence (5 emails)

Email Timing Purpose
1. Welcome Immediately Confirm, set expectations
2. Quick win Day 1 First value delivered
3. Social proof Day 3 Case study or testimonial
4. Deep dive Day 5 Feature education
5. Activation Day 7 CTA to upgrade/complete setup

5. SEO Content

Principle Application
Search intent Match what users actually search for
Headers hierarchy H1 → H2 → H3, keyword-rich
Meta description 150-160 chars, include CTA
Internal linking Connect related content
Content depth Comprehensive, not thin

Read the full file on GitHub · 99 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. 4d ago First seen · 99 lines · 31 tokens per session scan A 334fbc0fd603

Subscribe to this mod's changes

copywriting is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 708 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 2026-09-03.