clean-copy

clean-copy is a skill for Claude Code, Codex from petekp/claude-code-setup. It costs 76 tokens per session (919 once invoked), scanned A, original, MIT.

A review method for deciding whether user-facing interface text should exist before rewriting it. It covers labels, hints, warnings, empty states, notifications, confirmations, and button text.

In plain words
What is it for?
Use it when auditing or simplifying text in an interface, including labels, help text, warnings, empty states, toasts, and confirmations.
Why use it?
Extra copy can repeat nearby information or introduce worries users did not have. This method removes unnecessary text instead of merely polishing it.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when auditing or simplifying text in an interface, including labels, help text, warnings, empty states, toasts, and confirmations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/petekp/claude-code-setup/clean-copy
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.

Any agent
npx skills add petekp/claude-code-setup --skill clean-copy
Clone the repo
git clone --depth 1 https://github.com/petekp/claude-code-setup

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 clean-copy

README.md
[![agentmods](https://agentmods.dev/badge/skills/petekp/claude-code-setup/clean-copy/github.svg)](https://agentmods.dev/skills/petekp/claude-code-setup/clean-copy)
Your own site
<a href="https://agentmods.dev/skills/petekp/claude-code-setup/clean-copy"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/clean-copy/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for clean-copy

Your own site · 80×15
<a href="https://agentmods.dev/skills/petekp/claude-code-setup/clean-copy"><img src="https://agentmods.dev/badge/skills/petekp/claude-code-setup/clean-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 919 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 $0.00076 $0.00919
Opus 5.5 $0.00030 $0.00368
Sonnet 5.5 $0.00015 $0.00184
Haiku 4.5 $0.00008 $0.00092

Measured 23d ago against content hash 8388da270ff4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

clean-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 23d 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.

skills/clean-copy/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean copy

Most bad copy is not badly written. It is copy that should not be on the screen. Editing it for tone only makes the wrong thing read better. So the first question is never "how should this be phrased". It is: should this exist?

The ladder

Walk each string down these rungs in order. Stop at the first one that fires and delete.

1. Does this need to surface at all? Would the user ever have wondered about this, unprompted? If not, you are not answering a question. You are planting one. Nobody opens an avatar cropper wondering whether the circle is a true circle. A caption reading "the preview is rendered at the exact size used on your profile" makes them wonder whether it might not be.

2. Does the label need to exist? A caption earns its place only when the value is meaningless without it. If the label, the field, or the value beside it already says the thing, the caption is noise. A field labelled "Retry limit" does not need "how many times we retry" beneath it. A bare "30" does need "seconds" beside it. That one stays.

3. Is it pre-empting something the user never had to consider? The tell: copy that rules out a failure rather than describing a behaviour.

Cancel upload Always keeps the files already transferred. Never wipes the folder like the old cancel did.

That second sentence exists because of a bug. The user does not know about the bug, does not share your memory of fixing it, and now has a worry they arrived without. The fix for a fixed bug is the fix. Not a caption about the fix. The same goes for copy defending a design decision, or hedging about something that simply works: "this may look slow but it is not", "don't worry if the count seems off for a moment".

4. Rewrite to remove the offending part. If nothing is left, delete the element. Do not preserve a hint because there was a hint there. An empty hint prop comes off the component. An explanatory <p> gets deleted, not shortened to a stub.

What survives

Read the full file on GitHub · 49 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. 23d ago First seen · 49 lines · 76 tokens per session scan A 8388da270ff4

Subscribe to this mod's changes

clean-copy is a skill published in the GitHub repository petekp/claude-code-setup (48 stars, last pushed 10d ago), licensed MIT. It adds 76 tokens to every session and 919 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-23.