webnovel-handbook: Instructions file for Codex

AGENTS.md

webnovel-handbook AGENTS.md is an instructions file for Codex, OpenCode from miserylee/webnovel-handbook. It costs 2,318 tokens per session, scanned A, original, MIT.

A Chinese-language knowledge base and set of working rules for writing, reviewing, and managing web novels with AI.

In plain words
What is it for?
Starting novels, planning chapters and volumes, drafting or revising prose, reviewing manuscripts, maintaining writing references, and analyzing reader or project feedback.
Why use it?
It helps an agent prepare the story structure and source material before producing formal chapters.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is miserylee/webnovel-handbook's own configuration. It tells Codex and OpenCode how to work on webnovel-handbook itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything webnovel-handbook configures →

Reuse

Borrowing it

Nothing to install: this file belongs to miserylee/webnovel-handbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/miserylee/webnovel-handbook/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/miserylee/webnovel-handbook

Made for: Codex, OpenCode.

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 webnovel-handbook AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/miserylee/webnovel-handbook/agents-md.svg)](https://agentmods.dev/instructions/miserylee/webnovel-handbook/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/miserylee/webnovel-handbook/agents-md"><img src="https://agentmods.dev/badge/instructions/miserylee/webnovel-handbook/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,318 This file is loaded in full into every session.
When invoked 2,318 The same file — it is already loaded in full.
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 $0.02318 $0.02318
Opus 5 $0.01159 $0.01159
Sonnet 5 $0.00464 $0.00464
Haiku 4.5 $0.00232 $0.00232

Measured 7d ago against content hash 2354e82398d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

webnovel-handbook 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.

AGENTS.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

项目协作说明

这个项目是“学习如何写网文”的知识库。后续 AI 写网文、改网文、审稿或初始化小说项目时,可以把这里当作权威参考资料。

新手开书硬规则

  • 用户说“想开书”“帮我写第一章”“先试写一下”时,不默认进入正式正文。
  • 先做开书准备缺口诊断,判断是否已有项目简报、人物卡、设定台账、前 10 章方向、第一卷细纲、第一章任务单、风格手册和初始台账。
  • 缺口未补齐时,只能输出候选方案、开场小样、项目文档或章节任务单,不能把内容写成正式章节。
  • 用户不懂网文流程时,agent 主动引导补资料,不把“用户没要求”当作跳过大纲和细纲的理由。

每次先读

新会话或上下文丢失后,先读:

  1. README.md
  2. AGENTS.md
  3. docs/00-index.md

docs/sources/01-source-inventory.md 是大文件,不再作为默认整读入口。只有在新增来源、核查来源、处理引用边界或来源冲突时,才按关键词定向读取。

再按 docs/00-index.md 的“常用任务最小阅读包”读取专题。AGENTS.md 不再重复维护任务路线清单,避免和启动索引漂移。

  • 起草、续写、审稿、修订、开书、项目初始化、包装、数据复盘或知识库维护,都先回到 docs/00-index.md 选择本轮最小阅读包。
  • 如果任务路由不明、需要维护知识库或可能牵涉多个专题,再读 docs/workflows/57-knowledge-base-routing-consolidation-guide.md
  • 大文件仍然只按需检索:来源清单、模板仓库、扩展目录、README 下沉说明和变更日志详细归档不能因为“可能有用”就整篇读取。

来源优先级

处理本知识库时,优先级如下:

  1. 用户当前指令。
  2. 本项目已经确认的文档。
  3. 本仓库已经抽象化的通用写作方法与流程规范。
  4. 匿名旧项目样本、匿名编辑反馈样本、匿名读者反馈样本中已经沉淀的经验。
  5. 临时笔记和未整理材料。

如果来源之间冲突,先写明冲突,再按用户最新决定或本项目 docs/governance/99-decision-log.md 里的已确认规则处理。

本项目的特殊性

本项目不是单本小说,而是专门给后续 AI 写网文使用的知识库,所以允许把通用写作方法吸收、重组、展开,并写成详细参考。

写入时不要只复制来源原文。优先把内容整理成:

  • 原则:这条规则解决什么问题。
  • 用法:写作或审稿时怎么执行。
  • 风险:违反后会出现什么读者体感。
  • 检查问题:AI 或作者可以怎样自查。
  • 案例:来自旧项目的可复用经验。

编码与语言

  • 文档、笔记、模板默认使用中文。
  • 状态标签使用“已确认”“候选”“待确认”。
  • 文件读写使用 UTF-8。
  • 英文只保留在文件名、代码、稳定技术术语或来源原名里。

跨平台与命令执行

  • 维护本仓库时,优先使用 Bash/POSIX 兼容命令、Node.js 脚本或跨平台工具,不默认依赖 Windows 专属脚本。
  • 本仓库可能在 Linux、macOS 和 Windows 上维护;新增脚本、打包命令、安装说明和 agent 工作流必须考虑跨平台可用性。
  • 小范围文档修改优先使用补丁方式;大段文本重构优先使用 Node.js 读写 UTF-8,避免使用容易产生转义或编码问题的 shell 字符串拼接。
  • 如确需写平台专属命令,必须说明适用系统,并提供跨平台替代方案或 Node.js 版本。

维护规则

  • 新增稳定结论要写进专题文档,不只留在聊天里。
  • 新增来源要登记到 docs/sources/01-source-inventory.md
  • 新增关键决策优先记录到 docs/governance/99-decision-log.md 的短索引;确需长说明时,创建短小的单条决策文件并从 docs/governance/99-decision-log.md 链接。不要继续维护超大活跃文档或向已冻结的历史长归档追加正文。
  • 活跃文档应保持短小;内容膨胀时,允许索引链路变长,优先拆分成“入口索引 -> 分类索引 -> 目标短文档”。
  • 临时想法可以先放 notes/,但不能替代正式文档。
  • 不创建 finalv2 这类重复文档名;需要版本脉络时写进决策记录或案例笔记。
  • 如果用户指出“人物不活、剧情生硬、没有梗、情绪淡、读者不黏”,必须读取 docs/core-writing/11-human-writing-upgrade.md,不要只做句子润色。

开源维护补充

Read the full file on GitHub · 113 lines

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. 7d ago First seen · 113 lines · 2,318 tokens per session scan A 2354e82398d7

Subscribe to this mod's changes

webnovel-handbook AGENTS.md is an instructions file published in the GitHub repository miserylee/webnovel-handbook (6 stars, last pushed 2mo ago), licensed MIT. It adds 2,318 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 2026-08-31.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens