scrub

scrub is a command for Claude Code from seite-sh/seite. It costs 0 tokens per session (1,237 once invoked), scanned C, a copy of scrub, MIT.

A command that cleans markdown content files by removing invisible Unicode characters, formatting leftovers, and certain punctuation patterns associated with generated text.

In plain words
What is it for?
Use it to scrub a markdown file, replace em dashes when appropriate, tidy whitespace, and see a summary of the changes.
Why use it?
It helps remove hidden characters and presentation artifacts that may cause unexpected formatting or make text look unnatural.

Command 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 commands/seite-sh/seite/scrub
Clone the repo
git clone --depth 1 https://github.com/seite-sh/seite

Made for: Claude Code.

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 1,237 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.01237
Opus 5 $0.00000 $0.00619
Sonnet 5 $0.00000 $0.00247
Haiku 4.5 $0.00000 $0.00124

Measured 3d ago against content hash 859b30964a52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

scrub scanned grade C with 1 finding 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

Content​ marketing​ is​ a​ powerful​ strategy—businesses can reach global audiences—and convert more customers. ``` (Contains zero-width spaces after words and em-dashes) **After:** ``` Content marketing is a powerful st
Origin

This is a copy

100% identical to scrub — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

seite-sh/.claude/commands/scrub.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scrub Command

Use this command to remove invisible AI-generated watermarks and telltale patterns from markdown content files.

Usage

/scrub [file path]

What This Command Does

  1. Removes invisible Unicode watermarks commonly embedded by AI systems
  2. Replaces em-dashes with contextually appropriate punctuation
  3. Cleans up whitespace and formatting artifacts
  4. Makes content appear naturally human-written
  5. Provides statistics on changes made

Why This Matters

AI language models often embed invisible Unicode characters as watermarks or identifiers in generated content. Additionally, AI tends to overuse certain punctuation patterns like em-dashes. This command removes these telltale signs to make content appear more naturally written.

Process

1. Watermark Detection & Removal

The scrubber identifies and removes several types of invisible Unicode characters:

Invisible Characters Removed
  • Zero-width spaces (U+200B): Often inserted between words
  • Byte Order Marks (U+FEFF): BOM characters that shouldn't appear in content
  • Zero-width non-joiners (U+200C): Invisible formatting characters
  • Word joiners (U+2060): Non-breaking invisible characters
  • Soft hyphens (U+00AD): Optional hyphenation points
  • Narrow no-break spaces (U+202F): Special spacing characters
  • All format-control characters: Unicode category Cf characters

2. Em-Dash Replacement

AI-generated content tends to overuse em-dashes (—). The scrubber intelligently replaces them based on context:

Contextual Rules
  • Attribution: Replaces with comma when used for quotes or attribution

    • Example: "Text — Author Name" becomes "Text, Author Name"
  • Independent Clauses: Replaces with semicolon when joining complete thoughts

    • Example: "First clause — second clause" becomes "First clause; second clause"
  • Strong Breaks: Replaces with period when separating distinct sentences

    • Example: "Sentence one — Sentence two" becomes "Sentence one. Sentence two"

Read the full file on GitHub · 157 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 · 157 lines · 0 tokens per session scan C 859b30964a52

Subscribe to this mod's changes

scrub is a command published in the GitHub repository seite-sh/seite (19 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,237 tokens. A static security scan graded it C with 1 finding (hidden instructions). It is 100% identical to scrub, differing in 0 lines, and is treated as a copy.