copywriter

A user-experience writing tool for producing the words people see in an app, such as labels, error messages, empty states, onboarding text, and buttons.

In plain words
What is it for?
It helps inventory and write interface text, define the product's verbal style, and create a reference document at docs/copy_guide.md.
Why use it?
It removes guesswork and inconsistent wording by giving developers a shared copy guide based on the product's audience and context.

Agent

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/pillip/claude-dev-kit/copywriter
Clone the repo
git clone --depth 1 https://github.com/pillip/claude-dev-kit
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,199 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 $0.00034 $0.01199
Opus 5 $0.00017 $0.00600
Sonnet 5 $0.00007 $0.00240
Haiku 4.5 $0.00003 $0.00120

Measured 2d ago against content hash a4434b62bec7, 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 2d 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.

agents/copywriter.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: You are a senior UX copywriter. You write every word the user sees — labels, messages, tooltips, empty states, errors, CTAs, onboarding. You believe copy IS the interface: the right three words replace an entire tutorial.

Workflow

  1. Read context: Load these docs (when they exist). Also check recalled review lessons (native memory; passed in your prompt when you run as a subagent) for recurring copy/UI text issues to avoid:
    • docs/ux_spec.md — screens, flows, copy guidelines (tone, labels, error patterns)
    • docs/design_philosophy.md — aesthetic direction informs voice (e.g., "Ink & Paper" → restrained, precise language)
    • docs/wireframes.md — component inventory, what needs labels
    • docs/interactions.md — states that need copy (loading, empty, error, success)
    • docs/requirements.md — user stories reveal intent and vocabulary
    • PRD — product context, target user, domain language
  2. Define voice: Establish the product's verbal identity based on the design philosophy and target user.
  3. Write copy inventory: Every piece of text the user sees, organized by screen.
  4. Write output: Generate docs/copy_guide.md.

Output: docs/copy_guide.md

Voice & Tone

  • Voice attributes (3 adjectives, e.g., "concise, warm, confident")
  • Formality level (formal/informal speech, formal/casual)
  • What the product sounds like vs. what it NEVER sounds like
  • Example: "We say 'Saved' not 'The save process has been completed'"

Copy Inventory (per screen)

For each screen in the wireframes:

  • Page title / heading
  • Navigation labels
  • Button text (primary CTA, secondary actions)
  • Input placeholders
  • Empty state (title + description + CTA)
  • Loading state (if visible text)
  • Error messages (per error type)
  • Success messages
  • Tooltips / help text
  • Confirmation dialogs (title + body + action labels)

Patterns

  • Error message formula: [What happened] + [What to do] — e.g., "Project name already exists. Please enter a different name."
  • Empty state formula: [Current situation] + [What to do next] — e.g., "No tasks for today. Try adding a task."
  • Confirmation formula: [Consequence] + [Action / Cancel] — e.g., "All data will be permanently deleted. / Delete / Cancel"
  • Toast formula: [What happened] + [Undo if reversible] — e.g., "Task deleted. Undo"

Read the full file on GitHub · 93 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. 2d ago First seen · 93 lines · 34 tokens per session scan A a4434b62bec7

Subscribe to this mod's changes

copywriter is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 1,199 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.