ai-slop-detector

ai-slop-detector is a skill for Claude Code, Codex from nicepkg/ai-workflow. It costs 54 tokens per session (2,428 once invoked), scanned A, original, MIT.

A text-cleaning tool that rewrites drafts to remove common signs of AI-generated writing. It returns the revised text without an explanation.

In plain words
What is it for?
Use it to polish newsletters, articles, social posts, or other drafts. It can also clean text produced by another writing workflow.
Why use it?
It helps when writing sounds generic, overly polished, or unlike a person. It provides a final cleanup step before sharing AI-assisted text.

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/nicepkg/ai-workflow/ai-slop-detector
Any agent
npx skills add nicepkg/ai-workflow --skill ai-slop-detector
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

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 ai-slop-detector

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicepkg/ai-workflow/ai-slop-detector.svg)](https://agentmods.dev/skills/nicepkg/ai-workflow/ai-slop-detector)
Your own site
<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/ai-slop-detector"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/ai-slop-detector.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,428 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 $0.00054 $0.02428
Opus 5 $0.00027 $0.01214
Sonnet 5 $0.00011 $0.00486
Haiku 4.5 $0.00005 $0.00243

Measured 5d ago against content hash 621c1c107ffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-slop-detector 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 5d 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.

workflows/content-creator-workflow/.claude/skills/ai-slop-detector/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Slop Detector

What This Does

Takes any text and rewrites it to remove common AI writing patterns, making it sound authentically human. Returns only the cleaned final version.

When to Use

  • After generating any AI-assisted content
  • Before publishing newsletters, articles, or social posts
  • When text feels "too polished" or generic
  • As a final quality gate in any writing workflow

Instructions

Execute these steps NOW on the text provided:

  1. Scan the text for patterns listed below
  2. Rewrite each flagged section using the suggested fixes
  3. Output the cleaned text immediately - no preamble, no explanation

The input text is everything that preceded this skill's invocation. Process it now.


When Called by Another Skill

This skill is often invoked at the end of other skills (magic-model-review, bb-coaching-response, newsletter-coach, etc.).

When invoked mid-workflow:

  1. The text to clean is the draft just generated
  2. Process it immediately
  3. Return the cleaned version for the calling skill to present

LANGUAGE AND TONE PATTERNS TO ELIMINATE

Promotional/Puffery Phrases

Remove these entirely or replace with specific facts:

  • "stands as / serves as / is a testament"
  • "plays a vital/significant role"
  • "continues to captivate"
  • "leaves a lasting impact"
  • "rich cultural heritage/tapestry"
  • "nestled in the heart of"
  • "breathtaking," "must-visit," "stunning natural beauty"
  • "enduring/lasting legacy"

Fix: Use specific, factual descriptions

  • BAD: "The museum stands as a testament to the city's rich cultural heritage"
  • GOOD: "The museum houses 3,000 artifacts spanning four centuries of local history"

Editorializing Phrases

Remove these - present facts directly:

  • "it's important to note/remember/consider"
  • "it is worth noting"
  • "no discussion would be complete without"
  • "this article wouldn't exist without"

Fix: Just state the thing

  • BAD: "It's important to note that the company expanded rapidly"
  • GOOD: "The company opened 15 new locations between 2020-2023"

Read the full file on GitHub · 283 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 283 lines · 54 tokens per session scan A 621c1c107ffd

Subscribe to this mod's changes

ai-slop-detector is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 54 tokens to every session and 2,428 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 2026-08-30.