xhs-visual-director-skill: Instructions file for Codex

AGENTS.md

xhs-visual-director-skill AGENTS.md is an instructions file for Codex, OpenCode from ziguishian/xhs-visual-director-skill. It costs 833 tokens per session, scanned A, original, MIT.

A set of maintenance and writing instructions for a Xiaohongshu visual-director agent, where Xiaohongshu is a Chinese social platform focused on image-and-text posts. It defines the files, design rules, templates, and review process the agent should follow.

In plain words
What is it for?
Use it to maintain the agent skill, plan multi-page Xiaohongshu posts, choose a visual style based on the content, create reusable templates and examples, and generate image deliverables after visual review.
Why use it?
It keeps the agent focused on concrete page structure, visual direction, typography, color, and image prompts instead of producing generic style advice.

Instructions file for CodexOpenCode

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

This is ziguishian/xhs-visual-director-skill's own configuration. It tells Codex and OpenCode how to work on xhs-visual-director-skill 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 xhs-visual-director-skill configures →

About the project

ziguishian/xhs-visual-director-skill is an agent skill for planning and generating multi-page Xiaohongshu image posts, including their visual style, layouts, image prompts, publishing copy, and quality checks. It is aimed at creators, product teams, designers, and personal brands that want to turn topics, drafts, screenshots, or product material into coordinated social-media graphics.

ziguishian/xhs-visual-director-skill · 1,321 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to ziguishian/xhs-visual-director-skill. 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/ziguishian/xhs-visual-director-skill/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ziguishian/xhs-visual-director-skill

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 xhs-visual-director-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ziguishian/xhs-visual-director-skill/agents-md.svg)](https://agentmods.dev/instructions/ziguishian/xhs-visual-director-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ziguishian/xhs-visual-director-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/ziguishian/xhs-visual-director-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 833 This file is loaded in full into every session.
When invoked 833 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 $0.00833 $0.00833
Opus 5 $0.00417 $0.00417
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00083 $0.00083

Measured 7d ago against content hash c3f61bc0e060, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

xhs-visual-director-skill 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 7d 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.

AGENTS.md · 62 lines

What it actually says

AGENTS.md

本项目不是“小红书文案模板库”,而是一个“小红书高级图文视觉导演 Agent Skill”。

维护原则

  • 修改这个 Skill 时,优先维护 skill/SKILL.md
  • 所有规则必须服务于“小红书高级图文视觉导演”这个定位。
  • 不要把 Skill 写成泛泛的写作助手。
  • 不要输出空泛审美词,例如只写“高级、科技、极简、好看”。
  • 所有示例都要具体到页面任务、信息层级、构图、配色、字体和图像提示词。
  • 所有模板都要可直接复制使用。
  • 中文是默认语言。
  • 文件结构必须清晰,新增内容要放到对应目录。
  • README.md 要告诉用户如何使用这个 Skill,而不是只介绍概念。
  • 风格库必须可扩展。
  • 新增风格时必须同时更新 docs/style_system.mdtemplates/image_prompt_template.md
  • 任何输出都必须先判断内容,再选择风格。
  • 完整图文项目必须先走苏格拉底式 10 问澄清,再生成多页图文规划和视觉规划;用户明确要求跳过时除外。
  • 当用户要求生成图文图片时,最终交付物必须是图片文件;默认先生成 1 张视觉确认图,确认后再生成整套最终图,不要停留在模板或提示词。
  • 不要默认套黑色科技风。
  • 不要把可读的风格判断报告写成隐藏思考链。

文件职责

  • skill/SKILL.md:Agent 的触发场景、工作流、默认输出格式、审查规则。
  • skill/agents/openai.yaml:Codex UI 元数据;当 Skill 名称、定位或默认使用方式变化时同步更新。
  • docs/style_system.md:风格库、风格组合规则、内容类型到风格的映射表。
  • docs/page_structure_rules.md:封面、内页、结尾页的页面结构规则。
  • docs/prompt_rules.md:图像生成提示词写法、负面提示词规则、文字区域规划。
  • docs/anti_patterns.md:用户不喜欢的风格和避免方法。
  • docs/socratic_questioning_protocol.md:完整图文项目前置 10 问澄清流程。
  • docs/visual_consistency_protocol.md:多页图文比例、版式、边距、页码和提示词一致性协议。
  • docs/final_image_generation_workflow.md:先生成视觉确认图、再批量生成最终图片的交付流程。
  • templates/:可复用输出模板。
  • examples/:可复用案例,新增案例必须具体、完整、可模仿。

输出底线

一个合格输出必须同时回答:

  1. 这篇内容是什么类型。
  2. 传播目标是什么。
  3. 读者应该产生什么情绪。
  4. 为什么选这个风格。
  5. 为什么不选某些风格。
  6. 封面如何抓点击。
  7. 内页如何递进并产生收藏价值。
  8. 每页的视觉方案如何落地。
  9. 图像生成提示词如何直接复制使用。
  10. 发布文案如何引导收藏、评论和关注。

新增风格要求

新增风格时,先使用 templates/style_extension_template.md 填完整,再同步更新:

  • docs/style_system.md
  • templates/image_prompt_template.md
  • examples/style_reference_notes.md

如果新增风格面向一个明确行业,例如外贸、电商、教育、咨询、文旅,至少补一个行业主题案例到 examples/

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. 7d ago First seen · 62 lines · 833 tokens per session scan A c3f61bc0e060

Subscribe to this mod's changes

xhs-visual-director-skill AGENTS.md is an instructions file published in the GitHub repository ziguishian/xhs-visual-director-skill (1,321 stars, last pushed 2mo ago), licensed MIT. It adds 833 tokens to every session, about $0.0042 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 · 5,182 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