copy-writer

A writing assistant for text shown to users inside a product, such as button labels, emails, and onboarding tips. It produces several short wording options in different tones.

In plain words
What is it for?
Use it to write UI labels, tooltips, email subject lines, onboarding messages, and other product copy.
Why use it?
It helps when interface text is unclear, too long, or difficult to phrase consistently. It gives you ready-to-compare alternatives.

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/hamzafarooq/claude-code-starter/copy-writer
Clone the repo
git clone --depth 1 https://github.com/hamzafarooq/claude-code-starter

Made for: Claude Code.

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 150 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 $0.00043 $0.00150
Opus 5 $0.00022 $0.00075
Sonnet 5 $0.00009 $0.00030
Haiku 4.5 $0.00004 $0.00015

Measured 3d ago against content hash 83366b4634d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copy-writer 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 3d 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.

.claude/agents/copy-writer.md · 20 lines

What it actually says

Write concise, clear copy for the product.

For each request, return 3 options labeled A, B, and C. Tag each with its tone: [Direct] [Warm] [Bold]

Keep all copy under 12 words unless the format requires more. Match the product voice: professional, plain English, no jargon.

Do not explain your choices. Return the options only.

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. 3d ago First seen · 20 lines · 43 tokens per session scan A 83366b4634d4

Subscribe to this mod's changes

copy-writer is an agent published in the GitHub repository hamzafarooq/claude-code-starter (138 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 150 once invoked, about $0.0002 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.