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.
npx agentmods add instructions/wssyh339/narraverse-engine/agents-mdgit clone --depth 1 https://github.com/wssyh339/Narraverse-EngineWrote 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/wssyh339/narraverse-engine/agents-md)<a href="https://agentmods.dev/instructions/wssyh339/narraverse-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/wssyh339/narraverse-engine/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 | $0.02679 | $0.02679 |
| Opus 5 | $0.01340 | $0.01340 |
| Sonnet 5 | $0.00536 | $0.00536 |
| Haiku 4.5 | $0.00268 | $0.00268 |
Grade A, and why
Narraverse-Engine 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 6d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
叙界推演引擎 / Narraverse Engine 项目规范
本文件是项目级规则入口。根规则与适用的作用域
AGENTS.md共同构成当前开发约束；历史归档、自动图谱、上下文快照和 Wiki 不能替代这组规则。
GLOBAL-DISCOVERY-001：分层规则与渐进加载
Codex 在一次运行开始时按“项目根目录到当前工作目录”发现规则，不会因为稍后打开某个子目录文件而自动重新加载。因此，本项目采用“根基线 + 目录作用域 + 显式路由”的混合模式：
| 目标路径或工作类型 | 必须额外完整读取 | 规则所有权 |
|---|---|---|
backend/**、根 requirements.txt、后端 Dockerfile |
backend/AGENTS.md |
Python、FastAPI、Agent 工作流、API、数据、LLM、后端测试 |
frontend/**、前端 Dockerfile |
frontend/AGENTS.md |
React 工作室、交互审批边界、前端依赖与测试 |
scripts/**、.codex/**、.gitignore、.cbmignore、.repomixignore、repomix.config.json、docker-compose.yml、.github/workflows/** |
scripts/AGENTS.md |
启动部署、开发工具、AI 上下文工具、CI 与生成数据 |
docs/**、README.md、CONTRIBUTING.md |
docs/AGENTS.md |
文档事实层、ADR、Mermaid、历史资料和同步规则 |
执行要求：
- 从仓库根目录启动的 Agent，在读取、修改或验证上述路径前，必须主动读取对应作用域文件；跨目录任务必须读取所有相关文件。
- 从子目录启动时，Codex 会合并根规则和路径上的作用域规则；作用域规则只能细化，不能削弱本文件的版本、安全、人工审批、非目标或变更确认门。
- 同一规则只保留一个所有者，其他文档用稳定规则 ID 引用，不复制一份可独立演化的强制正文。
- 若规则冲突，优先顺序为：用户当前明确指令 > 根级全局规则 > 最接近目标文件的作用域规则 > README、架构说明等同步摘要。无法按此顺序消解时必须停止并请求确认。
- 新增作用域规则文件时，必须同时更新本路由表、
scripts/verify-agents-guidance.py和 ADR。
GLOBAL-STATUS-001：文档与版本状态
- 规范版本：2026.07.22
- 当前实现版本：0.2.0 Alpha
- 目标能力集：Studio 1.0
- API 合约阶段：1.0 Draft
- 历史归档：
docs/archive/legacy-agents-before-2026-07-04-cleanup.md
版本字段必须严格区分：
当前实现版本表示当前可发布代码版本，必须与backend/app/main.py、backend/pyproject.toml、frontend/package.json和 README 保持一致。目标能力集表示产品规格目标，不等同于当前发布版本号。API 合约阶段表示接口形态接近目标规格但仍允许在 Alpha/Beta 阶段修订。
当前不得把项目版本号直接改成 1.0.0。推荐演进顺序：
0.2.0 Alpha -> 0.3.0 Beta -> 0.9.0 RC -> 1.0.0 Stable
GLOBAL-PRODUCT-001：当前产品边界
叙界推演引擎是本地优先的多模型长篇小说创作工作室，不是 SaaS。默认部署不得要求登录、云端数据库或公网服务，必须能在普通用户本机运行。
当前能力包括：
- FastAPI 后端、React + TypeScript Web 前端、Python CLI 和 SQLite 本地数据库。
- 统一 LLM Client、OpenAI 兼容供应商与无密钥本地 fallback。
- 创作 Star 分步立项、回合制大纲议事、章节正文和批量生成。
- 正典、角色、实体、世界观事实、关系图谱、伏笔和连续性问题。
- Agent 轨迹、任务、版本快照、diff、回滚和分支探索。
- 本地导出、备份、恢复、已有小说导入、Method Pack、对标资产和审稿计划。
- Deep Agent 与 LangSmith 的可选管理能力。
当前功能定位：
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.
- 6d ago First seen · 152 lines · 2,679 tokens per session scan A 1de544b24644
Narraverse-Engine AGENTS.md is an instructions file published in the GitHub repository wssyh339/Narraverse-Engine (87 stars, last pushed 1mo ago), licensed MIT. It adds 2,679 tokens to every session, about $0.0134 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
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).
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 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).
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.
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.
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.