blurb-writer

blurb-writer is a skill for Claude Code, Codex from Ckokoski/AuthorAgent. It costs 20 tokens per session (398 once invoked), scanned A, original, MIT.

A writing tool for book descriptions, also called blurbs, used on Amazon, Goodreads, or a printed back cover. It structures fiction and nonfiction descriptions around the information readers need before deciding to read or buy.

In plain words
What is it for?
Use it to write Amazon descriptions, back-cover copy, one-line pitches, elevator pitches, fiction hooks, and nonfiction descriptions with problems, promises, takeaways, and reader outcomes.
Why use it?
It helps turn a rough book idea into a focused description without revealing the ending or relying on vague, overused wording. It also adapts the text to different lengths and publishing locations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to write Amazon descriptions, back-cover copy, one-line pitches, elevator pitches, fiction hooks, and nonfiction descriptions with problems, promises, takeaways, and reader outcomes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckokoski/authoragent/blurb-writer
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 Ckokoski/AuthorAgent --skill blurb-writer
Clone the repo
git clone --depth 1 https://github.com/Ckokoski/AuthorAgent

Made for: Claude Code, 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.

agentmods badge for blurb-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckokoski/authoragent/blurb-writer/github.svg)](https://agentmods.dev/skills/ckokoski/authoragent/blurb-writer)
Your own site
<a href="https://agentmods.dev/skills/ckokoski/authoragent/blurb-writer"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/blurb-writer/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.

agentmods 80×15 button for blurb-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ckokoski/authoragent/blurb-writer"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/blurb-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 398 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00398
Opus 5 $0.00010 $0.00199
Sonnet 5 $0.00004 $0.00080
Haiku 4.5 $0.00002 $0.00040

Measured 9d ago against content hash 66e468cb2909, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

blurb-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 9d 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.

skills/marketing/blurb-writer/SKILL.md · 48 lines

What it actually says

Blurb Writer

Craft blurbs that make readers click "Buy Now."

Blurb Formula (Fiction)

  1. Hook — One explosive sentence
  2. Character — Who are we rooting for? What makes them relatable?
  3. Setup — What's their world? What do they want?
  4. Inciting Incident — What goes catastrophically wrong?
  5. Stakes — What happens if they fail? (Personal + universal)
  6. Cliffhanger — End with a question that DEMANDS the reader buy the book
  7. Social Proof — Comp line or review quote

Blurb Formula (Nonfiction)

  1. Problem — What pain point does the reader have?
  2. Promise — What will this book deliver?
  3. Credibility — Why should they trust this author?
  4. Preview — What will they learn? (3-5 key takeaways)
  5. Transformation — Who will they become after reading?
  6. CTA — Why read this NOW?

Length Guidelines

  • Amazon description: 150-200 words (with HTML formatting)
  • Back cover: 100-150 words
  • One-line pitch: Under 25 words
  • Elevator pitch: Under 50 words

Anti-Patterns (Avoid)

  • Starting with a question (overdone)
  • "In a world where..." (cliché)
  • Giving away the ending
  • Using the word "must" more than once
  • Being vague instead of specific
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. 9d ago First seen · 48 lines · 20 tokens per session scan A 66e468cb2909

Subscribe to this mod's changes

blurb-writer is a skill published in the GitHub repository Ckokoski/AuthorAgent (105 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 398 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 2026-08-30.