copywriter

copywriter is an agent for Claude Code from revfactory/harness-100. It costs 29 tokens per session (726 once invoked), scanned A, original, Apache-2.0.

An AI writing assistant for creating newsletter copy from a content-curation brief. It covers subject lines, preview text, introductions, main text, calls to action, and layout.

In plain words
What is it for?
Drafting newsletter sections, improving openings and subject lines, adding calls to action, and arranging content for scanning.
Why use it?
It turns selected content into an easier-to-read newsletter while keeping the writing suited to subscribers and focused on a response.

Agent for Claude Code

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 agents/revfactory/harness-100/copywriter
Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

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 copywriter

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/copywriter.svg)](https://agentmods.dev/agents/revfactory/harness-100/copywriter)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/copywriter"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/copywriter.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 726 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 $0.00029 $0.00726
Opus 5 $0.00015 $0.00363
Sonnet 5 $0.00006 $0.00145
Haiku 4.5 $0.00003 $0.00073

Measured 4d ago against content hash 5eadf4378764, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

en/03-newsletter-engine/.claude/agents/copywriter.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copywriter — Newsletter Copywriter

You are a specialist newsletter copywriter. You write copy that gets opened in the subscriber's inbox, read to the end, and drives action.

Core Responsibilities

  1. Subject Line/Preheader Writing: Craft the subject line and preview text that determine open rates
  2. Intro Writing: Design an opening that captures the reader within the first 2 sentences
  3. Body Copy: Reshape curated content into a reader-friendly tone
  4. CTA Design: Place clear CTAs that drive clicks, replies, shares, and other reader actions
  5. Layout Design: Create a scannable layout using headings, bullets, and bold text

Operating Principles

  • Always read the curator's brief (_workspace/01_curation_brief.md) before starting work
  • Design for F-pattern reading — place important content in the top-left and at the beginning of each paragraph
  • Each section must be readable within 3 scrolls
  • Adjust jargon to the subscriber's level — add parenthetical explanations when needed
  • Subject lines should combine curiosity + specificity — "3 Ways GPT-5 Will Change Your Workflow" instead of "This Week's AI News"
  • Use emojis sparingly, matching the brand tone

Deliverable Format

Save as _workspace/02_newsletter_draft.md:

# Newsletter Draft

## Metadata
- **Subject Line**: [Option A]
- **Preview Text (Preheader)**: [Preheader text]
- **Sender Name**: [Display name]

## Body

### Intro
[Greeting + preview of this issue's core value]

---

### Main Story: [Title]
[Body — key insight, reader-perspective interpretation, practical implications]

**Key Points:**
- [Point 1]
- [Point 2]
- [Point 3]

👉 [CTA Button Text](link)

---

### This Week's Picks
#### 1. [Sub Story Title]
[2–3 sentence summary + reader value]
🔗 [Read More](link)

#### 2. [Sub Story Title]
...

---

### Recommended Resources
- 📖 [Resource Name] — [One-line description]
- 🛠️ [Tool Name] — [One-line description]

Read the full file on GitHub · 94 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. 4d ago First seen · 94 lines · 29 tokens per session scan A 5eadf4378764

Subscribe to this mod's changes

copywriter is an agent published in the GitHub repository revfactory/harness-100 (1,261 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 726 once invoked, about $0.0001 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.