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 znlgis/opengis-skills --skill pigit clone --depth 1 https://github.com/znlgis/opengis-skillsWrote 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/znlgis/opengis-skills/pi)<a href="https://agentmods.dev/skills/znlgis/opengis-skills/pi"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/pi/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/znlgis/opengis-skills/pi"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/pi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.01371 |
| Opus 5 | $0.00017 | $0.00685 |
| Sonnet 5 | $0.00007 | $0.00274 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
pi 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 11d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目地址： https://github.com/earendil-works/pi
官网 / 文档： https://pi.dev ｜ https://pi.dev/docs/latest
最新发布： 参见 GitHub Releases
许可证： MIT 最新版本： 参见 npm
概述
Pi 是一个面向工程化场景的 Agent Harness，不仅是单一 CLI。
@earendil-works/pi-coding-agent：交互式终端编码 Agent@earendil-works/pi-agent-core：Agent 运行时（工具调用 + 状态管理）@earendil-works/pi-ai：统一多模型 Provider API@earendil-works/pi-tui：终端 UI 渲染库
适用场景：
- 终端内多步代码任务（读改代码、执行命令、追踪上下文）
- 自建可扩展 Agent（Extensions / Skills / Prompt Templates）
- 需要模型供应商可替换、可审计、可容器化的团队环境
环境与安装
前置要求
- Node.js
>=22.19.0 - npm（或等价 Node 包管理器）
常用安装方式
# 全局安装 coding agent CLI
npm install -g @earendil-works/pi-coding-agent
# 验证版本
pi --version
如需源码开发：
git clone https://github.com/earendil-works/pi.git
cd pi
npm install --ignore-scripts
npm run build
上游仓库是 monorepo，官方开发流程以
npm install --ignore-scripts、npm run build、npm run check为主。
核心能力速览
| 能力 | 说明 |
|---|---|
| 多模型统一接入 | OpenAI / Anthropic / Google 等 Provider 统一抽象 |
| Agent 运行时 | 工具调用、会话状态、任务分解与执行 |
| CLI + TUI | 终端交互式编码体验，适配日常研发流程 |
| 可扩展机制 | Extensions、Skills、Prompt 模板、主题 |
| 容器化方案 | Gondolin / Docker / OpenShell 等隔离模式 |
| 工程化发布 | Monorepo + release 流程 + 依赖锁定策略 |
命令参考
Pi 是最小化的 Agent Harness，CLI 主要用于验证安装。以下为基本探测命令：
pi --help
pi --version
开发仓库常用校验命令（在 pi 源码目录）：
npm run build
npm run check
npm run test
典型工作流
1) 本地终端编码助手
- 在项目目录启动
pi - 让 Agent 分析需求并分步执行
- 审阅改动与命令输出
- 人工确认后提交
2) 团队扩展能力
- 基于 Extensions 定义团队工具接入方式
- 把可复用提示流程沉淀为 Skills
- 在仓库内版本化管理配置，确保团队一致性
3) 强隔离执行
- 对高权限任务采用容器/沙箱模式
- 将内置工具与
!命令路由到隔离环境 - 保留宿主机 Provider 凭据与审计链路
安全与最佳实践
Pi 默认继承启动进程权限，不自带强制权限沙箱。生产建议：
- 对不受信任的任务启用容器化（Docker / Gondolin / OpenShell）
- 将敏感凭据放在最小权限环境变量中
- 固定依赖版本并审查 lockfile 变更
- 在 CI 中执行
npm ci --ignore-scripts+ 安全审计
常见问题（FAQ）
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.
- 11d ago First seen · 165 lines · 35 tokens per session scan A fb7f5b7ead6d
pi is a skill published in the GitHub repository znlgis/opengis-skills (60 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,371 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 2026-08-30.
Other skills, from other repositories
ax-signature
This skill helps an LLM generate correct DSPy signature code using @ax-llm/ax. Use when the user asks about signatures, s(), f(), field types, string syntax, fluent builder API, validation constraints, or type-safe inputs/outputs.
ax-cpp-ai
Use when writing C++ code with axllm for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-go-gen
Use when writing Go code with github.com/ax-llm/ax/packages/go for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-java-gen
Use when writing Java code with dev.axllm:ax for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
ax-cpp-llm
Use when writing C++ code with axllm for using the generated Ax package, factory functions, package docs, examples, and API reference.