microcopy

microcopy is a skill for Claude Code, Codex from viknesh20-20/claude-code-tool-kit. It costs 50 tokens per session (1,945 once invoked), scanned A, original, MIT.

Writing and review guidance for small pieces of user-interface text, such as buttons, errors, tooltips, labels, and confirmation messages. It focuses on clear, consistent wording that helps people complete or recover from an action.

In plain words
What is it for?
Use it to replace placeholder copy, improve error and success messages, design empty states, label forms, write onboarding text, or review localization readiness.
Why use it?
Unclear interface text can make a product difficult to use even when the underlying feature works. It helps make messages direct, understandable, consistent, and ready for translation.

Skill for Claude CodeCodex

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 skills/viknesh20-20/claude-code-tool-kit/microcopy
Any agent
npx skills add viknesh20-20/claude-code-tool-kit --skill microcopy
Clone the repo
git clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kit

Made for: Claude Code, Codex.

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 microcopy

README.md
[![agentmods](https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/microcopy.svg)](https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/microcopy)
Your own site
<a href="https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/microcopy"><img src="https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/microcopy.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,945 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 $0.00050 $0.01945
Opus 5 $0.00025 $0.00972
Sonnet 5 $0.00010 $0.00389
Haiku 4.5 $0.00005 $0.00194

Measured 3d ago against content hash a609d2500d88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

microcopy 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/skills/microcopy/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/microcopy

Write the small strings that decide whether users figure your product out — or churn. Bad copy makes good visuals fail; good copy carries average visuals.

When to use

  • Designing or reviewing any user-facing text — buttons, errors, empty states, tooltips, confirmations, form labels, onboarding.
  • After a UX review flagged unclear messaging.
  • When a feature ships with placeholder strings ("Submit," "Error," "Loading…") and needs real ones.
  • When localizing — the source strings need to be localizable in the first place.

Operating method

1. Establish voice

Read 5–10 existing strings from the product before writing new ones. Identify:

  • Tone — professional / friendly / playful / clinical. Most B2B is professional-with-warmth; consumer varies wildly.
  • Person — second person ("Save your changes") almost always. First-person plural ("We saved your changes") for system updates only.
  • Verb usage — direct ("Save"), polite ("Please save"), or playful ("Stash it"). Pick one and stick with it.
  • Punctuation — sentence case vs title case for buttons. Periods at end of error messages or not.
  • Emoji — used or not. (Default: not. Add only if the product already uses them.)

If no existing strings exist, default to: direct, second person, sentence case for buttons, periods on full sentences, no emoji.

2. Apply the four rules

Verbs over nouns on buttons. Buttons do something. Use the verb.

Bad Good
Submit Send invite
OK Save changes
Confirmation Confirm payment
Settings Open settings

Specific errors with recovery. Tell the user what went wrong AND what to do.

Bad Good
Invalid input Email must include an @ symbol
Error Couldn't reach the server. Check your connection or retry.
Try again Card declined — try a different card
Failed Two-factor code expired — request a new one

Empty states have CTAs. Don't leave the user stranded with "No results."

Read the full file on GitHub · 199 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 · 199 lines · 50 tokens per session scan A a609d2500d88

Subscribe to this mod's changes

microcopy is a skill published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 1,945 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 2026-08-31.