copy-that-sells

copy-that-sells is a skill for Claude Code from avectats7/copy-that-sells. It costs 208 tokens per session (5,776 once invoked), scanned A, original, MIT.

A writing specialist for promotional text whose goal is to attract attention and encourage action. It covers advertising, landing pages, emails, social posts, product descriptions, headlines, taglines, and longer sales copy.

In plain words
What is it for?
Use it to write or improve ads, billboards, headlines, taglines, landing pages, emails, social content, product descriptions, and brand manifestos.
Why use it?
It helps when wording must do more than fill a design space: it must be noticed, remembered, and acted on. It combines concise creative ideas with structured arguments for different levels of buyer awareness.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the copy-that-sells plugin — 1 skill shipped together

Good fit Use it to write or improve ads, billboards, headlines, taglines, landing pages, emails, social content, product descriptions, and brand manifestos.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/avectats7/copy-that-sells/copy-that-sells
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 avectats7/copy-that-sells --skill copy-that-sells
Clone the repo
git clone --depth 1 https://github.com/avectats7/copy-that-sells

Made for: Claude Code.

Or install copy-that-sells, the plugin that ships this one along with the rest of its 1 skill.

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 copy-that-sells

README.md
[![agentmods](https://agentmods.dev/badge/skills/avectats7/copy-that-sells/copy-that-sells/github.svg)](https://agentmods.dev/skills/avectats7/copy-that-sells/copy-that-sells)
Your own site
<a href="https://agentmods.dev/skills/avectats7/copy-that-sells/copy-that-sells"><img src="https://agentmods.dev/badge/skills/avectats7/copy-that-sells/copy-that-sells/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 copy-that-sells

Your own site · 80×15
<a href="https://agentmods.dev/skills/avectats7/copy-that-sells/copy-that-sells"><img src="https://agentmods.dev/badge/skills/avectats7/copy-that-sells/copy-that-sells.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 208 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,776 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 $0.00208 $0.05776
Opus 5 $0.00104 $0.02888
Sonnet 5 $0.00042 $0.01155
Haiku 4.5 $0.00021 $0.00578

Measured 12d ago against content hash aa659ab89b72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

copy-that-sells 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/validate.py, tests/run-tests.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/copy-that-sells/SKILL.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copy That Sells

You are writing copy whose job is to be read, remembered, and acted on. Not copy that fills a slot.

Two traditions meet here. D&AD's Copy Book teaches craft: an idea worth having, words worth using, the visual and the line working together. Bly's Copywriter's Handbook teaches direct response: structured headlines, structured leads, structured arguments that convert. The best copy uses both. The strongest line in a billboard and the best opening in a sales email are the same skill applied at different lengths.

The print and OOH posters that win Cannes Lions are the gold standard for compression. If a headline and an image can carry the idea on a billboard with nothing else, the idea is sound. Apply that same test to a homepage hero, a paid social ad, a subject line, a deck cover slide. If it would not work as a poster, it is probably not finished.


Read These Before You Write

For any non-trivial copy task, read the reference files. They are short and dense.

Core craft (read on every task):

  • references/frameworks.md. Schwartz's awareness levels and market sophistication, Bly's headline categories, the modern extensions (Listicle, Negative, Outcome-first), the 4 U's, the So-What ladder, AIDA, PAS, BFD, structured leads, long-copy architecture, direct-response checklists.
  • references/craft.md. D&AD Copy Book lessons: idea-first thinking, headline-visual logic, compression, voice, rhythm, the test of reading aloud.
  • references/self-edit.md. Final pass checklist, including the anti-AI writing rules (English Era 1 to 4 and Spanish) that every output must clear.

Format and language (read when relevant):

  • references/formats.md. Per-format blueprints with word counts: subject line, cold email, landing hero, pricing page, sales page, billboard, paid social (with hook bank), paid search (RSA), push, App Store, manifesto, pre-roll.
  • references/spanish-craft.md. The 20 percent rule, verb position, regional variants (rioplatense, mexicano, castellano, andino, caribeño), vos/tú/usted, banned Spanish vocabulary, verbatim LatAm winners. Read on every Spanish task.
  • references/voice-bank.md. Fifteen voices with two-line samples each, including three native Spanish registers. Use when no voice guide is present or when the diagnostic symptom is "it does not sound like us."
  • references/diagnostics.md. The critique-first procedure for when the user pastes existing copy. Symptom-cause-fix table. Edit vs Restructure vs Burn down decision.

Read the full file on GitHub · 307 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. 12d ago First seen · 307 lines · 208 tokens per session scan A aa659ab89b72

Subscribe to this mod's changes

copy-that-sells is a skill published in the GitHub repository avectats7/copy-that-sells (12 stars, last pushed 1mo ago), licensed MIT. It adds 208 tokens to every session and 5,776 once invoked, about $0.0010 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

creative-director

AI creative director with recursive self-assessment. Generates concepts using world-class methodologies (SIT, TRIZ, Lateral Thinking, bisociation), scores against 6 weighted criteria with Cannes/D&AD/HumanKind calibration, and recursively refines until the 9+ threshold is reached. Accepts briefs in any format — text…

eiwru/creative-director-skill · 147 tokens

sealeap-amazon-apparel-lifecycle-ads

A playbook for planning advertising on Amazon US for clothing products, using an ASIN lifecycle. An ASIN is Amazon's product identifier; the lifecycle describes whether a product is new, growing, mature, declining, or seasonal.

xjli360/sealeap-amazon-ad-skills · 167 tokens

sealeap-amazon-product-targeting

An Amazon Ads planning skill for targeting product pages and categories, including competitor, complementary, upsell, and own-product traffic.

xjli360/sealeap-amazon-ad-skills · 168 tokens

_mureo-shared

Skill "_mureo-shared" from logly/mureo, covering mureo shared patterns, installation, setup, claude code (recommended) and manual configuration.

logly/mureo · 22 tokens

creative-generate

A workflow for creating advertising images and banners from a strategy brief. It separates the main visual artwork from the accurately typeset text and produces variants for display or social formats.

logly/mureo · 131 tokens

tracking-health

Preventive audit of conversion tracking across all configured ad platforms — Meta pixels + CAPI, Google Ads conversion actions, and final-URL tracking-parameter consistency on every platform — with a GA4 cross-check. Use when the user asks to check tracking, audit conversion measurement, verify pixels / tags, check…

logly/mureo · 168 tokens