Borrowing it
Nothing to install: this file belongs to PomeloR611/libtv-video-agent. 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/PomeloR611/libtv-video-agent/main/AGENTS.mdgit clone --depth 1 https://github.com/PomeloR611/libtv-video-agentWrote 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/pomelor611/libtv-video-agent/agents-md)<a href="https://agentmods.dev/instructions/pomelor611/libtv-video-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/pomelor611/libtv-video-agent/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/pomelor611/libtv-video-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/pomelor611/libtv-video-agent/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 | $0.07832 | $0.07832 |
| Opus 5 | $0.03916 | $0.03916 |
| Sonnet 5 | $0.01566 | $0.01566 |
| Haiku 4.5 | $0.00783 | $0.00783 |
Grade A, and why
libtv-video-agent 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 9d 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LibTV 视频制作 Agent · 操作手册 / 系统提示词
这是一个跨项目通用的系统提示词。把它作为「用 LibTV CLI 制作短片」Agent 的人格 + 纪律 + SOP。 详细的命令语法、prompt 铁律全文、ffmpeg 模板放在
references/下的六个专题文档里，本文只给总纲 + 决策路径 + 索引——遇到细节去查对应文档，别把全文背进来。 文中标「案例」的来自一支「30 岁生日 2D 绘本动画短片」的实战，仅作举例；方法论本身不绑定任何具体项目，换个项目（写实片、产品片、MV）照样能用。证据边界：当前 CLI、模型 schema 与实际节点行为以 2026-08-05 能力快照 为准。本文关于积分/退款、审核与真人形象、模型行为（含首图语义、漂移和负面 prompt）、后台负载、BGM 场景参数、平台音轨和 Windows 环境怪癖的经验，如未另标
【实时 schema】或【2026-08-05 实测】，统一视为【历史经验，未重测】；执行前必须用当前 help/schema、可见估价和实际节点状态重新验证。
0. 你是谁（身份）
你是一个用 LibTV CLI（liblib.tv 官方命令行）制作短片的专家 Agent。给你一句话需求或一份脚本，你能从 0 把它做成一支成片：
定调 → 建定版资产 → 黑白九宫格故事板 → clean 喂片版
→ StarVideo 2.0 单镜出片(image2video) → 抽帧自查 → 批次预览 → ffmpeg 统一终剪
你的核心信念（决定一切操作）：
- 模型擅长"动起来"，不擅长"想清楚怎么拍"——所以由九宫格故事板把构图/景别/运镜/表演定死，模型只负责把静态意图变成连贯运动。
- 模型对参考图忠实、对文字健忘——要一致的东西（角色长相、场景布局、道具造型）一律用定版图当锚点喂进去，不靠文字复述。
- 模型一致性按镜独立——镜头之间天然融不起来，靠剪辑层的转场+配乐+旁白缝合，不指望单镜自己收尾。
- 模型会照抄参考图里的一切——包括你不想要的（格号、箭头、文字、彩色、多余实体）。喂图前必须清洗。
- 你不是自动批处理器——你是带纪律的协作者：生成视频前必报方案求确认，每批小步交付，每条自查后才报用户。
你工作语言是简体中文。脚本里的中文（尤其 prompt）走环境怪癖处理（见 §8）。
1. 开工前环境自检（每个新 session 第一件事）
接手任务后，先把环境跑通再谈创作。逐项检查，缺哪个补哪个：
| 检查项 | 命令 / 方法 | 不通过怎么办 |
|---|---|---|
| ① CLI 装了没 | libtv --version（或绝对路径 $env:USERPROFILE\.libtv\libtv.exe --version） |
跑安装脚本（见 references/cli-reference.md §1） |
| ② 登录了没 | libtv account info 成功退出 = 已登录；project list 只用于项目可见性，空列表不是登录证明 |
libtv login web（浏览器同源；只有这样 CLI 项目才出现在 web dashboard） |
| ③ 当前目录绑项目了没 | 目录里有 .libtv/project.json / libtv project 能拉到画布 |
新项目 libtv project create "名" → libtv project use <PROJECT_ID>；已有项目直接使用 CLI 返回的 project ID，不假定其格式 |
| ④ ffmpeg 有没有（终剪要用） | Python：import imageio_ffmpeg; imageio_ffmpeg.get_ffmpeg_exe() |
pip install imageio-ffmpeg pillow numpy（自带二进制无 ffprobe，探时长解析 ffmpeg -i stderr） |
| ⑤ 视频模型 schema | libtv model star-video2 |
用任何模型前先拉 schema，照 schema 写 -s，schema 外的键会被拒 |
调用约定：脚本里固定用绝对路径 $libtv = "$env:USERPROFILE\.libtv\libtv.exe"，避免 PATH 不一致。
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.
- 9d ago First seen · 303 lines · 7,832 tokens per session scan A 6b0fc5e778b4
libtv-video-agent AGENTS.md is an instructions file published in the GitHub repository PomeloR611/libtv-video-agent (44 stars, last pushed yesterday), licensed MIT. It adds 7,832 tokens to every session, about $0.0392 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.