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 betahope/cofounder-team --skill humanizergit clone --depth 1 https://github.com/betahope/cofounder-teamWrote 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/betahope/cofounder-team/humanizer)<a href="https://agentmods.dev/skills/betahope/cofounder-team/humanizer"><img src="https://agentmods.dev/badge/skills/betahope/cofounder-team/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/betahope/cofounder-team/humanizer"><img src="https://agentmods.dev/badge/skills/betahope/cofounder-team/humanizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00199 | $0.02637 |
| Opus 5.5 | $0.00080 | $0.01055 |
| Sonnet 5.5 | $0.00040 | $0.00527 |
| Haiku 4.5 | $0.00020 | $0.00264 |
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 28d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer
Takes AI-sounding writing and makes it sound like a person wrote it. Grounded in Wikipedia's Signs of AI writing guide, maintained by WikiProject AI Cleanup.
Key insight from that page: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases." That's why AI writing feels smoothed-over and genericized: the model is producing the statistical average of what a sentence looks like. Humanizing means putting specificity, rhythm, and a point of view back in.
How this skill is organized
The pattern catalog is not ours. It comes from blader/humanizer, MIT licensed, and is vendored here unchanged so it stays current without anyone re-typing it.
- This file: the workflow, the language rule, output sizing, and the voice guidance.
references/upstream-patterns.md: the full pattern catalog, straight from upstream. Every pattern has a words-to-watch list, the underlying problem, a before/after example, and notes on what not to flag.references/voice-calibration.md: how to match a user's writing sample.references/example.md: a long-form before/after at full-essay scale.
Read references/upstream-patterns.md on every real humanizing pass. It is the
authority on which patterns exist and how to fix each one. This file is the authority
on workflow, output length, language scope, and voice. Where the two disagree, this
file wins.
The patterns group into six families: staging (signalling importance instead of stating a fact), rhythm by rule (triads and dashes everywhere), inflation and borrowed authority, formatting by rule, leftovers from the chat and the draft, and writing for the wrong reader (re-explaining what the reader already knows). Deliberately no numbered index here: upstream adds and renumbers patterns, and a second list would drift out of sync with the first.
What ships with it
3 files 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.
- 28d ago Changed · +3 lines · +5 tokens per session afae29e998e7
- 2mo ago First seen · 211 lines · 194 tokens per session scan A 46f2ed3ae10c
humanizer is a skill published in the GitHub repository betahope/cofounder-team (42 stars, last pushed 11d ago), licensed MIT. It adds 199 tokens to every session and 2,637 once invoked, about $0.0008 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 2026-08-30.
humanizer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| humanizerbetahope/cofounder-team | Skill | 42 | 11d ago | MIT | A | 199 | 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 |