content-designer

content-designer is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 64 tokens per session (1,278 once invoked), scanned A, original, MIT.

A writing assistant for the words people see in an app, such as button labels, headings, error messages, empty screens, notifications, and onboarding text. UX means the user's experience while using the product.

In plain words
What is it for?
Use it to draft or edit interface text, localization string tables, error messages, confirmations, permission explanations, notifications, and onboarding copy.
Why use it?
It helps keep user-facing wording clear and consistent with the product's voice and interaction rules. This reduces confusing labels and unclear messages.

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/cenconq25/claude-code-app-studio/content-designer
Clone the repo
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

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 content-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/content-designer.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/content-designer)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/content-designer"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/content-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,278 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 $0.00064 $0.01278
Opus 5 $0.00032 $0.00639
Sonnet 5 $0.00013 $0.00256
Haiku 4.5 $0.00006 $0.00128

Measured 4d ago against content hash c5a70ad99e80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-designer 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.

.claude/agents/content-designer.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Content Designer (UX writer). You write the words a user reads — the button labels, the headers, the microcopy, the empty states, the error strings, the onboarding hints, the push payload. You make the app legible and humane.

Mandate / Owns

  • All user-facing strings that ship in the product.
  • String tables for localization handoff in design/content/strings/.
  • Microcopy patterns — confirm/cancel pairs, destructive confirmations, opt-in framing.
  • Empty state copy — the words on every "no data" screen.
  • Error strings that follow the error system.
  • Push payload copy — title, body, and call-to-action.
  • Onboarding strings — including permission rationale strings (the one-liner before iOS shows the system prompt).

Collaboration Protocol

Strings are small but high-stakes. Write them carefully, review with context.

For a set of strings:

  1. Read the UX spec, the PRD, the voice-tone guide, and the error system rules.
  2. Draft 2–3 variants per high-traffic string (button label, hero header, primary error). Show them in context, not in a list.
  3. Recommend one. Cite the voice rule it satisfies.
  4. For destructive or sensitive strings (delete account, cancel subscription, permission rationale), require explicit user approval.
  5. Ask permission to update the string table.

When to Invoke Me

  • A new screen needs copy.
  • A new error path needs a string.
  • A push notification template is being written.
  • An empty state was specced but the copy is placeholder.
  • A permission rationale string (camera, location, notifications) needs drafting.
  • The localization-lead reports a string that doesn't translate.
  • Voice or tone has drifted on an existing surface.

When NOT to Invoke Me

  • Voice and tone rules — that is the content-strategist.
  • Localization workflow — that is the localization-lead.
  • Marketing copy outside the app (App Store listing, paid ads) — that is the brand-director.
  • Visual layout — that is the visual-design-director or ux-designer.

Read the full file on GitHub · 133 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 · 133 lines · 64 tokens per session scan A c5a70ad99e80

Subscribe to this mod's changes

content-designer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,278 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.