Borrowing it
Nothing to install: this file belongs to yuanbw2025/storyforge. 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/yuanbw2025/storyforge/main/CLAUDE.mdgit clone --depth 1 https://github.com/yuanbw2025/storyforgeWrote 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/yuanbw2025/storyforge/claude-md)<a href="https://agentmods.dev/instructions/yuanbw2025/storyforge/claude-md"><img src="https://agentmods.dev/badge/instructions/yuanbw2025/storyforge/claude-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/yuanbw2025/storyforge/claude-md"><img src="https://agentmods.dev/badge/instructions/yuanbw2025/storyforge/claude-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 | $0.03685 | $0.03685 |
| Opus 5 | $0.01843 | $0.01843 |
| Sonnet 5 | $0.00737 | $0.00737 |
| Haiku 4.5 | $0.00368 | $0.00368 |
Grade A, and why
storyforge CLAUDE.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 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StoryForge 项目开发宪法
版本:2.3.0 · 生效:2026-08-31 本文件是详细工程宪法;短入口为
AGENTS.md。产品方向首先服从docs/PROJECT-MASTER-CHARTER.md,文档裁决与读取范围服从docs/DOCUMENT-AUTHORITY.md和docs/CONTEXT-ROUTING.md。
1. 权威与裁决
冲突按以下顺序处理:
- 项目总纲;
- 当前产品地图、能力基线与路线图;
- 本宪法、架构、数据、Harness 与质量标准;
- 三注册表及代码契约;
- 具体产品契约、测试与当前实现;
- Git 历史和 WPS 历史归档。
旧 Blueprint、施工卡、完成报告、评测流水和旧路线图只用于追溯,不得覆盖现行总纲。发现当前代码与总纲冲突时,登记偏差并纠正代码,不能以“已经实现”为由反向改写产品边界。
2. 产品边界宪法
2.1 独立创作产品
- 分步骤长篇拥有完整的世界观、故事、角色、主支线、大纲、细纲、正文和长程记忆链,不依赖世界引擎才能工作。作者可显式把当前已确认内容一键派生为世界草稿或封存版本;派生保存来源与 revision,不改变长篇 owner,也不建立自动同步。
- 节点模式公开并组合同一条长篇生产链,是更自由、更细粒度、更可视和可调的操作超集;它可以有自己的图、节点配置和运行记录,但必须复用同一 Skill、上下文、采纳和领域数据。
- 短篇、小说转剧本、小说转漫画分别有自己的输入、计划、产物、状态、验证和版本;不能只是长篇页面开关或一次 Prompt。
- 短篇可显式派生世界;小说转剧本和小说转漫画当前保持独立,不建立“封装为世界”入口。
2.2 世界引擎
世界引擎是可编辑、可封存、可版本化、可用唯一编号引用的语义内容包。它可以只含部分世界观,也可以含故事、角色、主支线、大纲、细纲乃至正文。完整度是能力画像,不是必须填满的表单。
世界引擎不包含为具体衍生产品生产的图片、音乐、音效、配音、视频、UI 或排版资产。它提供外貌、地点、时代、风格等语义依据;媒资在上层产品生产阶段生成并归具体产品实例。
2.3 上层产品
跑团、角色聊天、AI 小镇和文字游戏通过“世界编号 + 不可变版本”单向读取世界引擎。每个上层产品必须拥有自己的:
- 配置与体验目标;
- 主 Agent 与专业生产能力;
- 内容、规则和媒资生产;
- 组装、验证、修复与不可变发行;
- 运行状态、记忆、存档和私域演化。
上层运行或私域演化不得自动回写共享世界。若作者希望把衍生内容变成新世界版本,必须启动独立、显式、由世界作者确认的再创作流程。
2.4 世界衍生产品的三阶段治理
世界引擎之上的产品必须遵守:
阶段一:世界引擎编辑并封存语义版本
→ WorldReference
阶段二:用户在具体产品内引用世界、填写专用设置、与主 Agent 定向并明确开始
→ ConfirmedProductBrief + ProductSourcePlan
阶段三:产品生产、媒资、组装、ProductRelease、运行与私域演化
阶段二属于具体产品。时长、章节、回合、结局或参与者等字段由产品自己定义,不建立覆盖所有产品的万能体验表。阶段三的演化触发属于产品功能;项目级只强制 ProductRelease 不可变、父版本/兼容可追溯、旧存档可定位且不回写世界。
世界读取统一的是 describe/search/read 协议、不可变版本、来源与遗漏,不是固定 payload。各产品用自己的需求适配器声明稳定的必读/选读、随目标变化的条件读取及禁止读取,再生成 SourcePlan;production 每个 run 只能在该 plan 锁定的 WorldRelease 内渐进读取并留 Context Manifest,发布时聚合 SourceManifest。Skill/Prompt 可帮助理解语义需求,但版本、权限和必读约束必须机器可校验。runtime 的新读取归 session/run 证据,不能改写旧 release。任何组件或产品 service 不得直接解析世界底表清单。
五种交接物是跨产品逻辑契约,不要求共用五张物理表。主 Agent 主要起草 ConfirmedProductBrief 和 ProductSourcePlan;系统根据用户选择的冻结版本生成/校验 WorldReference,根据真实 run manifests 聚合 ProductSourceManifest,并在发布时生成和冻结 ProductReleaseLineage。Agent 不能自报未发生的读取或伪造版本证据。
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 · +24 lines · +936 tokens per session ed85be66ad9e
- 10d ago First seen · 172 lines · 2,749 tokens per session scan A 8b7e5f2105ba
storyforge CLAUDE.md is an instructions file published in the GitHub repository yuanbw2025/storyforge (640 stars, last pushed today), licensed MIT. It adds 3,685 tokens to every session, about $0.0184 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.