What is text.humanize?

A writing-editing procedure that removes recognizable AI writing habits while preserving the author's meaning, structure, facts, and voice.

Use it to edit text with hedging, clichés, dramatic transitions, or other common AI-style patterns.

It makes text sound more natural without rewriting the argument or adding new ideas.

text.humanize — Skill for Claude Code by gpsaggese/helpers

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.

Any agent

npx skills add gpsaggese/helpers --skill text.humanize

Clone the repo

git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/text.humanize/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/text.humanize)

Your own site

<a href="https://agentmods.dev/skills/gpsaggese/helpers/text.humanize"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/text.humanize/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gpsaggese/helpers/text.humanize"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/text.humanize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,401 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.02401
Opus 5.5	$0.00005	$0.00960
Sonnet 5.5	$0.00003	$0.00480
Haiku 4.5	$0.00001	$0.00240

Measured yesterday against content hash 1fe35caea993, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

text.humanize 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

text.humanize — 89% identical, 144 lines differ

.claude/skills/text.humanize/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Change text with recognizable AI mannerisms (hedging, dramatic pivots, cliched transitions). Clean up AI-written content that is factually correct but flat

What This Skill Preserves

Author's opinions, arguments, and claims
Document structure and organization
Paragraph and section order
Core meaning and facts
Intentional stylistic choices (fragments, unconventional punctuation, etc.)

Workflow

Core Principles

Edit, don't rewrite. Clean up pattern slop, keep the voice, opinions, structure, and meaning
Apply systematically: check all 19 rules below. Skip a rule only if it does not apply
Use judgment on conflicts. If breaking a rule serves the writing (e.g., a well-placed em dash for effect), keep it
Change nothing else: no reordered paragraphs, added ideas, rephrased core arguments, or altered facts

Pattern Checklist

Scan for these AI markers before applying detailed rules:

Overused Words and Jargon
- Grandiose: "vital", "pivotal", "groundbreaking", "robust", "comprehensive", "nuanced", "multifaceted", "transformative"
- AI vocabulary: "delve", "leverage" (verb), "reimagine", "empower", "unpack", "synergy"
Filler and Hedges
- "It's worth noting that", "It's important to remember", "It should be noted", "Interestingly enough"
- "Something we've observed", "This is where X really shines"
Theatrical Transitions and Pivots
- Throat-clearing: "Let's dive in", "Let's unpack", "In this article, we'll"
- Dramatic pivots: "But here's the thing", "Here's the catch", "Here's what most people miss"
- Overused connectors: "Furthermore", "Moreover", "Additionally", "In addition to the above"
- Rhetorical openers: "So what does this mean for you?", "Why does this matter?"
Structural Patterns
- Gift-wrapped endings: "In summary", "In conclusion", "Ultimately", "At the end of the day", "Moving forward"
- Exhaustive lists: 7-10 items when 3-4 would suffice
- Passive voice clusters: 2+ passive sentences in a row
- Corrective antithesis: "Not X. But Y." setup-payoff constructions
Meta-Language and Vagueness
- Meta-verbs: "highlights", "underscores", "emphasizes", "showcases", "illustrates"
- Vague attribution: "some experts say", "widely covered", "significant attention"
- Copy-paste metaphors: same metaphor repeated word-for-word 3+ times

Read the full file on GitHub · 220 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.

yesterday First seen · 220 lines · 13 tokens per session scan A 1fe35caea993

Subscribe to this mod's changes

text.humanize is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 2,401 once invoked, about $0.0001 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 2026-11-06.

Writing and docs

text.humanize next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
text.humanizegpsaggese/helpers	Skill	158	today	Apache-2.0	A	13	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex