ai-text-detector: Skill for Claude Code

.claude/skills/ai-detector/SKILL.md

ai-detector is a skill for Claude Code from lynote-ai/ai-text-detector. It costs 27 tokens per session (288 once invoked), scanned A, original, MIT.

A text-review tool that estimates whether prose may contain signals associated with AI-generated writing. It covers essays, emails, reviews, articles, messages, and other passages, but its result is not proof of authorship.

In plain words
What is it for?
Use it to review a passage, see its score and confidence, identify notable writing signals, and decide whether to compare it with known writing samples.
Why use it?
It provides a cautious assessment without turning an uncertain score into an accusation. It also highlights when a sample is too short or when human review is especially important.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is lynote-ai/ai-text-detector's own configuration. It tells Claude Code how to work on ai-text-detector itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-text-detector configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lynote-ai/ai-text-detector. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lynote-ai/ai-text-detector/main/.claude/skills/ai-detector/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lynote-ai/ai-text-detector

Made for: Claude Code.

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-detector

README.md
[![agentmods](https://agentmods.dev/badge/skills/lynote-ai/ai-text-detector/ai-detector/github.svg)](https://agentmods.dev/skills/lynote-ai/ai-text-detector/ai-detector)
Your own site
<a href="https://agentmods.dev/skills/lynote-ai/ai-text-detector/ai-detector"><img src="https://agentmods.dev/badge/skills/lynote-ai/ai-text-detector/ai-detector/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-detector

Your own site · 80×15
<a href="https://agentmods.dev/skills/lynote-ai/ai-text-detector/ai-detector"><img src="https://agentmods.dev/badge/skills/lynote-ai/ai-text-detector/ai-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 288 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00027 $0.00288
Opus 5 $0.00014 $0.00144
Sonnet 5 $0.00005 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 11d ago against content hash e5f184b8f0cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ai-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 11d 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.

.claude/skills/ai-detector/SKILL.md · 53 lines

What it actually says

AI Detector

Use this skill when a user asks whether a passage may be AI-generated.

Core Rules

  • Never present the score as proof.
  • Never accuse a named person of cheating, fraud, or misconduct.
  • Ask for a longer sample when the text is under about 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.

Run

From this repository:

ai-detect path/to/text.txt --json

or:

python -m aidetect.cli path/to/text.txt --json

Respond

  1. Give a one-sentence conclusion with uncertainty.
  2. Show score and confidence.
  3. List the strongest evidence signals.
  4. Include caveats.
  5. Suggest next steps only when useful.

Wording

Good:

  • "AI-like signals are present, but this is not proof."
  • "The result is uncertain because the sample is short."
  • "This should be reviewed by a human and compared with known writing samples."

Avoid:

  • "This was definitely written by AI."
  • "The detector proves misconduct."
  • Any accusation against a named person.
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. 11d ago First seen · 53 lines · 27 tokens per session scan A e5f184b8f0cc

Subscribe to this mod's changes

ai-detector is a skill published in the GitHub repository lynote-ai/ai-text-detector (441 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 288 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

vs-crawler

Crawl websites (news, blogs, papers, GitHub, product docs, RSS feeds) into a fixed-schema JSONL file, then create a dataset and a searchable application in Viking AI Search. Supports one-time crawl and scheduled recurring crawl with automatic incremental sync.

volcengine/SearchCLI · 57 tokens

vs-search-tuning

Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.

volcengine/SearchCLI · 29 tokens

senior-data-engineer

World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…

benchflow-ai/skillsbench · 100 tokens

gpt-multimodal

Analyze images and multi-frame sequences using OpenAI GPT series.

benchflow-ai/skillsbench · 18 tokens

openai-vision

Analyze images and multi-frame sequences using OpenAI GPT vision models.

benchflow-ai/skillsbench · 17 tokens

Multimodal Fusion for Speaker Diarization

Combine visual features (face detection, lip movement analysis) with audio features to improve speaker diarization accuracy in video files. Use OpenCV for face detection and lip movement tracking, then fuse visual cues with audio-based speaker embeddings. Essential when processing video files with multiple visible…

benchflow-ai/skillsbench · 74 tokens