Borrowing it
Nothing to install: this file belongs to Guo-Chenxu/paper-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Guo-Chenxu/paper-agent/main/.claude/skills/ai-detector/SKILL.mdgit clone --depth 1 https://github.com/Guo-Chenxu/paper-agentWrote 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.
[](https://agentmods.dev/skills/guo-chenxu/paper-agent/ai-detector)<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/ai-detector"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/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.
<a href="https://agentmods.dev/skills/guo-chenxu/paper-agent/ai-detector"><img src="https://agentmods.dev/badge/skills/guo-chenxu/paper-agent/ai-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00156 | $0.01625 |
| Opus 5.5 | $0.00062 | $0.00650 |
| Sonnet 5.5 | $0.00031 | $0.00325 |
| Haiku 4.5 | $0.00016 | $0.00162 |
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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Detector Skill
This skill analyzes text for AI-generated writing patterns and gives concrete suggestions to make it sound more human.
The goal isn't just to flag problems — it's to help the writer understand why certain passages feel robotic and how to fix them specifically.
Reference Material
Primary reference: references/ai_writing_patterns.md
Project writing-pattern reference: .claude/rules/writing-patterns.md
Source: https://www.aicheckr.io/blog/spotting-ai-writing-patterns
When analyzing academic text, read .claude/rules/writing-patterns.md before every analysis so reusable project-specific writing issues are included. For general AI-pattern checks, first try fetching the live URL above for the latest content. If unreachable, use the patterns documented below.
No single pattern definitively proves AI authorship. A cluster of these signals together is what matters.
Pattern 1: Overused "AI Vocabulary"
AI models repeatedly reach for the same elevated words:
- Verbs: delve, illuminate, underscore, leverage, navigate, foster, embark
- Adjectives: pivotal, nuanced, multifaceted, comprehensive, robust, seamless
- Nouns: landscape, realm, tapestry, synergy, paradigm
Human writers vary their word choice more naturally and use plainer language.
Fix: Replace with simpler, more direct synonyms; vary word choice across the document.
Pattern 2: Em Dash Overuse
AI strongly prefers em dashes (—) over semicolons, colons, or subordinate clauses. A paragraph with 3+ em dashes is a yellow flag.
Fix: Rewrite as subordinate clauses or split into two sentences.
Pattern 3: Uniform Sentence Structure
AI mixes sentence lengths in a mechanical way — short, medium, long, repeat — rather than letting rhythm emerge from meaning. Human prose has more irregular cadence.
Fix: Vary sentence length deliberately; add a very short sentence for punch.
Pattern 4: American English Spelling
AI defaults to American English (e.g., "analyze" not "analyse", "color" not "colour") regardless of the author's locale.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 189 lines · 156 tokens per session scan A 04ed23dc298f
ai-detector is a skill published in the GitHub repository Guo-Chenxu/paper-agent (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 156 tokens to every session and 1,625 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
ai-detector compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-detectorGuo-Chenxu/paper-agent | Skill | 4 | 2d ago | Apache-2.0 | A | 156 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |