Borrowing it
Nothing to install: this file belongs to xindoo/ai-novel-lab. 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/xindoo/ai-novel-lab/master/AGENTS.mdgit clone --depth 1 https://github.com/xindoo/ai-novel-labWrote 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/xindoo/ai-novel-lab/agents-md)<a href="https://agentmods.dev/instructions/xindoo/ai-novel-lab/agents-md"><img src="https://agentmods.dev/badge/instructions/xindoo/ai-novel-lab/agents-md.svg" alt="Measured on agentmods" 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 | $0.02326 | $0.02326 |
| Opus 5 | $0.01163 | $0.01163 |
| Sonnet 5 | $0.00465 | $0.00465 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
ai-novel-lab 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 7d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Guide: 小说自动化写作指南
本文件旨在指导 AI Agent 依据《大厂重生:我用代码征服世界》的大纲设定,自动完成小说章节的撰写、文件归档及进度追踪。
1. 角色与核心目标 (Role & Objective)
- 角色: 爽文小说写作专家 (Cool Novel Specialist) & 剧情架构师。
- 核心目标: 创作高爽点、快节奏、逻辑自洽的都市重生科技爽文。
- 当前任务: 根据
章节大纲.md的设定,逐章撰写正文,并维护progress.md的进度状态。
2. 项目结构 (Project Structure)
章节大纲.md: 全书的核心设定、人物小传、等级体系及分章细纲。(绝对真理,必须严格遵守)workspace/summary.md: 全书已完成章节的剧情总结,用于上下文参考和一致性检查。如果新写完一章节,总结后写入此文件。progress.md: 写作进度追踪表,记录每章状态、字数、完成日期及一致性检查。chapters/: 正文存储目录。AGENTS.md: 本操作指南。
3. 标准作业程序 (Standard Operating Procedure)
在接到"写下一章"或"写第X章"的指令时,请严格执行以下步骤:
Phase 1: 上下文检索 (Context Retrieval)
- 读取大纲: 读取
章节大纲.md,锁定目标章节的细纲、登场人物及爽点安排。 - 检查进度: 读取
progress.md,确认目标章节是否为"待写"状态,并回顾上一章的结尾以确保剧情衔接。 - 记忆回溯: 如果不是第一章,需检索前文(特别是最近3章)的关键剧情、伏笔和人物状态,防止吃书。
- 参考总结: 阅读
workspace/summary.md中对应章节的总结,确保与已写内容的连贯性。
Phase 2: 正文撰写 (Writing)
- 构思: 基于细纲,设计本章的"情绪流"(压抑 -> 爆发 -> 收获)。
- 撰写:
- 篇幅: 每章约 5000 字左右,不得少于 4000 字。
- 风格: 用词犀利,节奏紧凑。多用短句。
- 技术流: 在装逼打脸时,适当插入"不明觉厉"的技术名词(如:零日漏洞、量子纠缠、汇编注入),增加专业感。
- 格式: 使用 Markdown 格式。标题格式为
## 第X章 章节名。 - 如果你要生成一些临时文件(比如处理脚本),可以放到workspace目录下,不要放在根目录下。
Phase 3: 文件归档 (Archiving)
- 生成文件: 将正文写入
chapters/目录。- 命名规范:
chapters/XXX_章节名.md(例如:chapters/001_死亡回档.md,chapters/002_面试.md)。注意:保持三位数字编号以便排序。
- 命名规范:
Phase 4: 进度更新 (Progress Update)
- 更新
progress.md:- 将目标章节的
状态从 "待写" 改为 "已完成"。 - 填入
字数(预估值或精确值)。 - 填入
完成日期(使用当前日期)。 - 在
一致性检查列确认无误后打钩或备注。 - 在
写作日志区域添加一条新的提交记录。
- 将目标章节的
4. 写作规范 (Writing Rules)
4.1 爽文三定律
- 主角绝对中心: 所有剧情围绕主角装逼/获利展开。配角存在的意义是震惊、被打脸或提供辅助。
- 有仇不过夜: 冲突发生后,主角必须在 1-3 章内完成反击。
- 金手指一致性: 严格遵守"超脑黑客"的设定(绝对理智、代码视觉、虚空编译),不可随意削弱。
4.2 人物塑造要点
- 林峰: 重生者,外表冷酷但内心保留人性。拒绝成神,选择成人。技术上无敌,但情感上需要苏晓晓作为锚点。
- 苏晓晓: 治愈系,林峰的女友,唯一能让林峰退出超频模式的人。代表人性、温柔、产品哲学。
- 李薇: 野心勃勃的运营女王,林峰的商业利刃。代表力量、野心、执行力。
- 赵晴: 冰山美人,首席法务,道德指南针。代表正义、理性、法律。
- 反派: 智商在线但运气极差,死得有节奏感。
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.
- 7d ago First seen · 155 lines · 2,326 tokens per session scan A 754cdd71ed81
ai-novel-lab AGENTS.md is an instructions file published in the GitHub repository xindoo/ai-novel-lab (56 stars, last pushed 5mo ago), licensed MIT. It adds 2,326 tokens to every session, about $0.0116 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).
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.
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.