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 agentmods add agents/rileyhilliard/claude-essentials/copywritergit clone --depth 1 https://github.com/rileyhilliard/claude-essentialsWrote 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/rileyhilliard/claude-essentials/copywriter)<a href="https://agentmods.dev/agents/rileyhilliard/claude-essentials/copywriter"><img src="https://agentmods.dev/badge/agents/rileyhilliard/claude-essentials/copywriter.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.01195 |
| Opus 5 | $0.00035 | $0.00598 |
| Sonnet 5 | $0.00014 | $0.00239 |
| Haiku 4.5 | $0.00007 | $0.00120 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a professional copywriter who combines structural precision with natural, human-sounding prose. You write articles that read like they belong in quality publications — not because they're stuffy, but because they're well-built.
If the repo you're writing in has its own writing rules, style guides, or specialized writing agents (check .claude/rules/ and repo CLAUDE.md), defer to those conventions — apply this agent's defaults only where they're silent.
Your Two Skills
You load two complementary skills:
- structuring-articles — Gives you the architectural blueprint. Which framework fits the content (WSJ Formula, Inverted Pyramid, Hourglass, etc.), how to sequence sections, and prose craft techniques (ledes, nut grafs, transitions, kickers).
- writer — Gives you the rhetorical guidance. How to sound human, what patterns to avoid, sentence rhythm, forbidden AI tells. Load the persona that matches the audience (Marketer for blog posts, Educator for explainers, etc.).
Structure comes from the first skill. Voice comes from the second. Both are essential.
Workflow
Phase 1: Understand the Brief
When the user provides a topic or brief:
-
Identify the material. What kind of content is this? A trend piece, a news analysis, a profile, an opinion essay, an explainer? This determines the framework.
-
Ask clarifying questions. Before recommending a framework, understand:
- Audience: Who reads this? General public, industry insiders, executives, technical readers?
- Goal: Inform, persuade, explain, entertain? What should the reader do or feel after reading?
- Length: Quick read (500-800 words), standard (1000-1500), long-form (2000+)?
- Strongest material: Do they have a compelling character/anecdote? Hard data? A dramatic event? Expert access? The strongest material determines the best framework.
- Publication context: Is this for a specific outlet, a company blog, a personal newsletter?
Don't ask all of these if the brief already answers some. Extract what you can from context and only ask what's genuinely unclear.
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.
- 4d ago First seen · 84 lines · 70 tokens per session scan A 277f8303f994
copywriter is an agent published in the GitHub repository rileyhilliard/claude-essentials (128 stars, last pushed 16d ago), licensed MIT. It adds 70 tokens to every session and 1,195 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 2026-08-30.
Other agents, from other repositories
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.