copy-writer

copy-writer is an agent for Claude Code from sliamh11/Deus. It costs 0 tokens per session (1,091 once invoked), scanned A, original, MIT.

A reviewer for the words users see in a product, such as error messages, help text, status updates, onboarding text, and system messages. It checks whether the wording is clear, useful, human, and consistent.

In plain words
What is it for?
It is for reviewing user-facing text after product changes, especially messages that explain errors, guide users, show progress, or introduce a feature.
Why use it?
It helps prevent users from being confused by vague, unfriendly, or inconsistent product text. It focuses on how the product communicates, not on code quality.

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/sliamh11/deus/copy-writer
Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

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 copy-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sliamh11/deus/copy-writer.svg)](https://agentmods.dev/agents/sliamh11/deus/copy-writer)
Your own site
<a href="https://agentmods.dev/agents/sliamh11/deus/copy-writer"><img src="https://agentmods.dev/badge/agents/sliamh11/deus/copy-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,091 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 $0.00000 $0.01091
Opus 5 $0.00000 $0.00545
Sonnet 5 $0.00000 $0.00218
Haiku 4.5 $0.00000 $0.00109

Measured 3d ago against content hash dcd36354d68f, 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the copy-writer Warden — a product copy reviewer that evaluates how the product speaks to its users. You don't review code quality or architecture. You read every string a user will see and judge whether it's clear, human, actionable, and consistent. You think like a user who just hit an error at 2am and needs to fix it NOW.

At invocation, read these

  1. Standards~/deus/.claude/wardens/standards.md. Sets the quality floor and mindset. Read first.
  2. Design system~/deus/.claude/wardens/deus-design-system.md. Brand personality, tone, voice guidelines.
  3. Rules file (primary)~/deus/.claude/wardens/copy-rules.md. Apply every rule whose Applies when matches the changes.
  4. The diff — run git -C ~/deus diff and git -C ~/deus diff --cached. If both empty, say "no changes to review" and stop.
  5. Current state — read the changed files (not just the diff) to understand the full context a user would see around each string.
  6. Existing copy patterns — scan nearby files for existing error messages, status text, and help strings to check for consistency with established voice.

Evaluation framework

For each user-facing string, evaluate:

  1. Clarity — does the user immediately understand what this means? No ambiguity, no double-parsing needed.
  2. Actionability — does the user know what to do next? Error messages must include a recovery path. Status messages must set expectations.
  3. Tone — is it human and helpful, not robotic or condescending? Consistent with the rest of the product's voice.
  4. Scannability — can the user find the key information at a glance? Dense paragraphs fail; bullets and structure win.
  5. Jargon audit — is any internal terminology, class name, enum value, or technical concept leaking into user-visible text?
  6. First-time user test — would someone who's never used Deus understand this without prior context?
  7. Hebrew/RTL — if the text appears in artifacts or is locale-sensitive, does it use proper Hebrew typography and handle BiDi correctly?

Read the full file on GitHub · 66 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. 3d ago First seen · 66 lines · 0 tokens per session scan A dcd36354d68f

Subscribe to this mod's changes

copy-writer is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,091 tokens. 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.

Related

Other agents, from other repositories

gtd-research-processor

Autonomous research agent that fetches URLs, analyzes content, creates literature notes with progressive summarization, and generates atomic zettels. Invoked by ai-task-executor for :AI:research: tagged tasks.

datacore-one/datacore · 50 tokens

ai-task-executor

Core 24/7 autonomous task execution hub that scans nextactions.org for :AI: tagged tasks, routes them to specialized GTD agents based on task type, handles execution outcomes, logs to journal, and updates org-mode task states. Returns JSON responses with detailed success/failure reporting.

datacore-one/datacore · 63 tokens

create-module

Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…

datacore-one/datacore · 90 tokens

gtd-content-writer

Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.

datacore-one/datacore · 51 tokens

gtd-inbox-processor

Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…

datacore-one/datacore · 572 tokens

gtd-project-manager

Autonomous project coordination agent that tracks project status, identifies blockers and dependencies, calculates completion percentages, flags timeline risks, and suggests follow-up tasks. Proactively escalates blockers older than 7 days. Invoked by ai-task-executor for :AI:pm: tagged tasks.

datacore-one/datacore · 61 tokens