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/lucasygu/redbook/claude-mdgit clone --depth 1 https://github.com/lucasygu/redbookWrote 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/lucasygu/redbook/claude-md)<a href="https://agentmods.dev/instructions/lucasygu/redbook/claude-md"><img src="https://agentmods.dev/badge/instructions/lucasygu/redbook/claude-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 | $0.00584 | $0.00584 |
| Opus 5 | $0.00292 | $0.00292 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
redbook CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — redbook CLI
Publishing
NEVER publish npm packages directly from local. Always use the npm-publish-cli agent to bump version and publish via CI. The GitHub Actions workflow (Publish to npm) handles publishing on push to main. Publishing locally races CI and causes workflow failures.
Dual publishing (automated):
- npm — publishes when
package.jsonversion changes on push to main - ClawHub — publishes when
SKILL.mdchanges on push to main (usesCLAWHUB_TOKENsecret)
Both are conditional jobs in .github/workflows/npm-publish.yml. Manual trigger via workflow_dispatch is also available.
Build & Test
npm run build— TypeScript compile + chmod- No test suite yet — verify manually with
redbook whoami
Project Structure
src/cli.ts— CLI entry point, 21 commands,getClient()is the single cookie→client funnelsrc/lib/client.ts— XHS API client (postComment,replyComment, etc.)src/lib/cookies.ts— Cookie extraction with Chrome profile auto-discoverysrc/lib/signing.ts— Request signingsrc/lib/analyze.ts— Viral note analysis and question detectionsrc/lib/reply-strategy.ts— Batch reply filtering, templating, rate-limited executionsrc/lib/template.ts— Viral content template extractionsrc/lib/health.ts— Note health check: level detection, sensitive words, tag countsrc/lib/render.ts— Card rendering (markdown → PNG via puppeteer-core, optional dep)SKILL.md— Skill documentation (serves both Claude Code and OpenClaw/ClawHub).github/workflows/npm-publish.yml— CI: build, npm publish, ClawHub publish
Render Command (Optional)
redbook render <file>— markdown → styled PNG cards using user's existing Chrome- Requires
puppeteer-coreandmarked(optional peer deps, lazy imported) - Uses Chrome at
/Applications/Google Chrome.app/...orCHROME_PATHenv var - No cookies/XHS API needed — purely offline
- HTML/CSS templates embedded as TypeScript template literals (no external files)
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 · 46 lines · 584 tokens per session scan A 42e060c95f1b
redbook CLAUDE.md is an instructions file published in the GitHub repository lucasygu/redbook (467 stars, last pushed 2mo ago), licensed MIT. It adds 584 tokens to every session, about $0.0029 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
xiaohongshu-skill AGENTS.md
Instructions for DeliciousBuding/xiaohongshu-skill, covering agents.md, safety, execution, development and architecture.
topology-gomoku AGENTS.md
AGENTS.md instructions for YinkaiYu/topology-gomoku, covering agents.md, 先确认工作位置, 身份与权限, 分支职责 and 平台专属适配.
redpress CLAUDE.md
Instructions for jackjin1997/redpress, covering redpress, 项目定位与边界, 核心产品原则, 架构 and 开发约定.
content-agent CLAUDE.md
Instructions for qiuxchao/content-agent, covering content agent, 技术栈, 启动方式, api 服务 and 前端（另一个终端）.
xiaohongshu-auto-ops-assistant AGENTS.md
AGENTS.md instructions for Sen-platotech/xiaohongshu-auto-ops-assistant, a project described as: 以人为最终责任节点的小红书内容生产、人工复核与受控发布工作流.
xhs-autopilot CLAUDE.md
Instructions for Jinsong-Zhou/xhs-autopilot, covering claude.md, project overview, setup, common commands and cover generation (pillow — basic).