deslop

deslop is a command for Claude Code from Abdulkader-Safi/AI-Writing-Rules. It costs 11 tokens per session (362 once invoked), scanned A, original, MIT.

A command for rewriting text so it sounds like it was written by a clear, direct person rather than generated by AI. It can work on a file or on the most recent text in the conversation.

In plain words
What is it for?
Use it to polish documentation, reports, messages, or other prose, with an optional checker that flags common writing problems before and after the rewrite.
Why use it?
It helps find and remove unnecessary wording, repetitive sentence patterns, and other signs of artificial writing while preserving factual content.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ai-writing-rules plugin — 1 skill, 1 command, 2 hooks shipped together

Good fit Use it to polish documentation, reports, messages, or other prose, with an optional checker that flags common writing problems before and after the rewrite.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Abdulkader-Safi/AI-Writing-Rules
Claude Code
/plugin install ai-writing-rules

Made for: Claude Code.

Or install ai-writing-rules, the plugin that ships this one along with the rest of its 1 skill, 1 command, 2 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 deslop

README.md
[![agentmods](https://agentmods.dev/badge/commands/abdulkader-safi/ai-writing-rules/deslop/github.svg)](https://agentmods.dev/commands/abdulkader-safi/ai-writing-rules/deslop)
Your own site
<a href="https://agentmods.dev/commands/abdulkader-safi/ai-writing-rules/deslop"><img src="https://agentmods.dev/badge/commands/abdulkader-safi/ai-writing-rules/deslop/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 deslop

Your own site · 80×15
<a href="https://agentmods.dev/commands/abdulkader-safi/ai-writing-rules/deslop"><img src="https://agentmods.dev/badge/commands/abdulkader-safi/ai-writing-rules/deslop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 362 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 $0.00011 $0.00362
Opus 5 $0.00005 $0.00181
Sonnet 5 $0.00002 $0.00072
Haiku 4.5 $0.00001 $0.00036

Measured 9d ago against content hash c7a2644a156c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deslop 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 9d 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.

commands/deslop.md · 28 lines

What it actually says

Rewrite $1 so it reads like a sharp, plain-spoken human wrote it.

If no path was given, use the most recent text you produced in this conversation.

Steps:

  1. Read the target. If it is a file, run the checker on it first: echo '{"tool_input":{"file_path":"TARGET"}}' | python3 "${CLAUDE_PLUGIN_ROOT}/scripts/slop-check.py"

  2. Read ${CLAUDE_PLUGIN_ROOT}/skills/anti-ai-writing/SKILL.md if it is not already in context. Open the specific files in ${CLAUDE_PLUGIN_ROOT}/research/ for any pattern the checker flagged that you are unsure how to fix.

  3. Beyond what the checker catches by regex, judge these by reading:

    • The deletion test. Remove each sentence in turn. If the paragraph loses nothing, the sentence goes.
    • Sentence rhythm. If every sentence is 18 to 24 words, break it up.
    • Elegant variation. If one thing has three names, pick one.
    • Register. Does a one-line answer arrive as five paragraphs?
  4. Rewrite. Preserve every fact, number, name, link, and code block exactly. Change only how it reads. Do not invent facts to replace vague claims: if a claim has nothing behind it, cut the claim.

  5. Apply the edit to the file, then re-run the checker to confirm it comes back clean.

  6. Report in three lines or fewer: what you cut, what you rewrote, and anything you left because fixing it needed a fact you do not have.

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. 9d ago First seen · 28 lines · 11 tokens per session scan A c7a2644a156c

Subscribe to this mod's changes

deslop is a command published in the GitHub repository Abdulkader-Safi/AI-Writing-Rules (27 stars, last pushed 20d ago), licensed MIT. It adds 11 tokens to every session and 362 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 2026-08-30.