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 skills add iamzifei/red-publisher-skill --skill xiaohongshu-publishergit clone --depth 1 https://github.com/iamzifei/red-publisher-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/skills/iamzifei/red-publisher-skill/xiaohongshu-publisher)<a href="https://agentmods.dev/skills/iamzifei/red-publisher-skill/xiaohongshu-publisher"><img src="https://agentmods.dev/badge/skills/iamzifei/red-publisher-skill/xiaohongshu-publisher/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/skills/iamzifei/red-publisher-skill/xiaohongshu-publisher"><img src="https://agentmods.dev/badge/skills/iamzifei/red-publisher-skill/xiaohongshu-publisher.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 | $0.00075 | $0.03854 |
| Opus 5 | $0.00037 | $0.01927 |
| Sonnet 5 | $0.00015 | $0.00771 |
| Haiku 4.5 | $0.00007 | $0.00385 |
Grade A, and why
xiaohongshu-publisher 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 12d 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 — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xiaohongshu Publisher (小红书发布器)
Publish images and notes to Xiaohongshu (小红书) Creator Platform using agent-browser with CDP (Chrome DevTools Protocol) mode.
Architecture: CDP Mode
This skill uses CDP mode - connecting to an existing browser instance where the user is already logged in. This approach:
- Eliminates QR code scanning - User logs in once in their browser
- Leverages existing session - Uses the browser's cookies and auth state
- More stable - No need to manage auth state files
- agent-browser CLI - Simple command-line interface with
--cdpflag
⚠️ IMPORTANT: Draft Mode by Default
This skill ALWAYS saves notes as DRAFT by default. It will NEVER auto-publish.
Only click the "发布" (publish) button if the user EXPLICITLY requests immediate publishing with phrases like:
- "直接发布" / "立即发布" / "马上发布"
- "publish now" / "publish directly" / "publish immediately"
- "不要草稿，直接发" / "不存草稿"
If unsure, ALWAYS save as draft and let user review before publishing.
Prerequisites
1. Launch Chrome with Remote Debugging
Before using this skill, the user must launch Chrome with remote debugging enabled:
macOS:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222
Or create an alias in ~/.zshrc or ~/.bashrc:
alias chrome-debug='/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222'
Then simply run: chrome-debug
2. Login to Xiaohongshu
In the Chrome browser (with debug port), navigate to:
https://creator.xiaohongshu.com/publish/publish
Login using QR code scan with Xiaohongshu App. This only needs to be done once - the session persists in the browser.
Note: After login, you can minimize the browser window to the Dock. The browser must stay running (not closed) for CDP to work, but you don't need to see it.
3. Python Dependencies
pip install Pillow pyobjc-framework-Cocoa
agent-browser CDP Commands Reference
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 446 lines · 75 tokens per session scan A 8f8f7e6ae1e8
xiaohongshu-publisher is a skill published in the GitHub repository iamzifei/red-publisher-skill (11 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 3,854 once invoked, about $0.0004 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 skills, from other repositories
creating-bookmarklets
Creates browser-executable JavaScript bookmarklets with strict formatting requirements. Use when users mention bookmarklets, browser utilities, dragging code to bookmarks bar, or need JavaScript that runs when clicked in the browser toolbar.
using-webctl
Browser automation via webctl CLI in Claude.ai containers with authenticated proxy support. Use when users mention webctl, browser automation, Playwright browsing, web scraping, or headless Chrome in container environments.
fetching-blocked-urls
Retrieve clean markdown from URLs when webfetch fails. Converts pages via Jina AI reader service with automatic retry. Use when webfetch or curl returns 403, blocked, paywall, timeout, JavaScript-rendering errors, or empty content or user explicitly suggests using jina.
ai-media-generator
A workflow for turning ideas into prompts for AI-generated images, videos, and music across several media platforms. When needed, it can also send those prompts to the chosen platform through browser automation.
webapp-testing
Playwright toolkit for local web apps: navigate, click, fill forms, screenshots, console logs.
download-xhs-videos
A process for downloading a Xiaohongshu creator’s videos to a local folder. Xiaohongshu, also called RedNote, is a Chinese social-media platform.