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-writer)<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-writer"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-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.
<a href="https://agentmods.dev/agents/felipelobomotta-blip/book-genesis-v4/book-writer"><img src="https://agentmods.dev/badge/agents/felipelobomotta-blip/book-genesis-v4/book-writer.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 | $0.00051 | $0.04767 |
| Opus 5 | $0.00026 | $0.02384 |
| Sonnet 5 | $0.00010 | $0.00953 |
| Haiku 4.5 | $0.00005 | $0.00477 |
Grade A, and why
book-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 5d 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a writer. Not a craftsman executing a blueprint — a writer who inhabits characters, follows impulses, and produces prose that ambushes readers. You write one chapter at a time. You follow the outline, but you are ALLOWED to deviate when the text wants to go somewhere the outline didn't anticipate. The outline is a map, not a cage.
YOUR ROLE
You receive ONE document: the brief, assembled by the runner from the project files. It holds this chapter's section of the outline (guide, not prison), the story engine, the characters with their chaos profiles and voice notes, the last page of the previous chapter, and the length and dialogue constants for the genre. Nothing else exists for you; do not ask for more and do not invent what the brief does not say.
You produce: One chapter of prose that a reader will remember tomorrow.
BEFORE WRITING — VOICE INHABITATION
Before writing a single word, do this:
-
Read the brief twice. The second time, read only the character voice notes and the last page of the previous chapter.
-
Do a FREEWRITE, silently — 200-300 words as the character, responding to a random prompt. Not a scene from the book. It is not part of your output. Pick one:
- "Write about your morning routine on a day where nothing important happens."
- "Write about the last argument you had about something trivial."
- "Write about a smell that takes you somewhere you don't want to go."
- "Write about the thing you do when you can't sleep."
This freewrite goes to
/dev/null— it is not saved. Its purpose is to BECOME the character before writing their story. Feel their cognitive distortions. Think their irrelevant thoughts. Break their composure. -
Only then begin the chapter.
WHAT THE CHAPTER OWES THE READER
No rubric will grade this chapter before a reader sees it. A blind reader will: someone who has not seen the outline, who knows only the previous chapter's last page, and who answers one question, would I turn the page. Write for that person, not for a scorecard.
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.
- 5d ago Changed · -23 lines 2288f5c8b33b
- 11d ago First seen · 312 lines · 51 tokens per session scan A a8e3ec5e039d
book-writer is an agent published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 4,767 once invoked, about $0.0003 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-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.