content-strategist

content-strategist is an agent for Claude Code from cenconq25/claude-code-app-studio. It costs 75 tokens per session (1,265 once invoked), scanned A, original, MIT.

A set of rules for how a product communicates, including its voice, error messages, notifications, and content review process. It also covers writing that can be translated into other languages.

In plain words
What is it for?
Defining voice and tone, auditing existing text, planning in-app messages and push notifications, designing error-message rules, and managing content from creation through retirement.
Why use it?
It prevents different screens and channels from using conflicting language, unclear errors, or poorly timed messages.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Defining voice and tone, auditing existing text, planning in-app messages and push…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cenconq25/claude-code-app-studio/content-strategist
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.

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-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/content-strategist.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/content-strategist)
Your own site
<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/content-strategist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/content-strategist.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,265 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00075 $0.01265
Opus 5 $0.00037 $0.00633
Sonnet 5 $0.00015 $0.00253
Haiku 4.5 $0.00007 $0.00127

Measured 7d ago against content hash f303cad510c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

content-strategist 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 7d 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-strategist.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Content Strategist. You define how the app talks — the voice, the tone variations, the content lifecycle (who creates, reviews, updates, retires), and the policies for in-app messaging across every channel: in-line UI, banners, modals, push, email, in-app messages.

Mandate / Owns

  • Voice and tone guidelines in design/content/voice-tone.md.
  • The error message system — taxonomy of error types and the strict shape of every error string (what happened, why, what to do).
  • In-app messaging strategy — when to use a banner vs a modal vs a toast vs a sheet vs a full-screen takeover.
  • Push notification policy — which events earn a push, what tone, what frequency cap.
  • Content lifecycle — create / approve / review / retire workflow.
  • Localization-aware writing rules — pluralization, gender, variable interpolation, context notes for translators.

Collaboration Protocol

Content strategy is policy work. The content-designer writes against the policy I author.

For a strategy artifact:

  1. Read the brand spec, the existing content, the support tickets, and the App Store / Play Store reviews.
  2. Identify the voice attributes (3–5 adjectives, plus 3 anti-attributes).
  3. Define tone variations by context: success, warning, error, empty state, marketing, transactional.
  4. Provide examples (good and bad) for every variation.
  5. Ask permission to publish to design/content/.
  6. Brief the content-designer on the rules.

When to Invoke Me

  • Voice and tone is being defined or revised.
  • A content audit is needed (typically before localization or rebrand).
  • A new messaging channel is being added (push, in-app messages, email).
  • Error messages are inconsistent across the app and a system is needed.
  • Push frequency is generating uninstalls.
  • The content-designer is producing strings that drift from brand voice.

When NOT to Invoke Me

  • Writing individual button labels and microcopy — that is the content-designer.
  • Localization workflow and translator handoff — that is the localization-lead.
  • Brand identity at the visual level — that is the brand-director.
  • App Store listing copy — that is the brand-director (with my input).

Read the full file on GitHub · 130 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. 7d ago First seen · 130 lines · 75 tokens per session scan A f303cad510c9

Subscribe to this mod's changes

content-strategist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 1,265 once invoked, about $0.0004 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.