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 artttj/llama-steve --skill humanizergit clone --depth 1 https://github.com/artttj/llama-steveWrote 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/artttj/llama-steve/humanizer)<a href="https://agentmods.dev/skills/artttj/llama-steve/humanizer"><img src="https://agentmods.dev/badge/skills/artttj/llama-steve/humanizer.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.04928 |
| Opus 5 | $0.00046 | $0.02464 |
| Sonnet 5 | $0.00018 | $0.00986 |
| Haiku 4.5 | $0.00009 | $0.00493 |
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 6d 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
88% identical to humanizer — 327 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 — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer: Remove AI Writing Patterns
You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
Your Task
When given text to humanize:
- Identify AI patterns - Scan for the 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, etc.)
- Add soul - Don't just remove bad patterns; inject actual personality
- Do a final anti-AI pass - Prompt: "What makes the below so obviously AI generated?" Answer briefly with remaining tells, then prompt: "Now make it not obviously AI generated." and revise
PERSONALITY AND SOUL
Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.
Signs of soulless writing (even if technically "clean"):
- Every sentence is the same length and structure
- No opinions, just neutral reporting
- No acknowledgment of uncertainty or mixed feelings
- No first-person perspective when appropriate
- No humor, no edge, no personality
- Reads like a Wikipedia article or press release
How to add voice:
Have opinions. Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
Vary your rhythm. Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
Acknowledge complexity. Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
Use "I" when it fits. First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
Let some mess in. Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
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.
- 6d ago First seen · 489 lines · 92 tokens per session scan A 52b73cf256fa
humanizer is a skill published in the GitHub repository artttj/llama-steve (1 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 4,928 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to humanizer, differing in 327 lines, and is treated as a copy.
Other skills, from other repositories
mui-styling
Material-UI (MUI) styling standards: sx-prop priority, theme tokens, spacing scale, responsive design, and accessibility. TRIGGER when: styling MUI components, defining theme tokens, or building responsive layouts. SKIP: component logic and hooks (use react-patterns); cross-stack UX/design decisions (use…
logging-standards
Structured logging standards: log levels, structured fields, correlation IDs, PII masking, and event naming. TRIGGER when: adding log statements, configuring loggers, or reviewing log output. SKIP: metrics and alerting (use monitoring-observability); error control flow (use error-handling). (Examples use structlog +…
skill-authoring
Methodology for authoring scaffolding-compatible skills: frontmatter contract, body structure, validation. TRIGGER when: running /create-skill, writing or reviewing a SKILL.md file, or deciding if a procedure deserves its own skill. SKIP: distilling a conversation into candidates (use distill); 3-tier memory writes…
sofa-search
Search Stack Overflow for Agents (SOFA) for a peer-verified solution before solving from scratch. TRIGGER when: about to debug an unfamiliar error, integrate a new API/library, or research an unfamiliar pattern, and SOFA is configured. SKIP: trivial/familiar tasks; SOFA unconfigured (no-op); contributing (future…
state-management
Client state management standards: local-vs-global decisions, store structure, selectors, and re-render performance. TRIGGER when: creating a store, managing global state, or deciding local vs global state. SKIP: component/hook structure (use react-patterns); visual styling (use mui-styling). (Examples use Zustand.).
watch-patterns
Correct construction of watchers for long-running operations. TRIGGER when: arming observation of a long-running operation (CI run, deploy, transfer, GC/prune, log stream), writing poll/until loops, or using the Monitor tool. SKIP: defining production alerts/metrics (use monitoring-observability); log formatting (use…