Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. 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/greenmtnsun/GitEasy/main/.claude/skills/humanized-writing/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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/greenmtnsun/giteasy/humanized-writing)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/humanized-writing"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/humanized-writing/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/greenmtnsun/giteasy/humanized-writing"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/humanized-writing.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 | $0.00119 | $0.01139 |
| Opus 5.5 | $0.00048 | $0.00456 |
| Sonnet 5.5 | $0.00024 | $0.00228 |
| Haiku 4.5 | $0.00012 | $0.00114 |
Grade A, and why
humanized-writing 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 today.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanized writing — two-pass pipeline
Origin: the 2026-08-01 DetentShell incident — a 24-post blog series written trying to sound human still read as "obviously AI generated" (Keith's words, and he was right). Good intent does not prevent the tells; only explicit rules checked against the text do. The rules below distill the tooling consensus (all of it derives from Wikipedia's "Signs of AI writing" catalog — there is no competing school to arbitrate).
The standing register rule ("let your yes be yes") lives in global CLAUDE.md §10 — that paragraph is its one home. This skill applies it; it does not restate it.
Pass 1 — write under these rules
Hard bans:
- Negative parallelism: "not just X, but Y" / "That's not A. That's B."
- Rule-of-three lists built for rhythm rather than because there are three things.
- More than one em dash per paragraph.
- Engineered aphorism endings — the kicker/mic-drop closer ("We ship questions."). End when the information ends.
- Bold lead-ins on list items ("Name. Text…").
- Fancy copulas ("serves as", "boasts", "stands as") where is/has works.
- Fake-significance vocabulary: pivotal, testament, underscores, crucial.
- The AI wordlist: delve, tapestry, landscape, leverage, robust, vibrant, showcase, foster, intricate, meticulous, seamless, elevate, empower, unlock, journey.
- Trailing present-participle commentary ("…, highlighting the importance of X").
- Meta/collaborative talk: "Here's the thing", "worth noting", "let's", rhetorical-question openers.
- Vague attribution ("experts agree", "many developers find").
- Elegant variation — synonym-cycling to avoid repeating a word. Repeating a word is human.
- Honesty narration and certifying flourishes — see CLAUDE.md §10 (yes-be-yes).
Requirements:
- Sentence-case titles, varied in form and length across a series. Uniformly clever titles are themselves a tell — that is specifically what Keith caught.
- Varied sentence and paragraph rhythm; fragments and contractions allowed.
- Specifics over adjectives: numbers, filenames, exact strings.
- Facts only — no invented users, anecdotes, or composite stories (pairs with
editorial-stanceandhonest-completion; reference them, don't duplicate).
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.
- today First seen · 84 lines · 119 tokens per session scan A ec69f660baec
humanized-writing is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 119 tokens to every session and 1,139 once invoked, about $0.0005 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 2026-11-18.
humanized-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| humanized-writinggreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 119 | Claude Code |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | today | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |