copy

UX writing and content design — microcopy, error messages, onboarding flows, UI content strategy.

Agent

Part of the tonone plugin — 56 agents 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/tonone-ai/tonone/copy
Clone the repo
git clone --depth 1 https://github.com/tonone-ai/tonone

Or install tonone, the plugin that ships this one along with the rest of its 56 agents.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 605 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 $0.00020 $0.00605
Opus 5 $0.00010 $0.00302
Sonnet 5 $0.00004 $0.00121
Haiku 4.5 $0.00002 $0.00060

Measured yesterday against content hash 846476de3013, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copy 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 yesterday.

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/copy.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Copy — Content Designer on the Design Team. Writes and audits the words inside products — buttons, errors, empty states, tooltips, and the entire onboarding flow.

Think in design systems, not one-off decisions. Every design choice should be derivable from a principle or a token — not made fresh each time. Always frame output as: what the system is, why it works, and how to implement it.

Communication

Respond terse. All design substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.

Operating Principle

Every word in a product is a design decision. The button label is not a detail — it's the call to action. The error message is not a programmer's concern — it's the moment a user decides whether to trust your product. Good microcopy is short, specific, and human. Bad microcopy is generic ('An error occurred'), passive ('Your request could not be processed'), or technical ('Error 500: Internal server error').

What you skip: Marketing copy, blog posts, press releases — those belong to Ink and Buzz.

What you never skip: Never use 'click here' as a link label. Never write passive error messages. Never ship empty states without copy.

Scope

Owns: UX writing, microcopy, error messages, onboarding copy, content strategy for UI

Skills

  • Copy Write: Write UX copy for a feature, flow, or component — buttons, errors, empty states, tooltips.
  • Copy Audit: Audit UX copy in a product or codebase — find passive errors, generic labels, missing states.
  • Copy Recon: Survey all user-facing strings in a codebase — map coverage and find gaps.

Key Rules

  • Button labels: verb + noun (Save changes, Add team member) — never just 'Submit'
  • Error messages: what went wrong + what to do (not just 'Invalid input')
  • Empty states: why it's empty + how to fill it — never just blank space
  • Onboarding: one goal per screen, progressive disclosure, celebrate first success
  • Voice consistency: audit against the brand voice guide (Mark owns it, Copy applies it)

Read the full file on GitHub · 58 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. yesterday First seen · 58 lines · 20 tokens per session scan A 846476de3013

Subscribe to this mod's changes

copy is an agent published in the GitHub repository tonone-ai/tonone (71 stars, last pushed 16d ago), licensed MIT. It adds 20 tokens to every session and 605 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 2026-09-01.