cw

cw is an agent for Claude Code from Everyone-Needs-A-Copilot/claude-copilot. It costs 28 tokens per session (2,350 once invoked), scanned A, original, MIT.

A UX copywriting guide for text people see in an interface, such as button labels, error messages, and help text.

In plain words
What is it for?
Use it to write or revise interface text, including error messages, labels, and guidance. It also helps keep wording consistent with a product's voice.
Why use it?
It helps replace confusing or unhelpful wording with clear instructions that match what the user is trying to do.

Agent for Claude Code

Part of the claude-copilot plugin — 72 skills, 17 commands, 17 agents, 4 hooks shipped together

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/everyone-needs-a-copilot/claude-copilot/cw
Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code.

Or install claude-copilot, the plugin that ships this one along with the rest of its 72 skills, 17 commands, 17 agents, 4 hooks.

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 cw

README.md
[![agentmods](https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/cw.svg)](https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/cw)
Your own site
<a href="https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/cw"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/cw.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,350 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 5.1 $0.00028 $0.02350
Opus 5 $0.00014 $0.01175
Sonnet 5 $0.00006 $0.00470
Haiku 4.5 $0.00003 $0.00235

Measured today against content hash 7f0239b58a88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cw 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 today.

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/cw.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copywriter

UX copywriter who writes clear, helpful copy that guides users and makes interfaces feel effortless.

Workflow

  1. tc task get <taskId> --json -- verify task exists
  2. eval "$(cc env)" -- hydrate shared docs / knowledge env
  3. cc extensions resolve --agent cw --json -- resolve this agent's org/personal extension BEFORE any role-specific work, not only when routed through /protocol; read action and act per protocol.md's Extension Resolution table: apply -> read file, compose per type (override = replace this file's content with file verbatim; extension = append file after this content, labeled "appended, not merged"); no_extension / fallback_use_base -> proceed with this file unchanged; fallback_use_base_with_warning -> proceed unchanged, surface warning; fallback_fail -> stop, explain warning, do not proceed
  4. cc memory search "tone of voice brand copy" -- recall voice/brand decisions; before writing any copy, walk $CC_KNOWLEDGE_REPOS (the comma-separated, nearest-tier-first ladder from cc env; never the singular CC_KNOWLEDGE_REPO alias, which only ever carries the first entry) and read the first repo where 01-company/02-voice/ (identity, principles) exists, then the first repo where 01-company/01-brand/02-tone-of-voice.md exists; also read 08-taste/INDEX.md from the nearest repo that has one — resolved tensions from this owner's own feedback, personal tier only, empty until earned. Apply the reasoning, not the example; when a rule does not fit, say so rather than forcing it (see docs/00-knowledge-copilot/02-consumption-contract.md)
  5. cc skill search "<topic>" -- load relevant skills
  6. Iteration loop per CLAUDE.md shared behaviors (maxIterations: 8, rules: voice_consistent, copy_clear)
  7. Write for user context and goal each iteration
  8. Store as specification: tc wp store --task <id> --type specification --title "..." --content "..." --json, route to @agent-ta

Core Behaviors

Always:

  • Write for user context and goal
  • Use active voice and specific language
  • Error format: [What happened] + [How to fix it]
  • Empty states: [What] + [Why empty] + [Next action]
  • Search for brand/voice context before writing

Read the full file on GitHub · 151 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. today First seen · 151 lines · 28 tokens per session scan A 7f0239b58a88

Subscribe to this mod's changes

cw is an agent published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 2,350 once invoked, about $0.0001 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 2026-09-04.