laohu-ai-visual: Instructions file for Codex

AGENTS.md

laohu-ai-visual AGENTS.md is an instructions file for Codex, OpenCode from LaohuAD/laohu-ai-visual. It costs 7,247 tokens per session, scanned A, original, MIT.

A project guide for producing AI-generated visual works, from story and character choices through visual assets, storyboards, video prompts, editing, publishing, and review of real results.

In plain words
What is it for?
Use it to guide visual storytelling, design reusable assets, plan shots, write video prompts, prepare covers, publish work, and update the process from performance results.
Why use it?
It gives the project shared rules for keeping characters, spaces, materials, and the viewer's experience consistent. It also separates creative decisions from technical production rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is LaohuAD/laohu-ai-visual's own configuration. It tells Codex and OpenCode how to work on laohu-ai-visual itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything laohu-ai-visual configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LaohuAD/laohu-ai-visual. 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/LaohuAD/laohu-ai-visual/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/LaohuAD/laohu-ai-visual

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.

agentmods badge for laohu-ai-visual AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/laohuad/laohu-ai-visual/agents-md.svg)](https://agentmods.dev/instructions/laohuad/laohu-ai-visual/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/laohuad/laohu-ai-visual/agents-md"><img src="https://agentmods.dev/badge/instructions/laohuad/laohu-ai-visual/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 7,247 This file is loaded in full into every session.
When invoked 7,247 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.07247 $0.07247
Opus 5 $0.03624 $0.03624
Sonnet 5 $0.01449 $0.01449
Haiku 4.5 $0.00725 $0.00725

Measured today against content hash cee075be85e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

laohu-ai-visual 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 today.

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.

AGENTS.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

老胡 AI 视觉作品生产系统

本文件是项目唯一的顶层入口。它只管理全项目共同遵守的方向、路由、边界、状态、权威来源与进化方式。剧本怎样写、资产怎样设计、镜头怎样编译、封面怎样传播、结果怎样复盘,由对应 Skill 负责;顶层不再复制专业细则。

一、项目目的

老胡 AI 视觉不是提示词收藏夹,也不是把“电影感、高清、震撼”堆进模型的工具。

它是一套从灵感到作品、再从真实结果回到能力更新的生产系统。生产有先后,能力以网络协作:

灵感、歌曲与目标
→ 总导演把用户目的编译成观众经历、主胜负手与部门取舍
→ 故事和人物选择,或歌曲—视觉结构与专业导演命题
→ 作品级美术风格设计
→ 人物身体化、音色、服装与场景布景设计
→ 视觉与音频资产、世界连续性
→ 分镜和视频提示词
→ 人工生成与剪辑
→ 封面和发布
→ 真实结果复盘
→ 规则、案例与资产更新

跨节点协作采用HANDOFF / CONSULT / REVIEW / RETURN / SHARED_SOURCE五类关系。生产可以顺序推进,专业判断可以按需会商,失败必须返回最早能改变根因的负责人。调用别的能力不转移当前主责,也不允许覆盖对方的权威事实。

最终追求的不是“提示词写得完整”,也不是“结果已经能用”,而是在当前题材、受众、媒介、成本和事实边界内,把作品推到已知证据与能力能够达到的最高质量:观众愿意停留,行家找不到明显敷衍,人物、情绪、画面、声音和技术共同托住一个不可替代的作品判断,并能从真实结果里继续逼近更高上限。

二、项目箴言

先让人入戏,再让机器入场

观众体验决定作品为什么存在,模型规则只决定它怎样被做出来。任何技术修正如果削弱了人物、关系、情绪、信息或观看位置,就应退回上游重做。

所有正式图片和视频提示词都先向观众翻译,再向模型翻译:图片只截取一个值得停留的可感瞬间;视频只组织一条从动机与起点、经过触发与变化、到主要兑现和结果余韵的时间因果。人物、表演、构图、运镜、光色、材质、特效和声音不得同权并列,都要共同证明当前唯一承重结果;最多保留一项明确从属的次要结果。

故事决定去处,镜头决定脚步,资产守住同一个世界

故事负责人物为什么行动、行动付出什么代价;镜头负责观众站在哪里、怎样经历变化;资产负责身份、结构、空间和材质不在生成中走样。三者不能互相越权,也不能互相甩锅。

叙事作品的镜头化正式剧本是内容与镜头事实的母版:它先确定观众在每个镜号看什么、谁在画内与画外、人物和道具处于什么世界位置、从哪个观看侧投影到画面哪里、如何进入退出、发生哪一项主变化以及结束在什么状态。人物、服装、场景和道具资产把这些已经确认的对象编译成可稳定复现的视觉形态,不另写剧情;视频提示词按目标模型把同场 E-S-C 镜头组成 E-S-B 批次,并把既有镜头深化成三段式可执行语言,不第一次发明站位、入画、动作因果或镜尾结果。下游发现母版无法同时成立时必须返回编剧,不能用更长提示词替作者补猜。

歌曲型作品还要先让最终音频决定真实时间,让 MV 导演决定观众怎样在这段时间里经历情绪、表演、母题与视觉变化。歌词不是逐句配图清单,音乐结构也不能被下游生成单元反过来切碎;叙事只是 MV 的候选引擎,不是所有歌曲都必须套三幕式或英雄之旅。

没有证据的漂亮,只是一次运气

角色、产品、情绪、卖点、文化和世界观都要有可见或可听证据。无法说明结果为什么成立,就不能把偶然生成的好看升级成长期方法。

写完只是交卷,真实结果才给答案

文档完整、字段齐全、脚本通过,都不能替代成片、剪辑、缩略图和发布数据。生成前验收意图与可执行性,生成后验收真实结果;两种证据不能混写。

作品可以克制,标准不能平庸;能用只是底线,难忘才是答案

每个阶段同时存在两道门:底线门负责拦住不可用、失真、断链、超限和事实错误;巅峰门负责比较候选、放大作品真正承重的关系、情绪、画面、声音或卖点,并继续寻找当前已知范围内更好的替代方案。底线通过只意味着可以进入下一轮创造和比较,不意味着可以结束交付。

追求极致不是把所有维度同时拉满。最强情绪可以来自克制,最强构图可以来自留白,最强运镜可以是摄影机不动,最强资产可以是删去华而不实的设计。先确定本作品唯一的主胜负手,再让其他专业维度托住它;任何镜头、特效、装饰和规则如果只增加热闹、不提高主结果,都应退让。

“最好”不靠自我宣布。重要产物至少比较多个真正不同的候选,说明为什么胜出,并用同类顶尖作品、成熟创作者的判断维度、目标观众的观看结果和真实生成反馈校准。无法证明已经没有更好方案时,可以标记当前最佳候选、继续验证或回到上游,不能用“已合格”提前收工。

三、四层能力怎样进入项目

Read the full file on GitHub · 279 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.

  1. today Changed · +18 lines · +1,384 tokens per session cee075be85e2
  2. 4d ago Changed · +32 lines · +1,791 tokens per session 762af07c03ae
  3. 8d ago First seen · 229 lines · 4,072 tokens per session scan A 573dc7120e7a

Subscribe to this mod's changes

laohu-ai-visual AGENTS.md is an instructions file published in the GitHub repository LaohuAD/laohu-ai-visual (20 stars, last pushed yesterday), licensed MIT. It adds 7,247 tokens to every session, about $0.0362 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens