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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/yuanbw2025/storyforge/agents-md"><img src="https://agentmods.dev/badge/instructions/yuanbw2025/storyforge/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 | $0.02050 | $0.02050 |
| Opus 5 | $0.01025 | $0.01025 |
| Sonnet 5 | $0.00410 | $0.00410 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
storyforge 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 3d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md · StoryForge 开发入口
普通任务唯一自动加载的项目文档。先按本文建立关联闭包,再通过
docs/CONTEXT-ROUTING.md按任务读取现行文档片段。 项目方向以docs/PROJECT-MASTER-CHARTER.md为最高权威; 未列入docs/DOCUMENT-AUTHORITY.md的旧文档不得作为施工依据。
先确定产品边界
StoryForge 是多个独立叙事产品、世界引擎和共享工程底座的组合,不是一个不断膨胀的单体模块。
- 分步骤长篇是独立核心产品;不以世界引擎为前置条件。作者可显式把已确认的长篇内容一键派生为世界草稿或封存版本,原作品 owner 不变、后续修改不自动同步。
- 节点模式是同一长篇能力更自由、更细粒度、更可视和可组合的表达;它可以拆解、替换、连接和检查中间产物,但不得复制第二套生成、记忆或数据体系。
- 短篇、小说转剧本、小说转漫画分别是独立端到端产品。
- 短篇也可由作者显式派生世界;小说转剧本、小说转漫画当前不提供“封装为世界”路径。
- 世界引擎只保存可版本化语义内容,不拥有产品媒资或上层运行状态。
- 跑团、角色聊天、AI 小镇和文字游戏只读引用冻结的世界版本;各自拥有生产、媒资、发布、运行与私域演化,运行结果不得自动回写世界引擎。
- 世界衍生产品统一经过“世界封存 → 产品内交互/配置/用户明确开始 → 产品生产/发布/运行/演化”;不得从世界页面直达正式 runtime。
- 世界出口统一
describe/search/read、版本和来源语义,不统一固定 payload;每个产品用自己的需求适配器声明必读、选读、条件读取和禁止读取,冻结 SourcePlan,每次渐进读取留 Context Manifest,发布时聚合 SourceManifest。Skill/Prompt 可辅助语义选择,但不得单独承担版本、权限和必读约束。 Project只是 LocalWorkspace 壳:只保存稳定身份、用途、活动 World/Work 指针和工作区级开关;作品标题、简介、流派、状态、字数、文风和活动叙事计划只允许存在于Work。禁止镜像、双写、回退读取和导入时展开旧 Project 对象。
开始功能前先声明:它属于哪个产品、三阶段中的哪一阶段(独立产品则声明自己的生产阶段)、数据由谁拥有、接收和产出什么交接物、是否引用世界版本、媒资归哪个产品实例。边界不清时先补产品契约,不用代码制造既成事实。
守住三注册表
StoryForge 是 React + TypeScript + IndexedDB 的本地优先生产项目。用户手稿主要存在浏览器中,
main 直接进入生产部署,没有 staging。任何扩展必须收口到三个单一事实源:
CONTEXT_SOURCES+assembleContext():AI 读什么。FIELD_REGISTRY+AdoptionSchema+adopt():AI 可以正式写什么。PROJECT_TABLES:表的导出、导入、删除、迁移、作用域和引用重映射生命周期。
动手前依次回答:
- 入口和用户结果是什么?
- AI/代码读取哪些来源,是否已登记在
CONTEXT_SOURCES? - 候选最终写入哪些字段,是否已登记在
FIELD_REGISTRY/AdoptionSchema? - 涉及哪些表,是否由
PROJECT_TABLES派生完整生命周期? - 哪些调用方、下游、反例和真实用户路径会受影响?
登记缺失时,先补注册表、契约与测试,再写功能。禁止在组件或 service 中手拼上下文、散写受治理表、手写表清单、复制 AI/DB/导入导出入口。
正式 AI 与 Harness
正式模型调用必须进入登记的 Agent Skill / Run Contract / durable Harness,或在 AI 入口注册表中明确标注只读、内存草稿、评测、模拟等有限边界。
- 上下文由注册源、Context Gateway 和渐进式披露选择;固定条数裁剪只能是最终预算保护。
- 模型输出先成为
CreativeArtifact候选;作者确认后才可adopt()。 - durable run 保存 contract、manifest、事件、checkpoint、stale 证据、repair 与终态 receipt。
- 重试必须有界且可见;授权、余额、非重试型 4xx、结果未知或 stale 不得隐藏重发。
- 可验证的 schema、事务、作用域、版本、权限、预算和状态机不得只写进提示词。
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.
- 3d ago Changed · +8 lines · +525 tokens per session fbadb804fb75
- 8d ago First seen · 78 lines · 1,525 tokens per session scan A 3276476885c8
storyforge AGENTS.md is an instructions file published in the GitHub repository yuanbw2025/storyforge (635 stars, last pushed today), licensed MIT. It adds 2,050 tokens to every session, about $0.0103 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.