Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/mythkiven/rednote-director-skill/agents-mdgit clone --depth 1 https://github.com/mythkiven/rednote-director-skillWrote 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/mythkiven/rednote-director-skill/agents-md)<a href="https://agentmods.dev/instructions/mythkiven/rednote-director-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/mythkiven/rednote-director-skill/agents-md.svg" alt="Measured on agentmods" 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 | $0.00713 | $0.00713 |
| Opus 5 | $0.00357 | $0.00357 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
rednote-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 6d 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.
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，优先维护根目录
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。
- 新增风格时必须新增一个
references/style-XX-*.md按需文件，并同步更新references/style_system.md索引。 - 任何输出都必须先判断内容，再选择风格。
- 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.md：Agent 的触发场景、工作流、默认输出格式、审查规则。agents/openai.yaml：Agent 客户端展示元数据；当 Skill 名称、定位或默认使用方式变化时同步更新。references/style_system.md：风格库索引、风格组合规则、内容类型到风格的映射表。references/style-XX-*.md：单个风格的完整定义、适用范围、版式结构、图像提示词模板和负面提示词。references/page_structure_rules.md：封面、内页、结尾页的页面结构规则。references/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。references/anti_patterns.md：用户不喜欢的风格和避免方法。assets/：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：
- 这篇内容是什么类型。
- 传播目标是什么。
- 读者应该产生什么情绪。
- 为什么选这个风格。
- 为什么不选某些风格。
- 封面如何抓点击。
- 内页如何递进并产生收藏价值。
- 每页的视觉方案如何落地。
- 图像生成提示词如何直接复制使用。
- 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 assets/style_extension_template.md 填完整，保存为新的 references/style-XX-*.md，再同步更新：
references/style_system.mdexamples/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/。
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.
- 6d ago First seen · 57 lines · 713 tokens per session scan A d1a7df8ff836
rednote-director-skill AGENTS.md is an instructions file published in the GitHub repository mythkiven/rednote-director-skill (35 stars, last pushed 2mo ago), licensed MIT. It adds 713 tokens to every session, about $0.0036 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
rig AGENTS.md
AGENTS.md instructions for githubnext/rig, covering agents.md, project overview, architecture, commands and code style.
serial-mcp-server CLAUDE.md
Instructions for Adancurusul/serial-mcp-server, covering claude.md, development rules, quality gates, build and run and cli surface.
diaolong-skill CLAUDE.md
Instructions for lj22503/diaolong-skill, covering claude.md — 雕龙 dragoncraft 项目规则（单 agent 模板 b）, 开工流程, 项目定位, 产出标准 and 进度跟踪.
AI-bounty-skill GEMINI.md
Gemini CLI instructions for aelf-hzz780/AI-bounty-skill, covering ai bounty claim extension, use this extension when and required steps.
skills CLAUDE.md
Claude Code instructions for mixedbread-ai/skills, covering mixedbread skills, repository structure, conventions, adding a new skill and testing a skill.
growmos AGENTS.md
Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.