Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Sen-platotech/xiaohongshu-auto-ops-assistantnpx agentmods add skills/sen-platotech/xiaohongshu-auto-ops-assistant/content-workflowWrote 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/sen-platotech/xiaohongshu-auto-ops-assistant/content-workflow)<a href="https://agentmods.dev/skills/sen-platotech/xiaohongshu-auto-ops-assistant/content-workflow"><img src="https://agentmods.dev/badge/skills/sen-platotech/xiaohongshu-auto-ops-assistant/content-workflow/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/sen-platotech/xiaohongshu-auto-ops-assistant/content-workflow"><img src="https://agentmods.dev/badge/skills/sen-platotech/xiaohongshu-auto-ops-assistant/content-workflow.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 | $0.00045 | $0.00809 |
| Opus 5 | $0.00023 | $0.00404 |
| Sonnet 5 | $0.00009 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
xiaohongshu-content-workflow 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 10d 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
小红书内容生产工作流
这是一份供 Codex、Claude Code 等 Agent 使用的通用流程。它负责把素材变成可审核的内容包，不构成发布授权。
1. 先锁定输入
开工前确认：
- 内容形态：单书深读、主题书单或文章深读；
- 目标读者与核心论点；
- 可合法使用的封面、肖像或历史照片；
- 账号展示名、系列名与期数；
- 哪些事实、引文和数字需要来源核验。
不要编造缺失的书目信息、人物经历、统计数字或引文。真实人物、书封和历史材料优先使用权利清楚的原始素材，不用 AI 图冒充史料。
2. 结构化内容
推荐的七页节奏：
- 封面：明确主体 + 一个钩子；
- 背景：读者为什么需要知道；
- 人物、作品或问题脉络； 4–6. 三个核心发现或时间节点；
- 收束：把细节提升为一个可讨论的问题。
内容少时减少页数，不用空话填充。每张图只承担一个论点，标题、证据和结论要能对应。
3. 图卡生成
复制模板时保留 assets/templates/ 与 assets/tokens.css 的相对位置，修改 CSS 变量和占位内容，然后渲染：
mkdir -p 本期/assets/templates 本期/output
cp assets/tokens.css 本期/assets/tokens.css
cp assets/templates/card_generic.html 本期/assets/templates/card_01.html
python3 assets/render.py 本期/assets/templates/card_01.html 本期/output/01_封面.png
要求：
- 画布 1242×1660（3:4）；
- 正文移动端可读，不出现大块无意义留白；
- 图片必须注明来源或在交付说明中记录授权；
- 页面不硬编码真实账号，使用本期配置替换占位符；
- 渲染后逐张目检，检查溢出、错字、裁切和图文事实一致性。
总览图：
python3 tools/contact_sheet.py output/00_总览.png output/0*.png
4. 文案与合规复核
以 assets/copy_template.md 为结构参考，最终只保留一个标题、一份正文和不超过 10 个标签。
运行只读召回：
python3 assets/sensitive_check.py scan 发布文案.md build/card_*.html
命中不等于违规。逐项核对事实、语境、版权、隐私、医疗/金融等高风险表述；不得用拆字、拼音、符号或外语替换规避平台识别。无法判断时停止并交给真人。
5. 输出内容包
至少包含：
- 按发布顺序编号的 PNG；
00_总览.png；- 最终标题、正文和标签；
- 素材来源与许可说明；
- 合规召回及人工处理记录；
- 状态标记
GENERATE_ONLY。
如需进入发布流程，必须另行生成不可变审核单，并遵守根目录 AGENTS.md。任何内容或元数据变化都需要新版审核单与重新确认。
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.
- 10d ago First seen · 83 lines · 45 tokens per session scan A 556557ae434e
xiaohongshu-content-workflow is a skill published in the GitHub repository Sen-platotech/xiaohongshu-auto-ops-assistant (0 stars, last pushed 28d ago), licensed Apache-2.0. It adds 45 tokens to every session and 809 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
bilibili-upload
A workflow for using the sau command-line tool to log in to Bilibili, a Chinese video-sharing platform, check an account, and upload videos.
xhs_note
A workflow for creating a Xiaohongshu post, a Chinese image-first social-media note, with short copy, hashtags, and at least three matching vertical images.
review-video-with-pingfusi
Have any video reviewed by a real human, through iterative pingfusi review rounds. Use when asked to "review this video", "check the rendered video", "does this video match the prompt/brief", "what do people think of this ad/trailer/demo", or after rendering a Remotion composition or AI-generated clip that no test can…
surface
Surface-native display for AI agents, driven by the surface CLI. Use when the user says "surface this", "show me X", or "put it on my display/screen"; wants a live interactive UI, chart, or tool they act on; needs a question answerable from any device; or asks you to react to what they click — even while you're…
openprd-audio-evidence
A method for checking real audio and speech-related output. ASR, or automatic speech recognition, turns spoken audio into text and timestamps; the method also covers sound quality and subtitle timing.
asset-review-agent
Independently review source-extracted quote, viewpoint, hook, and structure candidates. Image and shot assets are outside automatic review and enter only after explicit user interaction.