RedBookSkills is a command-line automation tool for Xiaohongshu, also known as Xiaohongshu or RED, that publishes content and retrieves or interacts with platform data through Chrome DevTools Protocol. It is for automating posts, searches, account management, comments, reactions, and related data collection on Windows with Chrome. The catalogue skill and instruction provide an agent workflow for operating this tool.
Borrowing it
Nothing to install: this file belongs to white0dew/XiaohongshuSkills. 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/white0dew/XiaohongshuSkills/main/AGENTS.mdgit clone --depth 1 https://github.com/white0dew/XiaohongshuSkillsWrote 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/white0dew/xiaohongshuskills/agents-md)<a href="https://agentmods.dev/instructions/white0dew/xiaohongshuskills/agents-md"><img src="https://agentmods.dev/badge/instructions/white0dew/xiaohongshuskills/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 | $0.00691 | $0.00691 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
XiaohongshuSkills 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.
What it actually says
仓库指南
项目结构与模块组织
本仓库是一个用于小红书自动化的 Python Skill 包。
scripts/包含全部可执行逻辑：publish_pipeline.py（主流程）、cdp_publish.py（CDP 自动化与账号命令）、chrome_launcher.py（Chrome 生命周期管理）以及辅助模块（image_downloader.py、account_manager.py、run_lock.py）。config/accounts.json.example是账号与 Profile 的配置模板。docs/存放集成说明（例如docs/claude-code-integration.md）。images/publish_temp/是临时素材目录占位。- 根目录关键文件：
README.md、SKILL.md、requirements.txt。
文件修改 /工作流
- 当新增或者修改功能之后，注意同步修改 SKILL.md 以及 README.md
- 新增功能时，建议在 plan.md 中先规划好，再实现，然后优化其中的内容
构建、测试与开发命令
python -m venv .venv && source .venv/bin/activate：创建并激活本地虚拟环境。pip install -r requirements.txt：安装运行依赖。python scripts/chrome_launcher.py：启动启用 CDP 的 Chrome（有界面）。python scripts/cdp_publish.py check-login：检查当前登录状态。python scripts/publish_pipeline.py --headless --title "T" --content "C" --image-urls "https://example.com/a.jpg"：执行端到端发布流程。python scripts/chrome_launcher.py --kill：关闭测试浏览器。
代码风格与命名规范
- 遵循 PEP 8，使用 4 空格缩进，并为模块提供清晰 docstring。
- 函数/变量使用
snake_case，类使用PascalCase，并显式添加类型注解（如list[str]、str | None）。 - CLI 参数优先使用长参数名，
argparse说明保持清晰、可读。 - 日志输出沿用
[module]前缀风格，便于排查。 - 考虑到操作随机值，模拟人机交互，避免被系统检测
测试指南
当前仓库尚未配置自动化测试套件。提交 PR 前请完成冒烟验证：
- 启动或重启浏览器：
python scripts/chrome_launcher.py --restart - 验证登录：
python scripts/cdp_publish.py check-login - 先在测试账号执行非破坏流程（不加
--auto-publish）。 若新增自动化测试，请放在tests/目录下，文件命名为test_*.py，并补充运行说明。
安全与配置建议
- 禁止提交真实 Cookie、账号令牌或个人 Chrome Profile 路径。
- 本地账号配置请基于
config/accounts.json.example复制为未跟踪的config/accounts.json后再使用。
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.
- 7d ago First seen · 42 lines · 691 tokens per session scan A 8c18035e9dbe
XiaohongshuSkills AGENTS.md is an instructions file published in the GitHub repository white0dew/XiaohongshuSkills (3,401 stars, last pushed yesterday), licensed MIT. It adds 691 tokens to every session, about $0.0035 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.