humanizer

A command for editing existing writing so it sounds more natural and less like it was produced by an AI system.

In plain words
What is it for?
It is for revising drafts that sound too artificial, including text described as “AI-generated” or “ChatGPT-like.”
Why use it?
It helps remove repetitive or robotic writing patterns while preserving a more personal voice.

Command for Claude Code

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 commands/marciopuga/cog/humanizer
Clone the repo
git clone --depth 1 https://github.com/marciopuga/cog

Made for: Claude Code.

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,507 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 $0.00054 $0.01507
Opus 5 $0.00027 $0.00754
Sonnet 5 $0.00011 $0.00301
Haiku 4.5 $0.00005 $0.00151

Measured 2d ago against content hash c8d4896d844e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

.claude/commands/humanizer.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use this skill when the user wants to humanize, de-AI, or clean up AI-generated text. Trigger if the conversation involves:

  • "Humanize this", "make this sound human", "de-AI this"
  • "This sounds too AI", "too ChatGPT", "sounds robotic"
  • Reviewing or editing text that reads like AI slop
  • Cleaning up drafts for natural voice Do NOT trigger for original writing tasks (use /explainer instead). This skill is for editing existing text to remove AI patterns.

Domain

Writing quality — removing AI artifacts and injecting human voice. Based on Wikipedia's "Signs of AI writing" guide (WikiProject AI Cleanup).

Core Principle

Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.

Process

  1. Read the input text carefully
  2. Identify all instances of the patterns below
  3. Rewrite each problematic section
  4. Ensure the revised text sounds natural when read aloud, varies sentence structure, uses specific details over vague claims, and uses simple constructions (is/are/has) where appropriate
  5. Present a draft humanized version
  6. Self-audit: "What makes the below so obviously AI generated?" — answer briefly with remaining tells
  7. Revise: "Now make it not obviously AI generated." — present the final version
  8. Brief summary of changes made

Output Format

Provide:

  1. Draft rewrite
  2. "What still sounds AI?" (brief bullets)
  3. Final rewrite
  4. Summary of changes

PATTERN REFERENCE

Signs of Soulless Writing (even if technically "clean")

  • Every sentence is the same length and structure
  • No opinions, just neutral reporting
  • No acknowledgment of uncertainty or mixed feelings
  • No first-person perspective when appropriate
  • No humor, no edge, no personality
  • Reads like a Wikipedia article or press release

How to Add Voice

  • Have opinions. React to facts. "I genuinely don't know how to feel about this" beats neutral pros-and-cons.
  • Vary rhythm. Short punchy sentences. Then longer ones that take their time. Mix it up.
  • Acknowledge complexity. Real humans have mixed feelings.
  • Use "I" when it fits. First person isn't unprofessional — it's honest.
  • Let some mess in. Perfect structure feels algorithmic. Tangents and half-formed thoughts are human.
  • Be specific about feelings. Not "this is concerning" but name what actually unsettles you.

Read the full file on GitHub · 167 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. 2d ago First seen · 167 lines · 54 tokens per session scan A c8d4896d844e

Subscribe to this mod's changes

humanizer is a command published in the GitHub repository marciopuga/cog (376 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,507 once invoked, about $0.0003 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.