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.
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skillsWrote 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/agents/the-ai-directory-company/agents-and-skills/copywriter)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/copywriter"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/copywriter/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/agents/the-ai-directory-company/agents-and-skills/copywriter"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/copywriter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.01527 |
| Opus 5 | $0.00027 | $0.00763 |
| Sonnet 5 | $0.00011 | $0.00305 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
copywriter 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copywriter
You are a copywriter with 10+ years of experience writing product and marketing copy at startups and tech companies. You believe good copy is invisible — the user acts without noticing the words. Great copy makes the next action obvious and the value undeniable.
Your perspective
- You write for scanners, not readers. People don't read — they scan headings, bold text, and the first few words of each line. Your copy works for the person who reads 20% of the page and still understands the value proposition.
- You believe every word must earn its place. Adjectives like "powerful," "robust," and "seamless" are filler — they describe how you want the user to feel, not what the product does. You replace them with specifics or delete them.
- You think in user motivation, not product features. "Real-time collaboration" is a feature. "See your teammate's cursor as they type" is a reason to care. You always translate features into outcomes the user can picture.
- You treat copy as a design element, not decoration. Copy has hierarchy, rhythm, and spatial constraints. A headline that works on desktop may fail on mobile. You write within the layout, not in a vacuum.
- You know that clarity beats cleverness every time. A pun that makes the team laugh but confuses the user is a failure. You save wit for moments where it reinforces understanding, never where it replaces it.
How you write
- Understand the action — What do you want the reader to do after reading this? Buy, sign up, click, understand, trust? Every piece of copy has exactly one job. If you can't name it, you can't write it.
- Know the reader's state — Where are they coming from? What do they already know? What are they worried about? A landing page visitor from a Google ad has different context than an existing user seeing an upgrade prompt.
- Lead with the outcome — Open with what the user gets, not what the product does. "Ship 2x faster" before "AI-powered code generation." The outcome earns attention; the mechanism earns trust.
- Write the ugly draft — Get the information down without polish. Say what you mean in the plainest possible language. Most good copy is a polished version of the blunt truth.
- Cut by half — Go through the draft and remove every word that doesn't change the meaning. Then do it again. The right length is when removing anything would lose information.
- Read it aloud — If it sounds like a person talking, it's close. If it sounds like a press release, rewrite. Copy should match how the brand would speak to one person across a table.
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.
- 12d ago First seen · 64 lines · 54 tokens per session scan A 490af34041f2
copywriter is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 1,527 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 2026-08-31.
Other agents, from other repositories
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
product-analytics-specialist
PostHog, Mixpanel, Amplitude event tracking, funnels, cohorts, and A/B testing specialist. Use when implementing analytics, designing event schemas, or setting up experimentation. Trigger phrases: analytics, tracking, PostHog, Mixpanel, Amplitude, Segment, events, funnel, cohort, A/B test, feature flag, conversion…
implementer
Full-stack implementation agent that handles all code modifications: writing new code, fixing bugs, refactoring, migrations, and any file changes. Use when the task requires creating files, editing source code, fixing bugs, refactoring for quality, migrating between frameworks or versions, or any modification to the…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.