What is ship-30-voice?

A writing guide based on the documented style of Nicolas Cole and Dickie Bush, writers known for teaching online writing. It focuses on short essays, social-media threads, hooks, and practical writing frameworks.

Use it to draft online-writing lessons, thread openings, atomic essays, newsletter letters, and step-by-step frameworks for publishing content.

It helps break a broad idea into clear, short lines with a defined audience, problem, and promise. It gives the writer a repeatable structure instead of relying on clever phrasing.

ship-30-voice — Skill for Claude Code by jpeslar1

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 jpeslar1/john-peslar-ai-skills --skill ship-30-voice

Clone the repo

git clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-skills

Made for: Claude Code.

Or install voice-dna, the plugin that ships this one along with the rest of its 79 skills.

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/jpeslar1/john-peslar-ai-skills/ship-30-voice/github.svg)](https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/ship-30-voice)

Your own site

<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/ship-30-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/ship-30-voice/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/jpeslar1/john-peslar-ai-skills/ship-30-voice"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/ship-30-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 303 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,139 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	$0.00303	$0.04139
Opus 5.5	$0.00121	$0.01656
Sonnet 5.5	$0.00061	$0.00828
Haiku 4.5	$0.00030	$0.00414

Measured 17d ago against content hash 196aa6dad56b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ship-30-voice 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 17d 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.

ship-30-voice/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship 30 (Nicolas Cole and Dickie Bush) Voice DNA

Ship 30 for 30 is a two-person voice. Nicolas Cole is the broke-in-Chicago copywriter turned ghostwriter who opens every letter "Dear Writer," and sells tough love as the favor nobody did him. Dickie Bush is the ex-BlackRock analyst who tweeted a 30-day writing challenge to 732 followers and then wrote the hook formula down: clear not clever, specify the who, what, and why, twist the knife. Together they write as "we" in the Start Writing Online newsletter: nautical, ritual, one idea per line, "Hit publish. Then hit publish again." The forms are X threads, atomic essays, and Substack letters, not LinkedIn, and this skill adapts accordingly. Ground every output in references/voice-corpus.md (verbatim excerpts, each tagged Cole, Bush, or co-authored) and references/source-map.md (sources and refresh notes).

Voice DNA

Cadence and rhythm

One idea per line. Roughly 70 percent of lines in the corpus are a single sentence or fragment; median sentence around 11 words.
The hook is a staircase: bold declarative, credibility number, knife twist, colon promise. "College completely failed in teaching me how to write. / So I spent over 500 hours... / But unlike college, these won't cost you $120,000. / Here they are for free:"
Repeated stems build the drumbeat: "That means nights. / That means weekends. / That means during your lunch break." (Cole); "And my first $100. / And my first $1,000. / And my first $5,000."
Lists are numbered 1-5 even inside a tweet; "Boom. Done." closes a demonstration.
Native length: a 3-5 line X opener, a 150-300 word atomic essay, or a 1,500-3,000 word Substack letter broken into one-line paragraphs.
Spoken (items 101-110, their own podcast), the one-line breaks dissolve into 25-60 word runs, but the frameworks survive: Bush counts and lists ('people don't pay for information, they pay for packaging, speed, implementation, and outcomes') and calls Cole in by name ('here's a fun game we should play, Cole'); Cole diagnoses a belief and lands a punchline ('That's it.', 'It's because you don't have anything for sale.').

Read the full file on GitHub · 164 lines

Files

What ships with it

2 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.

17d ago Changed · +1 lines 196aa6dad56b
18d ago First seen · 163 lines · 303 tokens per session scan A 9317edc02c16

Subscribe to this mod's changes

ship-30-voice is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 303 tokens to every session and 4,139 once invoked, about $0.0012 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 2026-10-19.

Writing and docs

ship-30-voice next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ship-30-voicejpeslar1/john-peslar-ai-skills	Skill	12	18d ago	MIT	A	303	Claude Code
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