Borrowing it
Nothing to install: this file belongs to ddcat-ai/open-ai-canvas. 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/ddcat-ai/open-ai-canvas/main/AGENTS.mdgit clone --depth 1 https://github.com/ddcat-ai/open-ai-canvasWrote 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/ddcat-ai/open-ai-canvas/agents-md)<a href="https://agentmods.dev/instructions/ddcat-ai/open-ai-canvas/agents-md"><img src="https://agentmods.dev/badge/instructions/ddcat-ai/open-ai-canvas/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 | $0.03622 | $0.03622 |
| Opus 5 | $0.01811 | $0.01811 |
| Sonnet 5 | $0.00724 | $0.00724 |
| Haiku 4.5 | $0.00362 | $0.00362 |
Grade A, and why
open-ai-canvas AGENTS.md scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 复用现有 `axios.create`；不要新增 `httpClient`、平行响应解包器或业务模块自己的 axios 实例。 How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件是影策仓库中 AI、自动化工具和协作者的工作约定。用户当前任务优先于本文件；本文件优先于个人习惯。所有结论应能回溯到代码、配置、测试、日志或文档，不用历史印象替代现状。
1. 项目边界
影策（ddcat-ai/open-ai-canvas）是面向 AI 影视与短剧创作的工作台，当前仍在快速开发。公开接口、数据结构和部署配置可能直接调整；除非任务明确要求，不为旧字段、旧 API 或旧数据增加兼容层。
仓库由几个边界清晰但可独立运行的单元组成：
| 单元 | 技术栈 | 入口 | 责任 |
|---|---|---|---|
web/ |
Vite、React 19、TypeScript、React Router、Ant Design、Tailwind、Zustand、TanStack Query | web/src/application.tsx、web/src/router.tsx |
工作区 UI、画布交互、浏览器缓存、API 调用和模型协议适配 |
backend/ |
Go 1.25、Gin、GORM、SQLite/PostgreSQL、Redis 协调 | backend/cmd/server/main.go |
登录、权限、业务 API、任务队列、资源、模型中转和后台管理 |
canvas-agent/ |
Node.js 18+、TypeScript、Express、MCP SDK、Codex SDK | canvas-agent/src/index.ts |
本机 Agent、MCP、画布会话桥接和本地渠道 |
plugins/yingce/ |
Codex App 插件清单和 skills | .codex-plugin/plugin.json |
将 Canvas Agent MCP 接入 Codex App |
docs/ |
Next.js、Fumadocs、MDX | docs/content/docs/ |
面向用户和开发者的专题文档；构建配置见 docs/source.config.ts |
根目录的 Dockerfile 构建前端静态镜像；nginx.conf 托管 SPA 并代理后端。docker-compose.dev.yml 是源码热更新开发编排，docker-compose.local.yml 是本地构建运行，docker-compose.deploy.yml 是 PostgreSQL + Redis 部署编排。
2. 开始工作前
- 先读取任务涉及的入口、调用方、配置、锁文件和相邻测试；先理解现状，再决定是否抽象或重构。
- 使用
rg/rg --files搜索，优先并行读取相关文件。不要为了“统一风格”改动无关模块、依赖、格式或用户已有修改。 - 先形成目标边界：页面负责什么、service 负责什么、handler/service/repository 如何分层、数据和错误如何流动。新增 helper 必须消除真实重复或隔离明确协议，不能只透传参数。
- 检查
git status --short。不覆盖、不回滚、不清理非本次产生的变更；不使用git reset --hard、git checkout --或宽范围删除。 - 手工编辑使用
apply_patch；默认使用 ASCII，业务中文或已有 Unicode 文件除外。注释只解释非直观算法、核心入口、安全边界和降级原因。
3. 目录职责和依赖方向
前端
web/src/pages/：路由页面及页面私有 hook/组件；页面协调流程，不直接拼装后端协议。web/src/layouts/：路由级布局、全局浮层和页面壳；不要在页面重复设置全局 body 状态。web/src/components/：真实跨页面复用的 UI 或交互能力；页面私有组件留在页面目录。web/src/services/api/：业务 API、模型渠道协议、资源 API；不依赖 JSX、路由或 AntD 提示。web/src/services/：文件、媒体、同步、缓存和生成任务等跨页面副作用。web/src/stores/：跨页面状态和持久化配置；页面临时状态留在页面，媒体大对象不进localStorage。web/src/lib/：纯函数、画布算法、协议转换、设计 token 和可独立测试的基础能力。web/src/styles/globals.css：变量、重置和必要的第三方覆盖；页面样式优先使用现有 token 或页面样式。
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.
- 8d ago First seen · 139 lines · 3,622 tokens per session scan A 48ec58f5212f
open-ai-canvas AGENTS.md is an instructions file published in the GitHub repository ddcat-ai/open-ai-canvas (832 stars, last pushed today), licensed MIT. It adds 3,622 tokens to every session, about $0.0181 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.