Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add GktuOktay/ai-skills --skill humanizergit clone --depth 1 https://github.com/GktuOktay/ai-skillsWrote 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/gktuoktay/ai-skills/humanizer)<a href="https://agentmods.dev/skills/gktuoktay/ai-skills/humanizer"><img src="https://agentmods.dev/badge/skills/gktuoktay/ai-skills/humanizer/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/gktuoktay/ai-skills/humanizer"><img src="https://agentmods.dev/badge/skills/gktuoktay/ai-skills/humanizer.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 | $0.00054 | $0.00692 |
| Opus 5 | $0.00027 | $0.00346 |
| Sonnet 5 | $0.00011 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
AI Text Humanizer 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 10d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Text Humanizer Guidelines
This skill provides techniques for modifying AI-generated text to make it sound natural, engaging, and genuinely human. AI often defaults to recognizable patterns and vocabulary that feel robotic or overly academic.
1. Avoid AI Tropes and Clichés
Language models tend to overuse certain dramatic or transitional words. Actively identify and replace them.
Words to Avoid (The "AI Blacklist"):
- Delve, dive into
- Tapestry, rich tapestry
- Testament to
- Landscape (e.g., "the digital landscape")
- Paradigm shift
- Unleash
- Embark on a journey
- "It is important to note that..."
- "In conclusion..."
Strategy: Rewrite the sentence to state the fact directly without the metaphorical fluff.
2. Write in Active Voice
Passive voice makes writing feel distant, formal, and confusing. Active voice is direct and energetic.
- Passive (AI default): The new feature was designed by our team to ensure user satisfaction is maximized.
- Active (Human): Our team designed the new feature to maximize user satisfaction.
- Rule: Subject + Verb + Object.
3. Vary Sentence Length and Structure
AI text often has a monotonous rhythm because it generates sentences of similar lengths. Human writing breathes; it has rhythm.
- Use short, punchy sentences for emphasis.
- Use longer, complex sentences to explain nuanced ideas.
- Example Rhythm: This is a short sentence. Here is another one. Then, just when you expect a third short sentence, you encounter a longer, more elaborate structure that connects multiple ideas together seamlessly. It feels natural. It feels alive.
4. Adopt a Conversational Tone
Write as if you are explaining a concept to a smart colleague over coffee.
- Use Contractions: Use don't, can't, it's, you're instead of do not, cannot, it is, you are.
- Ask Rhetorical Questions: Engage the reader occasionally (e.g., Sound familiar?).
- Embrace Imperfections: Minor conversational transitions (like starting a sentence with 'And' or 'But') are perfectly fine and often preferred.
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.
- 10d ago First seen · 65 lines · 54 tokens per session scan A 55f805e7804d
AI Text Humanizer is a skill published in the GitHub repository GktuOktay/ai-skills (2 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 692 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
azure-resource-manager-mysql-dotnet
Azure MySQL Flexible Server SDK for .NET. Database management for MySQL Flexible Server deployments.
aws-security-audit
Comprehensive AWS security posture assessment using AWS CLI and security best practices.
azure-microsoft-playwright-testing-ts
Run Playwright tests at scale with cloud-hosted browsers and integrated Azure portal reporting.
gha-security-review
Find exploitable vulnerabilities in GitHub Actions workflows. Every finding MUST include a concrete exploitation scenario — if you can't build the attack, don't report it.
performance-optimizer
Identifies and fixes performance bottlenecks in code, databases, and APIs. Measures before and after to prove improvements.
azure-mgmt-apicenter-py
Azure API Center Management SDK for Python. Use for managing API inventory, metadata, and governance across your organization.