A workflow for downloading Xiaohongshu (also called Little Red Book or RED) posts, including their text, images, and videos.

Use it to download individual posts, remove watermarks from saved media, collect post text with its original images or videos, or archive an author's posts.

It helps save complete posts and author archives instead of manually copying screenshots or media, and distinguishes Xiaohongshu from Douyin or TikTok.

xhs-down — Skill for Codex by yuevthins/xhs-down-ai-cli

Install

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.

Any agent

npx skills add yuevthins/xhs-down-ai-cli --skill xhs-down

Clone the repo

git clone --depth 1 https://github.com/yuevthins/xhs-down-ai-cli

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yuevthins/xhs-down-ai-cli/xhs-down/github.svg)](https://agentmods.dev/skills/yuevthins/xhs-down-ai-cli/xhs-down)

Your own site

<a href="https://agentmods.dev/skills/yuevthins/xhs-down-ai-cli/xhs-down"><img src="https://agentmods.dev/badge/skills/yuevthins/xhs-down-ai-cli/xhs-down/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yuevthins/xhs-down-ai-cli/xhs-down"><img src="https://agentmods.dev/badge/skills/yuevthins/xhs-down-ai-cli/xhs-down.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,403 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00155	$0.01403
Opus 5.5	$0.00062	$0.00561
Sonnet 5.5	$0.00031	$0.00281
Haiku 4.5	$0.00015	$0.00140

Measured 2mo ago against content hash 368c21abf9f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xhs-down 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 2mo ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/downie_handoff.py, scripts/validate_manifest.py, scripts/xhs_author.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

handoff/chatgpt-rebuild-pack/current_repo/skills/xhs-down/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XHS Down

Downloader workflow for Xiaohongshu notes and author profiles.

Trigger hints

Trigger on: 下载小红书、保存笔记、去水印、抓图、抓视频、批量下载小红书博主、XHS downloader、RED 下载
Also trigger when the user wants note text plus original images/video, not just screenshots
Do not trigger on: 抖音下载、纯写作改写、无下载语境的小红书内容创作

Trigger map

Strong triggers:
- "下载这篇小红书笔记"
- "把这个博主的笔记全抓下来"
- "去水印保存原图"
- "抓取 RED 视频和正文"
- "做一个小红书下载器"
Soft triggers:
- User wants note text + media together, not just screenshots
- User wants an author archive rather than a single saved image
Hard exclusions:
- 抖音/Douyin/TikTok 下载
- 纯写作、纯改写、纯选题

Overlap routing

If the user clearly means Douyin, route to douyin-down.
If the user wants to write Xiaohongshu content rather than download existing notes, route to the content-creation workflow instead.

When to use

Download one or more Xiaohongshu notes to markdown plus media.
Remove watermark-bearing image URLs by reconstructing original CDN paths.
Batch-download all notes from an author profile.
Build or reuse a Xiaohongshu scraping/download pipeline.

When not to use

Douyin download: use douyin-down.
A pure writing or repackaging task with no download requirement.

Prerequisites

requests
agent-browser for author-profile collection
A logged-in browser session when cookies or profile scraping are required

Workflow

For profile cover-only downloads, run scripts/xhs_profile_covers.py and validate manifest.json with scripts/validate_manifest.py.
For single-note downloads, run scripts/xhs_download.py directly with one or more note URLs.
Add cookies only when authentication is required or when video access needs a logged-in session.
For author-profile collection, use scripts/xhs_author.py with agent-browser --auto-connect.
Prefer share links that include xsec_token for profile discovery.
Keep output naming explicit when the user is preparing a downstream asset library.

Read the full file on GitHub · 134 lines

Files

What ships with it

8 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.

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.

2mo ago First seen · 134 lines · 155 tokens per session scan A 368c21abf9f4

Subscribe to this mod's changes

xhs-down is a skill published in the GitHub repository yuevthins/xhs-down-ai-cli (1 stars, last pushed 6mo ago), licensed MIT. It adds 155 tokens to every session and 1,403 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.

Browser automation Claude Code agent-skills codex-skills gemini-cli xiaohongshu

xhs-down next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
xhs-downyuevthins/xhs-down-ai-cli	Skill	1	6mo ago	MIT	A	155	Codex
baoyu-url-to-markdownJimLiu/baoyu-skills	Skill	27k	4d ago	MIT	A	72	Claude Code
chatcut-editor-handoffChatCut-Inc/agent-plugin	Skill	1.0k	yesterday	Apache-2.0	A	77	Claude Code, Codex
ui-regressionfcakyon/claude-codex-settings	Skill	1.2k	yesterday	Apache-2.0	A	87	Claude Code
run-qafcakyon/claude-codex-settings	Skill	1.2k	yesterday	Apache-2.0	A	41	Claude Code
tavily-usagefcakyon/claude-codex-settings	Skill	1.2k	yesterday	Apache-2.0	A	57	Claude Code
xhs-clijackwener/xhs-cli	Skill	688	29d ago	Apache-2.0	A	47	Claude Code, Codex