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.
npx skills add alebgl77/claude-inc --skill copywritinggit clone --depth 1 https://github.com/alebgl77/claude-incWrote 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.
[](https://agentmods.dev/skills/alebgl77/claude-inc/copywriting)<a href="https://agentmods.dev/skills/alebgl77/claude-inc/copywriting"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/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.
<a href="https://agentmods.dev/skills/alebgl77/claude-inc/copywriting"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/copywriting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00105 | $0.01032 |
| Opus 5.5 | $0.00042 | $0.00413 |
| Sonnet 5.5 | $0.00021 | $0.00206 |
| Haiku 4.5 | $0.00011 | $0.00103 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copywriting — Word Smith
"High-converting copy"
When to use
- Landing page, sales page, or hero copy — "write the landing page for our beta launch"
- Emails that must get opened and clicked — "draft the announcement email for new pricing"
- Short-form promo or ad copy blocks — "I need 10 headlines for this offer"
- Rewrites of flat, underperforming copy — "punch up this hero section"
- Not for long-form SEO content — hand that to
ai-seo
Workflow
- Lock the brief. One reader (role, pain, current belief), one offer, one action, one success metric. If any piece is missing, state your assumption in one line and keep moving.
- Pick the framework.
- AIDA — cold traffic; the reader needs the problem built before the pitch.
- PAS — problem-aware readers; agitate the pain they already feel, then resolve it.
- 4U (urgent, unique, useful, ultra-specific) — headlines and subject lines.
- Load the voice. Look for a brand or voice profile in the project (
brand/,voice.md, style guide). If found, extract tone rules and banned words. If not, mirror the user's existing copy and flag the gap at the top of the deliverable. - Build the headline matrix. 10 variants across distinct angles — benefit, pain, curiosity, proof/number, how-to, question, contrarian, urgency, comparison, story. Score each 0-4 on the 4Us; mark the top 3.
- Write the body. Follow the framework beat by beat. Attach a proof element to every claim — stat, customer quote, mini case, demo line, or guarantee. No naked promises.
- One CTA. Action verb + concrete outcome ("Send your first invoice free"). Repeat it verbatim in long assets; kill every competing link.
- Reading-level pass. Target grade 7 or below. Short sentences. Cut hedges and intensifiers — "really", "very", "arguably" all die.
- Run the "so what?" test. Read every line as the target reader asking "so what?". Any line without an answer gets cut or rewritten until the benefit is explicit.
- Deliver in the output format below.
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.
- 1mo ago First seen · 73 lines · 105 tokens per session scan A ff51f84aada3
copywriting is a skill published in the GitHub repository alebgl77/claude-inc (19 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 1,032 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
mantis-configure
Configures and validates Mantis pipeline environments, sandbox mechanisms, and AI models. Use to set up workflow.json, auto-detect host capabilities, switch between sandboxes (static-only, gvisor, microsandbox, gce), select AI models, and run fast 1-2s preflight tests. Don't use for scanning source code or running…
user-story-writer
Escribir historias de usuario bien estructuradas con criterios de aceptación y casos extremos. Úsalo cuando te pidan escribir historias de usuario, crear tickets a partir de un resumen de características, convertir un PRD en historias o redactar criterios de aceptación. Produce historias listas para estimar en formato…
output-dev-eval-testing
Create offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators with verify(), creating dataset YAML files, building eval workflows, or running workflow tests via CLI.
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
prompt-regression-suite
Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use when asked to stop prompt changes breaking production, set up golden tests or CI gates for an LLM feature, or test a model/prompt upgrade before shipping it. Produces a golden case set, per-case…