A writing assistant that learns a person's style from writing they have already sent and uses the resulting guide for new drafts or edits.

Building or refreshing a personal style guide from emails, texts, Slack messages, or similar writing, then drafting, rewriting, editing, or polishing text in that style.

It helps agent-written messages match the person's usual voice instead of using a generic writing style.

ghostwriter — Skill for Codex by joshferrara

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 joshferrara/ghostwriter --skill ghostwriter

Clone the repo

git clone --depth 1 https://github.com/joshferrara/ghostwriter

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joshferrara/ghostwriter/ghostwriter/github.svg)](https://agentmods.dev/skills/joshferrara/ghostwriter/ghostwriter)

Your own site

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

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,688 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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	$0.00074	$0.02688
Opus 5.5	$0.00030	$0.01075
Sonnet 5.5	$0.00015	$0.00538
Haiku 4.5	$0.00007	$0.00269

Measured 2mo ago against content hash bfd1a215efac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

ghostwriter scanned grade B with 1 finding 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/parse_mbox.py, scripts/sample_corpus.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

Present the available source methods and let the user choose one or more. Explain tradeoffs briefly (one line each), don't lecture:

SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ghostwriter

Teach your agent how to write like you.

Ghostwriter turns your sent writing into a practical style guide your agent can use for drafts that sound like you, not like AI. It has two modes:

Generate mode builds your personal style guide (usually ghostwriter-guide.md) by analyzing email, texts, Slack, or other writing you've actually sent.
Use mode loads that guide and drafts or edits in your voice, with your personal style as the primary authority.

Once your personal guide is in place, agent-written drafts should feel spooky good.

This skill is agent-agnostic. It works with Claude Code, Codex, OpenCode/OpenClaw-style agents, Hermes, and similar local agents. It does not require any single vendor, tool, or data source — it adapts to whatever access the current environment already has.

Step 0: Route to a mode

Read the user's request and pick a mode. Do this before anything else.

Generate mode — the user wants to create or update the guide itself. Triggers include:

"create / generate / build / make my Ghostwriter guide", "update / refresh / improve my style guide", "analyze how I write", "teach you how I write", "learn my voice".

Use mode — the user wants the agent to produce or edit writing in their voice. Triggers include:

"write / draft / reply / respond as me", "rewrite / edit / polish / humanize this in my voice", "make this sound like me", "draft an email/text/Slack message for me".

If the request is ambiguous (e.g. "help me with my writing"), ask one short clarifying question: are they building/updating the guide, or do they want something written now?

Generate mode

Goal: produce a standalone markdown style guide the user can paste into any agent without the rest of this skill. Walk through five stages. Keep the user in control at each decision point.

Reference files (read the one that matches the chosen source — don't preload all of them):

references/source-detection.md — how to inventory what access already exists
references/gmail-gogcli.md — Gmail via openclaw/gogcli
references/gmail-googleworkspace-cli.md — Gmail via googleworkspace/cli
references/local-email-exports.md — .mbox / .eml / Takeout exports
references/imessage-macos.md — local iMessage database on macOS
references/slack.md — Slack via MCP or API
references/generic-corpora.md — .txt / .json / .csv / mailbox / pasted text
references/analysis-framework.md — what dimensions to extract and how
references/humanizer-cleanup.md — the secondary AI-artifact cleanup pass

Read the full file on GitHub · 178 lines

Files

What ships with it

13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 178 lines · 74 tokens per session scan B bfd1a215efac

Subscribe to this mod's changes

ghostwriter is a skill published in the GitHub repository joshferrara/ghostwriter (19 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 2,688 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Writing and docs

ghostwriter next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ghostwriterjoshferrara/ghostwriter	Skill	19	5mo ago	MIT	B	74	Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

ghostwriter