the-humanizer

the-humanizer is a skill for Claude Code, Codex from artttj/rapid-stack. It costs 106 tokens per session (7,842 once invoked), scanned A, original, MIT.

A writing guide that reviews text for patterns often associated with artificial or overly polished writing, then rewrites it in a more natural voice.

In plain words
What is it for?
Use it to humanize text, check for AI-like wording, adapt writing for a channel, or rewrite content in a chosen voice.
Why use it?
It helps make writing sound less formulaic and better suited to its channel or the writer’s voice.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/artttj/rapid-stack/the-humanizer
Any agent
npx skills add artttj/rapid-stack --skill the-humanizer
Clone the repo
git clone --depth 1 https://github.com/artttj/rapid-stack

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for the-humanizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/artttj/rapid-stack/the-humanizer.svg)](https://agentmods.dev/skills/artttj/rapid-stack/the-humanizer)
Your own site
<a href="https://agentmods.dev/skills/artttj/rapid-stack/the-humanizer"><img src="https://agentmods.dev/badge/skills/artttj/rapid-stack/the-humanizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00106 $0.07842
Opus 5 $0.00053 $0.03921
Sonnet 5 $0.00021 $0.01568
Haiku 4.5 $0.00011 $0.00784

Measured 3d ago against content hash 56a00cd484c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

the-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 3d 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.

.opencode/skills/the-humanizer/SKILL.md · 485 lines

How it starts

The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.

 .-----------.
 | ~~  o  ~~ |
 | ~  (_)  ~ |    The Humanizer
 | ~~ \_/ ~~ |    v2.2
 |  scanning |    Crazy Marketer
 '-----------'

Changelog

Every time this skill is updated, log the changes below with the date and a brief description. This section must be maintained on every edit.

Version Date Changes
v2.2 2026-05-06 Pattern refresh. +2 hollow intensifiers (pivotal, enduring) and +8 AI vocabulary words (intricate, underscore/underscores, vibrant, groundbreaking, showcasing, garner, meticulous, surpass). +2 phrase categories: promotional verb upgrades ("stands as", "serves as", "boasts", "features" replacing plain "is/has") and vague unsourced attribution ("industry reports", "observers have cited", "experts argue", "due to its unique characteristics"). +4 structural markers: avoidance of plain "is/are", present-participle attachments for shallow analysis, challenges-then-future content-mill framework, Title-Cased Headers. Sources: Wikipedia "Signs of AI writing" community register, Sean Goedecke's em-dash analysis, Hacker News discussion on AI vocabulary leaking into everyday speech.
v2.1 2026-03-30 Weekly pattern refresh. +4 AI vocabulary words (elevate, realm, essentially, certainly). +5 AI phrases & metaphors (not only...but also, here's a breakdown, in the ever-evolving landscape, a testament to, there is a specific kind of [noun] that happens when). +3 LinkedIn-specific structural markers (common-belief-then-counter opener, period-separated word emphasis, self-intro paragraph at post bottom). Sources: LinkedIn feed analysis (15+ posts from user's live feed) + web research (SEJ, Hastewire, WalterWrites, onesecmedia).
v2.0 2026-03-25 Major release: The Humanizer is now a universal content reviewer. Auto-detects content type (blog post, LinkedIn post, email, Slack message) and applies channel-specific AI pattern detection, scoring, and rewrite rules automatically. New patterns since v1.0: +16 AI vocabulary words (tapestry, multifaceted, nuanced, foster, cultivate, facilitate, utilize, comprehensive, albeit, whilst, theater, plainly, superpower, empower, journey, reality). +12 AI phrases & metaphors (brutal clarity, lost the plot, painfully clear, blunt honesty, that way you can, with precision, lived experience, launching a new chapter, the energy in the room, laying the groundwork, Here's to [noun]!, will never be the same, that promise becomes reality, ends the era of, the same tension, keeping my hands dirty). +1 new phrase-level category (stacked abstract noun lists). +18 structural markers (three-part parallel structure, colon-list pattern, contrast-based negation constructions, exclamation-point inflation, adverb-stacking pivot formula, declarative simplicity setup, triple rhetorical question hook, self-posed question as transition, declarative reveal pattern, label-colon framework, stat bomb opener, honesty disclaimer, credential stacking opener, definition reframe, punchy orphan closer, tension-colon opener, parenthetical aside for fake candor, standalone hype fragment). New channel-specific detection: LinkedIn (engagement bait closers, vulnerability performance, fake humility, one-line paragraph formatting, tag-and-thank, arrow chains, vulnerability bait hooks, hyperbole openers, negation upgrades). Email (AI greetings, AI closings, corporate filler, fake personalization, hedge language, over-politeness stacking, subject line patterns, buried asks, template structures). Slack (over-formal language, corporate filler, unnecessary hedging, emoji overload, length violations). New channel-specific scoring: Email uses Clarity + Appropriate Tone instead of Reader Value + Domain Credibility. Slack uses Naturalness + Clarity + Brevity. New files: the-humanizer-linkedin.md (standalone), the-humanizer-email.md (standalone). Source: LinkedIn feed analysis of 15+ organic posts.
v1.0 2026-03-10 Initial release. Expanded AI vocabulary with 10 new high-signal words. Added "AI phrasing & metaphors" category with 7 entries. Added stacked abstract noun lists detection. Added 10 structural markers: three-part parallel structure, colon-list pattern, contrast-based negation constructions, exclamation-point inflation, adverb-stacking pivot formula, declarative simplicity setup, triple rhetorical question hook, self-posed question as transition, declarative reveal pattern, label-colon framework. Source: LinkedIn feed analysis.

Read the full file on GitHub · 485 lines

Changes

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.

  1. 3d ago First seen · 485 lines · 106 tokens per session scan A 56a00cd484c5

Subscribe to this mod's changes

the-humanizer is a skill published in the GitHub repository artttj/rapid-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 7,842 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

reflect

Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.

alvinunreal/oh-my-opencode-slim · 53 tokens

codemap

Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.

alvinunreal/oh-my-opencode-slim · 34 tokens

scientific-schematics

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways…

xintaofei/codeg · 68 tokens

openpets

Use when the user asks to install, configure, verify, troubleshoot, or understand OpenPets; install or select a pet; connect Claude Code, OpenCode, Cursor, Codex, or MCP clients; configure a project to use a specific pet; or debug openpetsstatus, openpetsreact, or openpetssay.

alvinunreal/openpets · 70 tokens

git-master

MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git…

code-yeongyu/oh-my-openagent · 81 tokens

atlas-obscura

Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.

borski/travel-hacking-toolkit · 44 tokens