copywriting

copywriting is a skill for Claude Code, Codex from no-session/claude-code-skills. It costs 133 tokens per session (6,481 once invoked), scanned A, original, MIT.

A writing assistant for marketing copy, such as landing pages, emails, advertisements, sales pages, and product descriptions. It helps shape the message around the audience, offer, and desired action.

In plain words
What is it for?
Use it to draft headlines, calls to action, landing-page sections, email sequences, ads, and other promotional text.
Why use it?
It reduces the work of choosing a suitable structure, tone, and positioning for copy intended to encourage a response.

Skill for Claude CodeCodex

Part of the claude-code-skills plugin — 6 skills shipped together

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/no-session/claude-code-skills/copywriting
Any agent
npx skills add no-session/claude-code-skills --skill copywriting
Clone the repo
git clone --depth 1 https://github.com/no-session/claude-code-skills

Made for: Claude Code, Codex.

Or install claude-code-skills, the plugin that ships this one along with the rest of its 6 skills.

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/no-session/claude-code-skills/copywriting.svg)](https://agentmods.dev/skills/no-session/claude-code-skills/copywriting)
Your own site
<a href="https://agentmods.dev/skills/no-session/claude-code-skills/copywriting"><img src="https://agentmods.dev/badge/skills/no-session/claude-code-skills/copywriting.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,481 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00133 $0.06481
Opus 5 $0.00067 $0.03240
Sonnet 5 $0.00027 $0.01296
Haiku 4.5 $0.00013 $0.00648

Measured 5d ago against content hash 34d01a25bc94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 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.

skills/copywriting/SKILL.md · 682 lines

How it starts

The opening of the file, as written. The whole thing — 682 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copywriting

Agent Behavior

When triggered, follow this process:

1. Infer First, Ask Second

From the user's request, infer as much as possible: product, audience, tone, copy type, awareness level. Only ask about what you truly cannot infer. If you have enough to start, start — deliver a first draft and offer to refine.

Always infer:

  • Copy type from context (if they say "landing page," don't ask "what type of copy?")
  • Tone defaults to confident, clear, conversational unless specified
  • Awareness level defaults to Solution-Aware for organic traffic, Problem-Aware for paid/cold traffic

Only ask when critical info is missing:

  • What the product does (if not obvious from context)
  • The specific desired action (trial, demo, signup)
  • The unique mechanism (if you can't find or infer it)

2. Diagnose and Choose

  • Match audience awareness level to framework (see Awareness Levels)
  • Select copy length based on price point and decision complexity
  • Pick positioning angle based on competitive context

3. Deliver

  • Write the full copy in the appropriate format
  • Include 3–5 headline variants
  • Include 2–3 CTA variants
  • Label each section clearly (Hero, Problem, Solution, Proof, CTA)
  • Run the Pre-Delivery Checklist before presenting

4. Offer Next Steps

After delivering, offer: A/B variants, shorter/longer version, adaptation for a different channel.


First Principles

1. Copy Is Salesmanship in Writing

Its only purpose is to drive action — a sign-up, a demo booking, a trial start. Your landing page is the first salesperson a cold visitor meets. Treat it like a high-stakes conversation, not a brochure.

2. Write for "You," Not "We"

  • Say "you" and "your" more than "we" and "our"
  • Describe their problem, not your product history
  • Use their words (from reviews, support tickets, calls) — not your jargon

3. Benefits Over Features

Push every feature through this chain:

Feature           →  "AI-powered analytics dashboard"
Advantage         →  "Insights update in real time, unlike manual reporting"
Benefit           →  "Save 15 hours/week on reporting"
Emotional Outcome →  "Make decisions with confidence instead of second-guessing stale numbers"

Read the full file on GitHub · 682 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. 5d ago First seen · 682 lines · 133 tokens per session scan A 34d01a25bc94

Subscribe to this mod's changes

copywriting is a skill published in the GitHub repository no-session/claude-code-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 133 tokens to every session and 6,481 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens