A local detector for AI-writing patterns. It scores the first 256 KB of extracted prose in files saved through supported file-edit tools, and asks for the flagged spans to be fixed. Plain text is accepted up to 512 KB, supported archives up to 4 MB. Python standard library only, no network, no model. Prose only, never code.
Install · What it does · Measured · Limits · Patterns · Ethics
[!IMPORTANT] This is a command-line tool and an agent plugin. There is no website and no hosted version. Nothing you write is uploaded, there is no account, and no text ever leaves your machine. Any site offering a service under this name is unrelated to this project.
Install
Paste into Claude Code, Codex, Cursor, or any coding agent:
Install the sloptrim plugin from https://github.com/seyedehsanhadi/sloptrim
Restart, then run /sloptrim doctor. It answers with four [OK] lines.
Explicit commands, and installing without the marketplace
/plugin marketplace add seyedehsanhadi/sloptrim
/plugin install sloptrim@sloptrim
git clone https://github.com/seyedehsanhadi/sloptrim.git ~/.claude/skills/sloptrim
mkdir -p ~/.claude/commands
cp ~/.claude/skills/sloptrim/install/sloptrim-command.md ~/.claude/commands/sloptrim.md
Do not skip the mkdir. On a fresh machine ~/.claude/commands does not exist yet
and the copy fails with "No such file or directory". In PowerShell the last two lines
are New-Item -ItemType Directory -Force $HOME/.claude/commands and Copy-Item.
The copy puts /sloptrim in the / menu, because Claude Code does not scan a skill
folder's own commands/. A marketplace install needs no such step. Either way the
router also answers to /sloptrim:sloptrim.
What it does
The score is 0-100 against 71 documented patterns. 62 of them have a detector; the other 9 need a reading and are worked during the rewrite. Of the 62, 50 can move the score and 12 are reported as writing advice and count for nothing: most of them because measurement showed they mark formal register rather than machine authorship, the rest because they are typographic habits.
| Formats | 20, including .docx, .pptx, .xlsx, OpenDocument, .epub, .ipynb, LaTeX; the first 256 KB of extracted prose is scored |
| Runs in | Claude Code, on save. Other agents via /sloptrim init, which writes the contract to AGENTS.md, and .cursor/rules/ |
| Needs | Node for the hooks, Python 3.9 or newer for the detector, nothing else |
| Suite | 119 Python tests and 72 hook checks, green in CI on Linux, Windows and macOS, against Python 3.9 and 3.13 (macOS on 3.13) |
| Does not see | A file written by a Bash command, which reaches disk without passing Write or Edit |
| Command | Effect |
|---|---|
/sloptrim full | Contract + guard (default) |
/sloptrim strict | Flags at 20 instead of 40, and asks for a character scrub |
/sloptrim lite / off | Contract only / nothing |
/sloptrim check <file> | Score a file, name the tells, no rewrite |
/sloptrim init | Write the contract to ./AGENTS.md and a Cursor rule to ./.cursor/rules/ |
/sloptrim doctor | Diagnose the install |
python scripts/detect.py draft.docx # JSON: patterns, metrics, 0-100 score
A score lands in one of five bands: clean, light tells, mixed, heavy tells,
pervasive tells. The guard nudges above 40, or above 20 in strict mode.
Measured
Sloptrim's public matched benchmark uses five separate 30-human/30-machine arms
from the Human Detectors
release, pinned at commit afcf03d. Each arm is matched by prompt and scored
separately. AUC is a ranking measure, not accuracy at Sloptrim's guard threshold.
| machine arm | ROC-AUC | bootstrap 95% CI | default TPR / FPR |
|---|---|---|---|
| GPT-4o | 0.946 | 0.876–0.992 | 46.7% / 0% |
| Claude 3.5 Sonnet | 0.842 | 0.729–0.936 | 3.3% / 0% |
| o1-pro | 0.877 | 0.771–0.957 | 23.3% / 6.7% |
| paraphrased GPT-4o | 0.838 | 0.735–0.929 | 6.7% / 3.3% |
| humanized o1-pro | 0.762 | 0.648–0.871 | 0% / 3.3% |
Across these arms, Sloptrim achieved ROC-AUC 0.762–0.946. Confidence intervals use 10,000 paired prompt-cluster bootstrap resamples. The public result record pins the source hash; the harness refuses any other file. The benchmark texts are not redistributed here.
git clone https://github.com/jenna-russell/human_detectors.git
git -C human_detectors checkout afcf03d14d2da4a038d8d0fafa5ec779dd858181
python scripts/benchmark_frontier.py PATH_TO_HUMAN_DETECTORS_JSON
What it cannot do
It cannot prove whether a model wrote something. The public arms show that the score often ranks these machine samples above matched human samples. The threshold results show why that is not the same as a dependable yes/no classifier: sensitivity changes sharply with model, prompt, formatting and threshold.
It is not an authorship classifier and must not be used as one. A score says something about writing, never about a person. Read ETHICS.md.
License
Apache-2.0 (full text, NOTICE). Cite with CITATION.cff.