pi-bluebook — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by xiaomoBoy · Agent Tool · ★ 194

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is pi-bluebook safe to install? View the security audit →

About pi-bluebook

Pi 学习蓝皮书|Pi Coding Agent 中文学习路线 一本面向中文初学者的非官方 Pi Coding Agent(极简终端 Coding Harness)学习手册。从安装、登录和第一个可验收任务开始,逐步掌握 Session、Context、Skill、Extension、Subagent 与长期 Agent 工作流。 在线阅读 · 直接开始操作 · 系统阅读 · 反馈问题 · 繁體中文版 这是什么 真实学习路线:不从功能清单开始,而是先完成一件可以亲自检查结果的小任务,再逐步进入会话、上下文、扩展和长期工作流。 面向中文初学者:同时提供 macOS 与 Windows Git Bash 路径,命令、Pi 内部操作和任务文字分开说明。 强调独立验收:每一课按“场景 → 概念 → 实操 → 验收”展开,不把 Agent 自述“完成了”当作完成。 持续核验更新:版本、认证、模型和命令等易变化信息会标注核验日期,并以 Pi 官方文档 和 官方源码 为准。 当前内容与学习路径 2026 开放学习版的读者对象、阅读顺序、基本主张和内容边界已经确定;网站仍会持续校订错字、失效命令、链接和核验日期。当前导论、序章、五个模块、14 课和 8 个配套案例,已经形成从理解 Pi、完成第一次任务、管理会话与上下文,到扩展、分工、长任务和安全验收的完整学习路径。需要真实系统界面的进阶效果会明确标出,不用文字或伪图代替实测。 [2026 开放学习版说明](d

agent-harnessagent-skillsai-agentchinesecoding-agentcontext-engineeringlearning-pathpipi-agentpi-coding-agent

Quick Facts

Stars194
Forks14
LanguageMarkdown
CategoryAgent Tool
LicenseMIT
Quality Score64.8658576938996/100
Last Updated2026-09-14
Created2026-09-08
Est. Tokens~17k

Compatible Skills

These tools work well together with pi-bluebook for enhanced workflows:

  • pi-harness — semantic(0.69)+complementary+similar_pop (59%)
  • pi-extensions — semantic(0.60)+complementary+similar_pop (56%)
  • PiDeck — semantic(0.58)+complementary+similar_pop (55%)

pi-bluebook alternative? Top 6 similar tools

Looking for a pi-bluebook alternative? If you're comparing pi-bluebook with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • openclaw-docs by yeuxuan · ⭐ 744

    OpenClaw 中文文档站 | AI 智能体框架 源码剖析 安装教程 | WhatsApp Telegram Discord 飞书 多通道机器人

  • skillport by gotalab · ⭐ 406

    Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.

  • pi-tool-display by MasuRii · ⭐ 250

    Compact tool call rendering, diff visualization, and output truncation extension for Pi coding agent. Hides, c

  • cc-harness-skills by LearnPrompt · ⭐ 233

    Portable CC-inspired skills for memory, verification, multi-agent coordination, context compression, and proac

  • bitrouter by bitrouter · ⭐ 228

    The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight &

  • pi-rtk-optimizer by MasuRii · ⭐ 228

    Pi extension that optimizes RTK command rewriting and tool output compaction for the coding agent.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Markdown Agent Tools

Frequently Asked Questions

What is pi-bluebook?

pi-bluebook is Pi Coding Agent 中文学习蓝皮书:从安装与第一个可验收任务开始,逐步掌握 Session、Context、Skill、Extension、Subagent 与长期 Agent 工作流。. It is categorized as a Agent Tool with 194 GitHub stars.

What programming language is pi-bluebook written in?

pi-bluebook is primarily written in Markdown. It covers topics such as agent-harness, agent-skills, ai-agent.

How do I install or use pi-bluebook?

You can find installation instructions and usage details in the pi-bluebook GitHub repository at github.com/xiaomoBoy/pi-bluebook. The project has 194 stars and 14 forks, indicating an active community.

What license does pi-bluebook use?

pi-bluebook is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to pi-bluebook?

The top alternatives to pi-bluebook on Agent Skills Hub include openclaw-docs, skillport, pi-tool-display. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools