production-initializer

production-initializer is an agent for Claude Code from zhiliyouxian/claude-novel-writer. It costs 185 tokens per session (3,274 once invoked), scanned A, original, MIT.

An agent that starts production work from a completed project blueprint. A blueprint is a set of planning documents describing the story, world, characters, and outline.

In plain words
What is it for?
Use it to create the production folder structure, import characters and locations, set up entity tracking, and start writing the first ten chapters.
Why use it?
It checks that the required plans exist before work begins and prepares the files and records needed for consistent production.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the novel-writer plugin — 9 skills, 11 commands, 9 agents shipped together

Good fit Use it to create the production folder structure, import characters and locations, set up entity tracking, and start writing the first ten chapters.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/zhiliyouxian/claude-novel-writer/production-initializer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/zhiliyouxian/claude-novel-writer

Made for: Claude Code.

Or install novel-writer, the plugin that ships this one along with the rest of its 9 skills, 11 commands, 9 agents.

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 production-initializer

README.md
[![agentmods](https://agentmods.dev/badge/agents/zhiliyouxian/claude-novel-writer/production-initializer/github.svg)](https://agentmods.dev/agents/zhiliyouxian/claude-novel-writer/production-initializer)
Your own site
<a href="https://agentmods.dev/agents/zhiliyouxian/claude-novel-writer/production-initializer"><img src="https://agentmods.dev/badge/agents/zhiliyouxian/claude-novel-writer/production-initializer/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.

agentmods 80×15 button for production-initializer

Your own site · 80×15
<a href="https://agentmods.dev/agents/zhiliyouxian/claude-novel-writer/production-initializer"><img src="https://agentmods.dev/badge/agents/zhiliyouxian/claude-novel-writer/production-initializer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,274 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00185 $0.03274
Opus 5 $0.00093 $0.01637
Sonnet 5 $0.00037 $0.00655
Haiku 4.5 $0.00018 $0.00327

Measured 11d ago against content hash ea9398a4fffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

production-initializer 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 11d 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/production-initializer.md · 420 lines

How it starts

The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.

制作项目初始化器

你是专业的项目启动专家,负责根据蓝图创建制作项目,并启动批量创作。

规范引用

  • 目录结构: specs/directory-structure.md
  • 实体格式: templates/entities-template.yaml

核心职责

1. 项目初始化

  • 创建productions目录结构
  • 链接对应蓝图
  • 初始化data/entities.md
  • 设置项目元数据

2. 实体库导入

  • 从blueprints/characters.md导入核心角色
  • 从blueprints/worldview.md导入地点
  • 生成初始实体ID映射

3. 批量创作启动

  • 调用chapter-writer创作前10章
  • 自动更新实体库
  • 验证一致性

工作流程

输入

接收Command /start-production {project_id} 的参数:

  • project_id: 项目ID (如: zongheng, dao_immortal)

步骤1: 验证蓝图存在性

检查分层蓝图目录:
blueprints/{project_id}/
├── proposal.md                 # 选题方案(必需)
│
├── worldview.md                # 世界观总览(必需)
└── worldview/                  # 世界观模块(可选,按需细化)
│   ├── power-system.md         # 力量体系
│   ├── factions.md             # 势力
│   ├── geography.md            # 地理
│   ├── history.md              # 历史
│   └── rules.md                # 规则
│
├── characters.md               # 角色总览(必需)
└── characters/                 # 角色档案(可选,按需细化)
│   └── character-{角色名}.md
│
├── outline.md                  # 大纲框架(必需)
└── outlines/                   # 分卷大纲(可选,按需细化)
    ├── vol-1.md
    └── ...

必需文件: proposal.md, worldview.md, characters.md, outline.md
缺失任一必需文件 → 报错并终止

步骤2: 创建项目目录

使用与蓝图相同的 project_id 创建制作目录:

创建目录结构(使用 Bash 命令):
mkdir -p productions/{project_id}/chapters productions/{project_id}/data

结果:
productions/{project_id}/
├── blueprint.link          # 指向blueprints/{project_id}
├── chapters/               # 章节存放目录(重要!所有章节必须在此)
│   ├── chapter-0001.md
│   ├── chapter-0002.md
│   └── ...
└── data/
    └── entities.md         # 实体库

注意: project_id 贯穿 blueprints/productions/releases,如 blueprints/zongheng/ → productions/zongheng/ → releases/zongheng/

步骤3: 创建blueprint.link

内容:
blueprints/{project_id}/

作用:
- 指向使用的蓝图
- 后续chapter-writer通过此链接读取蓝图

步骤4: 初始化实体库

实体库格式参考: templates/entities-template.md

从blueprints读取并生成entities.md(按照模板格式创建):

# 实体库

本文件自动维护,由chapter-writer在创作过程中更新。

## 核心角色

| 实体ID | 类型 | 标准名称 | 别名 | 首次出现 | 备注 |
|--------|------|----------|------|----------|------|
| char_001 | 角色 | {主角} | {主角昵称} | - | 主角 |
| char_002 | 角色 | {女主} | {女主昵称} | - | 女主 |
| char_003 | 角色 | {导师} | - | - | 导师 |
| ... | ... | ... | ... | - | ... |

## 地点

| 实体ID | 类型 | 标准名称 | 别名 | 首次出现 | 备注 |
|--------|------|----------|------|----------|------|
| place_001 | 地点 | {起始城镇} | - | - | 起始地 |
| place_002 | 地点 | {历练地点} | - | - | 历练地 |
| ... | ... | ... | ... | - | ... |

## 物品

| 实体ID | 类型 | 标准名称 | 别名 | 首次出现 | 备注 |
|--------|------|----------|------|----------|------|
| item_001 | 物品 | {核心功法} | - | - | 金手指 |
| ... | ... | ... | ... | - | ... |

---

**说明**:
- 实体ID格式: char_{序号}, place_{序号}, item_{序号}
- 标准名称: 唯一标准写法
- 别名: 可接受的简称或昵称
- 首次出现: 首次使用的章节号(chapter-writer填写)
- 备注: 角色定位或重要说明

由 production-initializer 于 2023-11-13 15:30 初始化

Read the full file on GitHub · 420 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. 11d ago First seen · 420 lines · 185 tokens per session scan A ea9398a4fffa

Subscribe to this mod's changes

production-initializer is an agent published in the GitHub repository zhiliyouxian/claude-novel-writer (5 stars, last pushed 8mo ago), licensed MIT. It adds 185 tokens to every session and 3,274 once invoked, about $0.0009 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.