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 agentmods add instructions/blader/humanizer/agents-mdgit clone --depth 1 https://github.com/blader/humanizerWhat 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 | $0.00541 | $0.00541 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
humanizer AGENTS.md 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 yesterday.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guide for agents
This file explains how to change Humanizer without breaking its package or prompt.
What this repo contains
Humanizer is an agent skill written in Markdown. SKILL.md is the prompt that agents read. The repo has no build step.
Keep the skill portable. Do not write instructions that limit it to one or two agent tools.
Key files
SKILL.mdis the source of truth and the repo's only skill file. It contains portable YAML metadata, 35 numbered patterns, and their examples.README.mdexplains installation, use, patterns, and version history..claude-plugin/plugin.jsondescribes the Claude plugin and points its skill loader at the rootSKILL.md..claude-plugin/marketplace.jsonlets users add this repo as a Claude marketplace.scripts/validate-package.pychecks package files and shared values.
Rules for changes
Keep SKILL.md and README.md in sync.
- Patterns: The skill has 35 numbered patterns. If you add, remove, or renumber a pattern, update the README table, heading, validator, and every pattern reference.
- Version: Keep the same version in
SKILL.mdundermetadata.version, the first README version entry, and.claude-plugin/plugin.json. Do not add a top-levelversionfield to the skill. - Compatibility: Keep install and use instructions neutral across agents. Names such as Claude Code, OpenCode, and Codex are examples, not limits.
- History: Add a short README version note for any behavior change or non-obvious fix.
- Checks: Before publishing, run
python3 scripts/validate-package.py,npx skills add . --list, andclaude plugin validate ..
Writing style
Use Plain Language in code comments, prompts, documentation, descriptions, validation messages, and progress reports.
- Lead with the main point.
- Use common words and active voice.
- Keep sentences and paragraphs short.
- Use one term for the same item.
- Use
mustfor requirements. - Use headings, lists, and tables when they help the reader.
- Remove repeated or unnecessary words.
- Limit acronyms and explain technical terms.
- Avoid double negatives.
- Keep exact identifiers, commands, paths, schema fields, quotations, watched phrases, and behavior-bearing examples.
- Keep the full technical meaning.
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.
- yesterday First seen · 50 lines · 541 tokens per session scan A 331911dd8b10
humanizer AGENTS.md is an instructions file published in the GitHub repository blader/humanizer (38,958 stars, last pushed 13d ago), licensed MIT. It adds 541 tokens to every session, about $0.0027 per session on Opus 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.
Other instructions, from other repositories
avoid-ai-writing CLAUDE.md
Instructions for conorbronsdon/avoid-ai-writing, covering claude.md, what this is, repository structure, how to make changes and architecture of the skill.
shuorenhua AGENTS.md
Instructions for MrGeDiao/shuorenhua, covering 仓库说明, 语言, 风格, 布局 and 协作.
vibeflow CLAUDE.md
Instructions for pe-menezes/vibeflow, covering vibeflow monorepo, structure, cross-edition sync rules, file mapping and what to sync.
humanise CLAUDE.md
Claude Code instructions for Nisus74/humanise, covering claude.md, the one rule: body vs soul, repo map, the acceptance gate (read before changing the engine) and commands.
humanise AGENTS.md
AGENTS.md instructions for Nisus74/humanise, covering agents.md and launch documentation.
humanise GEMINI.md
Gemini CLI instructions for Nisus74/humanise: Gemini CLI and Google Antigravity read this file. This repo is the humanise writing skill: it makes AI-generated prose sound like a specific human wrote it.