PTENES
Text linter · cleaning with a rival model

AI text a person would publish

Scores your text from 0 to 5, flags every machine-written pattern, and can fail the build. Then a model from another family cleans the draft.

Illustration of SlopMonster, a monster that hunts AI text
What it is

An honest scorer and a cleaner that doesn't proofread its own work

AI text has a telltale smell: delve, seamless, unlock, "it's not just a tool, it's a journey". Readers notice and stop trusting you. SlopMonster adds two things the other tools skip.

📏 Score from 0 to 5, no opinions

Five groups of patterns, one point each. Below 5/5, the command exits with an error, so it works as a CI gate. Developers call this a linter.

🔁 Rival model does the cleanup

If Claude wrote it, GPT cleans it up. If GPT wrote it, Claude cleans it up. A model can’t hear its own accent. The script refuses to send the draft back to the same model family.

🧾 Never invents evidence

No “10,000 happy customers” when the business doesn’t have them. Any number next to a word for people gets flagged. If the number is real, --allow-proof becomes a warning.

How it works

The four-step cycle

The scorer gets the first and last word, because the scorer is honest and the model is persuasive. “Almost clean” is how a page ends up sounding just like every other AI page on the internet.

1 · Score (deslop.py)→ 2 · Rewrite in 3 passes→ 3 · Clean with a rival model (cleanse.sh)→ 4 · Rescore; only publish at 5/5

Pass 1 · vocabulary

Kills delve, seamless, robust, unlock, elevate, leverage. Replace it with a simpler word, not a fancy synonym.

Pass 2 · patterns

Kills not just X, but Y, reflexive lists of three, stacks of em dashes, piled-on caveats, and the closing summary nobody asked for.

Pass 3 · bring a person back in

One specific number per claim. Sentences of very different lengths. One edge case: a contraction, a fragment, a sentence starting with "And".

The 5 rules

What the scorer hunts for

It matches one group and loses a point. Four groups strip away the AI accent. The fifth asks whether the line is selling anything.

1

AI vocabulary

Two lists. The first matches by root: elevate gets elevates e elevating. The second matches word for word, so it won't flag "we craft furniture by hand".

2

AI constructions

17 sentence patterns, not words. not just X, but Y, say goodbye to, that's where X comes in, and questions the author answers themselves.

3

Punctuation cadence

Two em dashes within a 220-character window. Semicolons only above a threshold proportional to the page size.

4

Rule of three

faster, smarter, and better. Intentionally narrow: it only triggers on three loose words with an Oxford comma, or on a short sentence closing the clause.

5

Sales and fabricated evidence

A number next to a word for people, like 10,000+ happy users. Intentionally easy to trigger: a false alarm costs ten seconds; an error leaves a lie on your site.

!

English only

The catalog is English-only. Portuguese text gets 5/5 because the scorer can’t read the language, not because it’s clean. Model-based cleanup works in any language.

Prerequisites

Python and, if you want cleanup, an AI CLI

The scorer is pure Python, uses the standard library, and has no dependencies. Cleanup uses the CLI codex or claude. Without either one, the script prints the prompt for you to paste into a chat.

Python 3

Any recent version 3. The project CI runs on 3.11.

# check the version
python3 --version

Clone the repo

No installation. The scripts run directly from the folder.

git clone https://github.com/inematds/SlopMonster
cd SlopMonster

Rival CLI (optional)

For automatic cleanup: codex if you write with Claude, claude is written with GPT.

# one of the two, depending on the draft family
which codex claude
Usage guide · step by step

From draft to 5/5

All commands are real and run from the repo root. The step 1 example intentionally scores 3/5.

1

Score a passage

Pass the text directly. The scorer names each flag and exits with code 1 when it scores below 5.

python3 tools/deslop.py --text "It's not just a tool, it's a game-changing journey."
# → score 3/5, flags both patterns, exit 1
2

Score a page or a Markdown file

In HTML, it reads only what visitors can see. In markdown, it skips code spans, fenced blocks, and strikethrough text, because literal text isn't sales copy.

python3 tools/deslop.py index.html
python3 tools/deslop.py index.html --view hero   # one element by id
python3 tools/deslop.py README.md
3

Clean with a rival model

The cleaned text goes to stdout, and notes about what changed go to stderr. Read the notes: sometimes the model deletes your closing line and only mentions it there.

tools/cleanse.sh rascunho.md > limpo.md 2> notas.txt
# writing with GPT? make Claude the cleaner:
DESLOP_WRITER=gpt tools/cleanse.sh rascunho.md > limpo.md
4

Always rescore

A cutting-edge model is great at removing markers and quite capable of adding new ones while it does so. Cleanup without re-scoring is a coin toss.

python3 tools/deslop.py --text "$(cat limpo.md)"
# only publish at 5/5
5

Real numbers? Clear the evidence rule

If the number is true and you can prove it, rule 5 becomes a warning and still prints the matches for you to review.

python3 tools/deslop.py index.html --allow-proof
6

Fail the build in CI

The repo workflow runs the tests and scores the published text on every push. Copy it to your repo and point it to the file with your text.

cp .github/workflows/slop.yml <seu-repo>/.github/workflows/
# in the yml, replace examples/gate-sample.txt with your file
python3 tools/deslop.py --text "$(cat examples/gate-sample.txt)"
7

Use as a skill in Claude Code

Copy the folder into skills and call it. The SKILL.md it's pure markdown, so it works for Codex and other agents too.

cp -r SlopMonster ~/.claude/skills/slopmonster/
# in Claude Code: /slopmonster, "remove the slop from this", "does this sound like AI?"
8

Changed a regex? Run the regression suite

The catalog matches word roots, and a bad stemming shortcut leaves the scorer quietly half-blind. The test suite catches that.

python3 tools/test_deslop.py
bash tools/test_cleanse.sh
Examples

A real before and after

Real lines from the Ridgeline Roofing site and an unedited pass on the Jasper.ai homepage, which went from 3/5 to 5/5 in one pass, with the meaning intact and nothing invented. Full records at examples/ no repo.

Rule 1, AI vocabulary
We leverage industry-leading materials to deliver unparalleled protection.
We source materials from manufacturers who test for wind, hail and sun.
Rule 2, AI constructions
Not just a roof, but peace of mind.
A written scope and a fixed number before anyone climbs a ladder.
Rule 5, fabricated evidence
Loved by 10,000+ happy homeowners.
Roofing, and only roofing, since 2001. A date can't be argued with.
The five SlopMonster mascots, one for each rule
The five mascots, one for each rule. The repo README passes the scorer itself with 5/5.