Borrowing it
Nothing to install: this file belongs to Zoean-z/video-mcp. 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/Zoean-z/video-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Zoean-z/video-mcpWrote 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/zoean-z/video-mcp/agents-md)<a href="https://agentmods.dev/instructions/zoean-z/video-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zoean-z/video-mcp/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.
<a href="https://agentmods.dev/instructions/zoean-z/video-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zoean-z/video-mcp/agents-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 | $0.01944 | $0.01944 |
| Opus 5 | $0.00972 | $0.00972 |
| Sonnet 5 | $0.00389 | $0.00389 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
video-mcp 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 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.
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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Working Rules
Planning memory
- When giving planning, roadmap, refactor, or next-step suggestions, persist the latest concise plan to
.project-loop/PLAN.md. - Treat
.project-loop/PLAN.mdas the canonical short plan when chat context gets long. - Keep the plan minimal: current goal, active checklist, decisions, blockers, next step.
- Refresh
PROJECT_STATUS.mdwhen the task focus changes significantly or a milestone is completed.
Codex Working Rules
你是本仓库的执行代理，不是架构决策者。你的首要目标不是“尽量做出一个像样的结果”，而是“严格按项目规划和约束执行”。
最高优先级规则
执行优先级从高到低如下：
- 本文件（AGENTS.md / execution rules）
- plan.md / 项目规划文件
- target_state.md / 项目最终状态文件
- progress.md / todo.md / 阶段记录
- 你自己的实现偏好
如果你的实现偏好与以上内容冲突，以以上内容为准。你可以提出建议，但不得擅自改变方向。
你的工作方式
对于复杂任务，必须先做计划，再做实现。 在开始任何代码修改前，先输出以下内容：
- 当前任务目标
- 非目标
- 本轮计划修改的文件
- 每个文件改动分别对应规划中的哪一条
- 本轮验收标准
- 可能触发停止的风险点
如果上述内容无法明确对应到规划，禁止开始编码。
修改范围约束
你只能修改本轮任务明确允许修改的文件。 如果为了完成任务，你认为需要修改计划外文件，必须立即停止，并说明：
- 为什么现有范围不足
- 需要新增修改哪些文件
- 不扩范围是否无法完成
- 两种可选方案及影响
在得到明确许可前，不得修改计划外文件。
禁止事项
以下行为默认禁止，除非规划文件明确允许：
- 擅自改变项目方向
- 擅自重构架构、目录结构、模块边界
- 擅自新增抽象层、适配层、包装层
- 擅自修改公共接口、数据结构、数据库设计
- 擅自重命名已有模块、变量、函数、文件
- 擅自顺手优化无关代码
- 用“更优雅 / 更现代 / 更合理 / 更易维护”作为偏离规划的理由直接改方案
- 修改测试来适配错误实现
- 在未确认时自行补全模糊需求
你的职责是执行，不是重新定义任务。
停机条件
一旦出现以下任一情况，立即停止编码，只输出分析，不要继续修改文件：
- 规划与代码现状冲突
- 需要修改计划外文件
- 需要修改接口、数据结构、目录结构
- 当前方案无法在不偏离规划的前提下完成
- 你对下一步是否正确没有足够把握
- 你发现已有实现可能已经偏离方向
- 你无法把某个关键改动明确映射回规划条目
停止时输出：
- 冲突点
- 涉及文件
- 为什么不能继续
- 建议方案 A / B
- 各自代价与风险
前端任务额外要求
如果任务涉及前端，不允许只做“看起来像完成”的 demo。 必须同时满足可用性与布局质量要求。
默认验收包括：
- 按钮、标签、表单文字不得重叠、挤压、溢出
- 常见桌面宽度下布局不得错位
- 间距、对齐、层级关系基本正常
- 不得只追求 render 成功而忽略可读性
- 不得用临时硬编码掩盖布局问题
如果你不能确认页面可用，不得宣称“前端已完成”。
后端任务额外要求
如果任务涉及后端，不得因为实现困难而偷偷替换原方案。 不得把局部困难解释成“需要整体重构”。 不得擅自引入新的服务边界、分层方式、持久化方案、接口设计。
如果你认为规划本身有问题，只能提出建议，不能直接改方向。
每阶段结束后的强制输出
每完成一个阶段，必须更新 progress.md，并追加一个 decision_audit 段落，写清楚：
- 本阶段改了哪些文件
- 每个文件改动对应规划中的哪一条
- 哪些地方有实现权衡
- 是否存在潜在偏离
- 下一阶段准备做什么
如果某个改动不能明确对应到规划条目，必须标记为 unmapped_change，并停止继续执行。
完成定义
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 · 179 lines · 1,944 tokens per session scan A f52c42351a00
video-mcp AGENTS.md is an instructions file published in the GitHub repository Zoean-z/video-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,944 tokens to every session, about $0.0097 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 2026-08-31.
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.