ghostwriter

A writing aid that turns transcripts, notes, interviews, and research into polished prose while preserving a recognizable personal voice.

In plain words
What is it for?
Use it to create articles or newsletters from interviews, refine notes, or adapt source material to a particular author’s voice or style.
Why use it?
It removes the manual work of shaping scattered source material into publishable writing and helps avoid wording that obviously sounds machine-generated.

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/cdeistopened/skill-stack/ghostwriter
Any agent
npx skills add cdeistopened/skill-stack --skill ghostwriter
Clone the repo
git clone --depth 1 https://github.com/cdeistopened/skill-stack

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,469 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 $0.00048 $0.02469
Opus 5 $0.00024 $0.01234
Sonnet 5 $0.00010 $0.00494
Haiku 4.5 $0.00005 $0.00247

Measured 2d ago against content hash 39ce0c299ddf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ghostwriter 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/skills/ghostwriter/SKILL.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ghostwriter Skill

Purpose

This skill transforms source material - transcripts, notes, research, interviews - into authentic, human-written content that reads naturally without obvious AI tells. It extends the anti-ai-writing skill by adding voice adaptation and source material conversion techniques.

Core Philosophy: The best ghostwriting is invisible. Readers should feel like they're reading a real person's thoughts, not a filtered or processed version of source material.

This skill assumes you've read the anti-ai-writing skill. It builds on those fundamentals with additional techniques for voice adaptation and source material conversion.

When to Use This Skill

Use the Ghostwriter skill when:

  • Converting transcripts or interviews into polished articles or newsletters
  • Refining notes into publishable content
  • Converting source material into different voices or styles
  • Building content that maintains a distinctive, personal voice
  • Adapting writing to match a specific author's style

Use in conjunction with:

  • anti-ai-writing skill for core humanization patterns
  • Voice style profiles for adapting to specific voices
  • Source material that needs authentic conversion
  • brand-identity-wizard profile for brand voice consistency

The 8 Human Desires Framework

Great writing taps into core human desires. Choose 1-2 per piece:

1. Safety of Tribe

Belonging, community, fitting in

  • "The hidden skills that separate successful people from struggling ones"
  • Use when: Readers need to feel part of something larger

2. Survival & Success

Progress, achievement, security

  • "The greatest threat to your potential is getting tied down too early"
  • Key phrases: "breakthrough," "advancement," "finally," "unlocked"

3. Life Enjoyment

Pleasure, experiences, freedom

  • "Why most people miss the best parts of their work"
  • Key phrases: "savor," "freedom," "experience," "joy"

4. Social Acceptance

Status, respect, recognition

  • "What successful people know that average people don't"
  • Key phrases: "elite," "leaders know," "insiders understand"

Read the full file on GitHub · 335 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 · 335 lines · 48 tokens per session scan A 39ce0c299ddf

Subscribe to this mod's changes

ghostwriter is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,469 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens