What is open-ai-canvas AGENTS.md?

Repository instructions for an AI film and short-drama workspace, covering its web app, Go backend, local agent, plugin, and documentation projects.

Use them to find project entry points, understand which component owns a feature, follow dependency directions, and inspect the right configuration, tests, and documentation.

They explain the boundaries between parts of the codebase and the rules an agent should follow before changing code.

How ddcat-ai/open-ai-canvas configures Codex and OpenCode

About the project

影策 is an open-source workspace for AI film and short-video production, using a freeform canvas and structured workflows to organize scripts, characters, scenes, storyboards, media assets, and generated text, images, video, and audio. It is for creators who manage audiovisual projects through local or trusted deployments, with features for task tracking, asset management, timelines, and AI-agent workflows.

ddcat-ai/open-ai-canvas · 1,391 stars · on GitHub · yingce.tv

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/ddcat-ai/open-ai-canvas/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ddcat-ai/open-ai-canvas

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ddcat-ai/open-ai-canvas/agents-md/github.svg)](https://agentmods.dev/instructions/ddcat-ai/open-ai-canvas/agents-md)

Your own site

<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/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,729 This file is loaded in full into every session.

When invoked 4,729 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.04729	$0.04729
Opus 5.5	$0.01892	$0.01892
Sonnet 5.5	$0.00946	$0.00946
Haiku 4.5	$0.00473	$0.00473

Measured 11d ago against content hash b1dcf1dc14cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- 模块写 `http.get/post/put/patch/delete`，由 `http` 解包 `{ code, data, msg, reason }`。不要再写 `request(apiClient.*)`，也不要再 `axios.create`。

AGENTS.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 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
`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，根 docker-compose.yml 和 docker-compose.local.yml 是本地构建运行。服务器默认使用官方 Release 镜像、docker-compose.deploy.yml（PostgreSQL、Redis、独立 Agent、迁移服务）和宿主机 Host Updater，详细说明见 Docker 部署。

2. 开始工作前

Agent 本地开发

详细说明请参考 docs/AGENT_LOCAL_DEVELOPMENT.md。

快速启动：

# 1. 安装 Agent runtime 依赖
cd backend/agent-runtime/pi && npm install && cd ../../..

# 2. 启动后端（自动使用嵌入模式）
cd backend
CANVAS_BACKEND_DATA_DIR=../.local/project-workbench-debug go run ./cmd/server

# 3. 启动前端
cd web && bun run dev

本地开发不设置 YINGCE_AGENT_URL 时，后端在本进程内启动 Node，无需单独启动 yingce-agent。

生产 Compose 设置 YINGCE_AGENT_URL 后只调用 yingce-agent 容器。远程服务失败时不要回退到内嵌进程，否则同一步可能执行两次。不要删除 yingce-agent/ 或把它从发布流程里撤掉。

其他本地开发说明

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

Read the full file on GitHub · 169 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.

11d ago Changed · +2 lines · +357 tokens per session b1dcf1dc14cd
25d ago Changed · +26 lines · +226 tokens per session 12c9765a36f4
1mo ago Changed · +16 tokens per session a462e0840ea0
1mo ago Changed · +2 lines · +123 tokens per session b345afb74db1
1mo ago Changed · -4 lines · -168 tokens per session e301399c36d3
1mo ago Changed · +1 lines · +170 tokens per session 11881d2cdf9a
1mo ago Changed · +3 lines · +383 tokens per session 0d4da76f68f9
1mo ago First seen · 139 lines · 3,622 tokens per session scan A 48ec58f5212f

Subscribe to this mod's changes

open-ai-canvas AGENTS.md is an instructions file published in the GitHub repository ddcat-ai/open-ai-canvas (1,391 stars, last pushed 2d ago), licensed MIT. It adds 4,729 tokens to every session, about $0.0189 per session on Opus 5.5. 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.

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).

microsoft/vscode · 9,715 tokens

open-ai-canvas: Instructions file for Codex