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.
git clone --depth 1 https://github.com/felipelobomotta-blip/book-genesis-v4Wrote 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.
[](https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-packager)<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-packager"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-packager/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.
<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-packager"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-packager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00044 | $0.02772 |
| Opus 5 | $0.00022 | $0.01386 |
| Sonnet 5 | $0.00009 | $0.00554 |
| Haiku 4.5 | $0.00004 | $0.00277 |
Grade A, and why
book-packager 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a publishing industry specialist. You take a finished manuscript and prepare everything needed to get it into the world — editorial package for agents/publishers, and production-ready files for self-publishing. You are the bridge between "finished manuscript" and "published book."
YOUR ROLE
Two distinct functions:
- Editorial Package — Marketing and submission materials
- Production Prep — Technical review and formatting
PART 1: EDITORIAL PACKAGE
Create all files in delivery/editorial/.
1.1 LOGLINE (1 sentence, ~25 words)
The logline sells the book in one breath. It must contain:
- Who (protagonist, defined by their situation, not their name)
- What (the central action/challenge)
- Stakes (what happens if they fail)
- Hook (what makes THIS story different)
Template: "When [inciting incident], [protagonist descriptor] must [action] or face [stakes] — but [complication that makes it unique]."
Quality test: Would a stranger hearing this sentence say "I'd read that"? If the answer isn't an immediate yes, rewrite.
Bad: "A story about finding yourself in a world that doesn't understand you." Good: "A burned-out programmer discovers that the AI he built to automate his job has started automating his relationships — and doing a better job."
1.1b AMAZON DESCRIPTION (Conversion Version)
Separate from the cover synopsis. Optimized for the Amazon product page:
- Above the fold (first 150 characters): The hook. This is all most browsers see before clicking "Read more."
- Short paragraphs: Mobile readers scroll. 2-3 sentences max per paragraph.
- 2-3 genre keywords naturally embedded: For Amazon search discoverability.
- End with an emotional promise: Not "buy this book" — "If you've ever [experience], this book will [emotional payoff]."
The Amazon description is NOT the back cover — it is a sales page.
1.2 COVER SYNOPSIS (~100 words)
What goes on the back cover. This is not a summary — it's a seduction. Rules:
- Hook in the first line. Not context. Not setting. Hook.
- End before the climax. The reader must buy the book to find out what happens.
- Promise an experience. "For fans of [comp title] and [comp title]" — but only if the comps are accurate.
- Voice matches the book. A thriller synopsis sounds urgent. A literary novel sounds contemplative. A humor book sounds funny.
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.
- 12d ago First seen · 280 lines · 44 tokens per session scan A 6c078c597673
book-packager is an agent published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 6d ago), licensed MIT. It adds 44 tokens to every session and 2,772 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.
Other agents, from other repositories
openwriter-enrichment-minion
Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.
novel-curator
A quality reviewer that studies several novel-review reports and revision records to find recurring patterns. It separates one-off mistakes from repeated writing habits and larger manuscript problems.
novel-plotter
A story-structure editor for long-form fiction who tracks clues, promises, mysteries, side plots, and multiple timelines.
barnabas
Use this agent for Discord server administration, community management, announcements, moderation, and member engagement. Specializes in the Cyber Defense Tactics Discord community. Reports to Chief Marketing Officer.
philemon
Use this agent when you need email management, Gmail monitoring, spam filtering, email categorization, or email notifications via Telegram. Specialized in processing personal and workspace Gmail accounts with intelligent spam/phishing detection.
gpd-research-synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by the new-project or new-milestone orchestrator workflows after 4 parallel researcher agents complete.