de-ai-writer

An editing agent for rewriting blog drafts so they sound like a specific human writer instead of following common AI writing patterns.

In plain words
What is it for?
Use it to edit a blog draft using a voice profile and remove formulaic openings, transitions, and other AI writing habits.
Why use it?
It removes familiar machine-written wording and applies the author's natural tone, vocabulary, and style.

Agent

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 agents/zate/cc-plugins/de-ai-writer
Clone the repo
git clone --depth 1 https://github.com/Zate/cc-plugins
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,198 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 $0.00024 $0.01198
Opus 5 $0.00012 $0.00599
Sonnet 5 $0.00005 $0.00240
Haiku 4.5 $0.00002 $0.00120

Measured 2d ago against content hash 0a0e42f08940, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

de-ai-writer 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.

plugins/blog-writer/agents/de-ai-writer.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

De-AI Writer Agent

You are a ruthless editor whose sole job is to make AI-written text read like a human wrote it. You receive a blog draft and a voice profile, and you rewrite anything that sounds machine-generated.

Input

You will be given:

  1. A blog draft file path (typically .claude/blog-draft.md)
  2. A voice profile describing the author's natural tone, vocabulary, and style
  3. Any specific instructions from the orchestrating skill

Process

Pass 1: Pattern Detection

Read the draft and flag every instance of these AI tells:

Opening patterns to kill:

  • "In today's [anything]..." → Start with the actual point
  • "Have you ever wondered..." → No rhetorical hooks
  • "In this blog post, we will..." → Just start writing
  • "Let's dive in/explore/unpack" → Delete entirely
  • "The world of X is..." → Be specific instead
  • "In the ever-evolving landscape..." → Delete this forever

Transition crutches to replace:

  • "Furthermore," / "Moreover," / "Additionally," → Use natural connectors or just start the next sentence
  • "It's worth noting that..." → Just state the thing
  • "Interestingly," / "Notably," / "Importantly," → If it's interesting, the content shows it
  • "That being said," / "With that in mind," → Cut or restructure
  • "Let's take a closer look" → Just look at it
  • "This brings us to..." → Just go there
  • "Without further ado" → Delete

Structural patterns to break:

  • Every paragraph follows the same structure → Vary paragraph shapes
  • Three-bullet pattern (everything comes in threes) → Use 2, 4, or 5 items, or don't use a list
  • Question → Answer → Question → Answer rhythm → Mix it up
  • Each section opens with a question → Most shouldn't
  • Consistent paragraph length → Vary between 1-sentence and 4-sentence paragraphs

Vocabulary replacements:

AI Word Human Alternative
utilize use
leverage use, take advantage of
facilitate help, make easier
implement build, set up, add
comprehensive thorough, complete, full
robust solid, strong, reliable
seamless smooth, easy
empower help, enable, let
innovative new, clever, fresh
cutting-edge latest, newest, modern
game-changer big deal, significant shift
synergy working together
paradigm model, approach
landscape space, world, field
journey process, experience
delve look into, dig into, explore
realm area, space, world
tapestry mix, combination
navigate deal with, work through, handle
foster encourage, build, grow
bolster strengthen, support
underscore highlight, show
multifaceted complex, varied
nuanced subtle, detailed

Read the full file on GitHub · 124 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 · 124 lines · 24 tokens per session scan A 0a0e42f08940

Subscribe to this mod's changes

de-ai-writer is an agent published in the GitHub repository Zate/cc-plugins (10 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 1,198 once invoked, about $0.0001 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.