clearmode: an anti-AI-slop writing standard and plain-language checker
CLEAR-100 scores any text 0 to 100 against 43 rules, then names the line that loses the reader. Ban the words and you have fixed a third of the problem. clearmode checks the other two thirds: can an outsider follow it, and does it say anything.
The four axes
| Axis | What it asks | Weight |
|---|---|---|
| Plain | Can someone outside the field read it once and get it? | 30% |
| Human | Does it read like a person who did the work? | 30% |
| Structured | Does the shape of the page match the shape of the information? | 25% |
| Dense | Does every sentence carry something a reader could not guess? | 15% |
Bands: 90 and up ships, 80 to 89 is one pass short, 70 to 79 reads assisted, under 70 reads like a model wrote it.
Quickstart
git clone https://github.com/eugeniughelbur/clearmode.git
cd clearmode
python3 scripts/clearcheck.py tests/fixtures/bad.mdNo pip, no npm, no config. Python 3.10 and the standard library.
One rule pack, 18 targets
rules/clear-100.json is the single source of truth. Every target below is generated from it, so they never drift apart.
| Surface | File |
|---|---|
| Claude Code | SKILL.md plus references/ |
| Codex CLI | targets/codex/AGENTS.md |
| Cursor, Copilot, Gemini CLI, Aider, Windsurf, Zed | targets/agents-md-snippet.md |
| Cursor project rules | targets/cursor/clearmode.mdc |
| Grok, ChatGPT, any chat | targets/grok/custom-instructions.txt |
| Any API system prompt | targets/system-prompt.txt |
| Vale | targets/vale/ |
How it compares
Checked 2026-08-28. Anti-slop repos ban vocabulary. Vale ships an engine with no opinion. ASD-STE100 Simplified Technical English fixes ambiguity for trained technicians and bans contractions. clearmode is the only one that scores all four axes at once and ships identical rules to every agent you use.
FAQ
What is AI slop?
Low-quality AI-generated text. The 2026 arXiv paper that first defined the term found readers judge slop through latent dimensions like coherence and relevance, not through a word list alone. That is why clearmode scores density and structure, not just vocabulary.
How do I check if my text sounds AI-generated?
Run python3 scripts/clearcheck.py yourfile.md. Anything under 70 reads like a model wrote it. The report names the exact line and rule.
Is this an AI detector?
No. It measures readability, not authorship. A human can write a 41. A model can write a 95.
Does it work with ChatGPT, Cursor, Codex, or Grok?
Yes. The targets/ directory holds a prebuilt file for each. Copy one file, or run ./install.sh.
How is this different from an anti-slop word list?
A word list catches delve and stops. clearmode also asks whether a non-specialist can follow the sentence, whether the page has a shape, and whether the sentence says anything the reader could not guess.
Why not just use ASD-STE100?
Simplified Technical English solved ambiguity for aerospace manuals in 1986 and still works. It also bans contractions and reads robotic, has no concept of AI slop, and assumes a trained technician as the reader.
What reading grade should I aim for?
Grade 9 or lower for a general audience, 11 for technical docs, 8 for social. The profiles set this for you.
Can I turn a rule off?
Yes. Edit rules/clear-100.json, then run python3 scripts/compile_targets.py. Never hand-edit a generated target.
Does it run offline?
Yes. Python 3.10 and the standard library. No API key, no network call, no telemetry.