Borrowing it
Nothing to install: this file belongs to felipelobomotta-blip/book-genesis-v4. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/felipelobomotta-blip/book-genesis-v4/master/AGENTS.mdgit 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/instructions/felipelobomotta-blip/book-genesis-v4/agents-md)<a href="https://agentmods.dev/instructions/felipelobomotta-blip/book-genesis-v4/agents-md"><img src="https://agentmods.dev/badge/instructions/felipelobomotta-blip/book-genesis-v4/agents-md/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/instructions/felipelobomotta-blip/book-genesis-v4/agents-md"><img src="https://agentmods.dev/badge/instructions/felipelobomotta-blip/book-genesis-v4/agents-md.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 | $0.00993 | $0.00993 |
| Opus 5 | $0.00496 | $0.00496 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
book-genesis-v4 AGENTS.md 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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository is Book Genesis: a Python runner that turns one idea into a manuscript, chapter by chapter, using Markdown prompt templates in agents/ and phase prompts in skills/book-genesis-codex/references/.
Default Behavior
When asked to create, plan, draft, judge, revise, or package a book, use the runner. Do not orchestrate the phases by hand and do not grade prose yourself.
book-genesis setup # once: providers, keys, models (or python runner/cli.py setup)
book-genesis new --idea "..." --language <code> # the whole pipeline with progress
python runner/cli.py doctor # what is installed; how roles will be assigned
python runner/cli.py init <project> --idea "..." --language <code>
python runner/cli.py run-phase <project> # repeat for intake, foundation, architecture
python runner/cli.py book <project> # every chapter; chapter 1 judged by the reader panel
python runner/cli.py judge <file.md> --genre "..." # blind-read any chapter
python runner/cli.py panel <project> <n> # the whole panel on a written chapter
book-genesis review <project> [--open] # inspect the generated project report
book-genesis export <project> --format markdown|epub [--output PATH] [--overwrite]
The design is recorded in docs/adr/0001-runner-orquestra-juiz-cego.md and docs/adr/0002-autonomia-painel-adaptadores.md. The short version:
- the runner owns project writes and consumes text responses. Claude tools are disabled; Codex uses an ephemeral read-only sandbox. Generic adapters follow their declared CLI capabilities;
- the judge (
agents/book-judge.md) is blind: prose only, no outline, no foundation, no writer notes; it compares drafts instead of scoring them; - the writer does not know any rubric;
agents/book-evaluator.mdis a diagnostic for the editor, not a gate; - the guided terminal session pauses for agreement on the brief, outline and chapter 1;
--yesor noninteractive input runs autonomously. The panel consists of model readers with different personas, and different families when configured.--humanadditionally requires the explicit approval command; - the runner uses whatever CLI is installed (
claude,codex, anything declared inrunner/config/adapters.yaml) or--manualprompt files; a single-family run is allowed and carries a warning inRUN_REPORT.md; - Claude is invoked in safe mode with tools disabled. Codex is invoked for text-only output; that input contract does not prove every Codex tool is disabled in every host environment.
- constants live in
runner/config/genre-profiles.yaml,runner/config/models.yamlandrunner/config/adapters.yaml; prompts reference them and never restate numbers.
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.
- 4d ago Changed · -12 lines · +388 tokens per session 55908adb8e91
- 10d ago First seen · 67 lines · 605 tokens per session scan A 0a4cadd0173d
book-genesis-v4 AGENTS.md is an instructions file published in the GitHub repository felipelobomotta-blip/book-genesis-v4 (114 stars, last pushed 4d ago), licensed MIT. It adds 993 tokens to every session, about $0.0050 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.