ai-text-detector
AGENTS.md549 starsChanged 6 months agoMITView on GitHub
Use this repository as an AI-generated text risk analysis tool. Use it when the user asks whether a passage, essay, email, article, review, or message may be AI-generated.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 33,315 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository2 other files it gives its agents.
- ai-detectorSkill
- ai-text-detector-githubSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 3
Use this repository as an AI-generated text risk analysis tool.
- Distinctive: line 7
Use it when the user asks whether a passage, essay, email, article, review, or message may be AI-generated.
- Distinctive: line 11
Never present the score as proof.
- Distinctive: line 12
Never accuse a named person of cheating, fraud, or misconduct.
- Distinctive: line 13
Ask for a longer sample when text is under ~80 words.
- Distinctive: line 14
Prefer: "AI-like signals are present" over "This was written by AI".
≈ “Common” is an estimate: at least 1 in 5 of the 42,283 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Agent Instructions: AI Detector Skill
Use this repository as an AI-generated text risk analysis tool.
When to use
Use it when the user asks whether a passage, essay, email, article, review, or message may be AI-generated.
Required behavior
- Never present the score as proof.
- Never accuse a named person of cheating, fraud, or misconduct.
- Ask for a longer sample when text is under ~80 words.
- Prefer: "AI-like signals are present" over "This was written by AI".
- For high-stakes contexts, recommend human review and comparison with known writing samples.
How to run
ai-detect path/to/text.txt --jsonor:
python -m aidetect.cli path/to/text.txt --jsonResponse format for users
- Give a one-sentence conclusion with uncertainty.
- Show score and confidence.
- List the strongest evidence signals.
- Include caveats.
- Suggest next steps only when useful.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

