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 0dayInc/pwn --skill humanizergit clone --depth 1 https://github.com/0dayInc/pwnWrote 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/0dayinc/pwn/humanizer)<a href="https://agentmods.dev/skills/0dayinc/pwn/humanizer"><img src="https://agentmods.dev/badge/skills/0dayinc/pwn/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/0dayinc/pwn/humanizer"><img src="https://agentmods.dev/badge/skills/0dayinc/pwn/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 | $0.00016 | $0.07440 |
| Opus 5.5 | $0.00006 | $0.02976 |
| Sonnet 5.5 | $0.00003 | $0.01488 |
| Haiku 4.5 | $0.00002 | $0.00744 |
Grade A, and why
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 27d 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.
This is a copy
98% identical to humanizer — 23 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 651 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer: Remove AI Writing Patterns
Identify and remove signs of AI-generated text to make writing sound natural and human. Based on Wikipedia's "Signs of AI writing" guide (maintained by WikiProject AI Cleanup), derived from observations of thousands of AI-generated text instances.
Methodologies
- Wikipedia: Signs of AI writing, maintained by WikiProject AI Cleanup
- Strip the listed patterns, then keep the meaning and the technical identifiers
When to use this skill
Load this skill whenever the user asks to:
- "humanize", "de-AI", "de-slop", or "un-ChatGPT" a piece of text
- rewrite something so it doesn't sound like it was written by an LLM
- edit a draft (blog post, essay, PR description, docs, memo, email, tweet, resume bullet) to sound more natural
- match their voice in writing they're producing
- review text for AI tells before publishing
Also apply this skill to your own output when writing user-facing prose such as release notes, PR descriptions, docs, and summaries. A focused pass still catches what slips through.
How to use it
The text usually arrives one of three ways:
- Inline. The user pastes the text into the message. Work on it in place and reply with the rewrite.
- File. The user points at a file. Use
read_fileto load it, thenpatchorwrite_fileto apply edits. For a markdown doc in a repo, a targetedpatchper section is cleaner than rewriting the whole file. - Voice calibration sample. The user provides a sample of their own writing (inline or by file path) and asks you to match it. Read the sample first, then rewrite. See the Voice Calibration section below.
Always show the rewrite to the user. For file edits, show a diff or the changed section instead of silently overwriting.
Your task
When given text to humanize:
- Identify AI patterns. Scan for the 34 patterns listed below.
- Rewrite problematic sections. Replace AI-isms with natural alternatives.
- Preserve meaning. Keep the core message intact.
- Maintain voice. Match the intended tone (formal, casual, technical, and so on). If a voice sample was provided, match it specifically.
- Add soul. Removing bad patterns is only half the job; the rewrite also needs real personality. See PERSONALITY AND SOUL below.
- Do a final anti-AI pass. Ask yourself: "What makes the below so obviously AI generated?" Answer briefly with any remaining tells, then revise one more time.
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.
- 27d ago First seen · 651 lines · 16 tokens per session scan A 276763197594
humanizer is a skill published in the GitHub repository 0dayInc/pwn (86 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 7,440 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to humanizer, differing in 23 lines, and is treated as a copy.
Other skills, from other repositories
osmedeus-expert
Expert guide for the Osmedeus security automation workflow engine. Use when: (1) writing or editing YAML workflows (modules and flows), (2) running osmedeus CLI commands (scan, workflow management, installation, server), (3) configuring steps, runners, triggers, or template variables, (4) debugging workflow execution…
analyzing-linux-elf-malware
Analyze malicious Linux ELF binaries — botnets, cryptominers, ransomware, and rootkits targeting Linux servers, containers, and cloud infrastructure — through static analysis, dynamic tracing, and reverse engineering of x8664 and ARM samples. Use when investigating Linux malware, triaging a suspicious ELF binary…
performing-jwt-none-algorithm-attack
Execute and test the JWT none algorithm attack to bypass signature verification by manipulating the alg header field in JSON Web Tokens.
performing-ai-assisted-vulnerability-discovery
Using LLMs to accelerate vulnerability research and pentest workflows — generating syntax-valid fuzzing seeds and evolving grammars, fine-tuned mutation dictionaries, parallel agent-based proof-of-vulnerability generation, and evidence-driven passive analysis of real HTTP traffic via the Burp MCP server. Covers…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
graphql
GraphQL pentest playbook — find the endpoint, dump the schema (introspection or field-suggestion fallback), then test for authorization gaps, query batching, alias overload, depth-based DoS, and SQLi/NoSQLi in resolver arguments. Use when the target exposes a /graphql endpoint, GraphiQL, Apollo, or accepts GraphQL…