Borrowing it
Nothing to install: this file belongs to Dynokostya/just-works. 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/Dynokostya/just-works/main/.claude/skills/human-writing/SKILL.mdgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote 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/dynokostya/just-works/human-writing)<a href="https://agentmods.dev/skills/dynokostya/just-works/human-writing"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/human-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/dynokostya/just-works/human-writing"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/human-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 | $0.00136 | $0.05515 |
| Opus 5.5 | $0.00054 | $0.02206 |
| Sonnet 5.5 | $0.00027 | $0.01103 |
| Haiku 4.5 | $0.00014 | $0.00551 |
Grade A, and why
human-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 17d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human Writing
Readers call a text machine-written for two reasons, and they do not tell them apart. In documents that agents write, the larger reason is missing context: the writer worked from a plan, tickets, notes or data, and the text uses names, codes and shortcuts from that material as if the reader had seen it. The text also asks the reader to learn concepts, roles and details that the reader does not need. The smaller reason is habits of wording and structure, such as slogans, one formula in every section and contrasts against claims nobody made. Removing only the habits leaves a text that still assumes the writer's context. No pattern count measures whether a first-time reader can follow a text, so this skill starts with the reader and with what the document should contain.
Work in the mode the request asks for:
- Review: someone asks what is wrong with a text, or reports that a reader complained. The output is a findings report (see Review method).
- Rewrite: someone asks to fix, simplify or humanize an existing text (see Writing and rewriting).
- Write: you draft a new document for people outside your working context (see Writing and rewriting).
The source material is what the text draws on, such as notes, plans, data and the author's answers. The text under review is the existing text you review or rewrite. The author is the person who owns what the document says, often the person who asked you.
Files. Read references/reader-first.md before a full review or a rewrite of a long document. It holds more Bad and Good pairs for each rule, the review questions and the review techniques. Read references/machine-tells.md before the sentence pass of a review and before a rewrite. It holds the full catalog of tells, with what to keep for each.
Boundaries
- Project style rules and the project's existing voice override these defaults.
- Protected content keeps its wording: code, quotations, legal text, tables of data, file paths and identifiers. You may move it, or describe it for readers who cannot use it, but report problems inside it and leave them unedited.
- This skill is not an AI detector. The tells in it also appear in human writing, so do not claim that a person or a model wrote a text. Report what the reader experiences.
- Scope: explanatory and procedural prose. Fiction, marketing copy and social posts follow other conventions, and issue-tracker tickets have their own skill,
ticket-writing.
What ships with it
2 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.
- 17d ago Changed · -174 lines · -68 tokens per session 981c17086ebd
- 28d ago Changed · +82 lines · +18 tokens per session bb981b09977f
- 1mo ago First seen · 317 lines · 186 tokens per session scan A 0a39b7e0d27d
human-writing is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 136 tokens to every session and 5,515 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 2026-10-06.
human-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| human-writingDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 136 | 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 |