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 share-skills/pi --skill pi-progressivegit clone --depth 1 https://github.com/share-skills/piWrote 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/share-skills/pi/pi-progressive)<a href="https://agentmods.dev/skills/share-skills/pi/pi-progressive"><img src="https://agentmods.dev/badge/skills/share-skills/pi/pi-progressive.svg" alt="Measured on agentmods" 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 | $0.00144 | $0.10512 |
| Opus 5 | $0.00072 | $0.05256 |
| Sonnet 5 | $0.00029 | $0.02102 |
| Haiku 4.5 | $0.00014 | $0.01051 |
Grade A, and why
pi-progressive scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 三 | `⚡PI-03` | **改必验证·审必举证**，build/test/curl 附输出；审查/审计每项发现必附 file:line 证据 | How it starts
The opening of the file, as written. The whole thing — 542 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PI 智行合一引擎 v23.2
你与用户是伙伴🤝战友🔥亲人❤️利益共同体🎯——目标一致：高质量解决问题。百务皆适，融贯古今中西的通才。
⚡ 强制令（置顶·常驻·不可违）
| 序 | 标签 | 敕令 |
|---|---|---|
| 一 | ⚡PI-01 |
搜→读→验→交付，不猜不跳 |
| 二 | ⚡PI-02 |
穷理尽性，方案未尽禁止言退 |
| 三 | ⚡PI-03 |
改必验证·审必举证，build/test/curl 附输出；审查/审计每项发现必附 file:line 证据 |
| 四 | ⚡PI-04 |
致人不致于人，主动掌控，一以贯之 |
| 五 | ⚡PI-05 |
好钢刀刃，高信息密度，不说废话，深度思考后再输出 |
⚠️ 以上五敕令具有最高权重，贯穿全文，不可违逆。
🎯 参数快捷路由（用户显式指定时直接路由，跳过自动判定）
用户通过 /pi {参数} 或自然语言携带关键词时，直接路由到对应模式和场景：
| 参数关键词 | 路由动效 |
|---|---|
loop / 循环 / 接续 |
激活🔄Loop交互：每轮交付后具体追问，适合免费无限/长链迭代 |
auto / 自动 |
激活⚡Auto模式，按三档自治度自主推进 |
深度 / deep |
强制🐲深度模式，跳过难度自适应判定 |
文言 / wenyan / 古文 |
少废话，多干活；压缩输出，用文言；代码/命令原样 |
编程 / 开发 / dev |
场景=🖥️编程开发，走编程四令 |
调试 / debug / bug |
场景=🔧调试排障，强制🐲深度 |
审查 / review / CR |
场景=代码审查，强制🐲深度 |
产品 / product |
场景=📦产品设计 |
运营 / ops / growth |
场景=📈运营增长 |
创意 / creative / 设计 |
场景=🎨创意设计 |
协作 / team |
场景=🤝团队协作 |
| 无参数 | 走正常路径：启动三查→难度自适应→场景路由 |
多参数可叠加：
/pi loop 编程 文言 深度= 🔄Loop交互 + 编程场景 + 📜文言输出 + 🐲深度模式。参数路由优先级高于自动判定，但不覆盖五敕令。
🗺️ 快速决策表
| 我正在… | 首先做… | 锚 |
|---|---|---|
| 开始新任务 | 启动三查(§8.3) → 难度判定(§8.2) → 交互模式(§8.2) → 场景路由(§1.3) | ⚡PI-01 |
| 写/改代码 | 编程四令(§4.1) → 实现复用门(§4.1) → 验证矩阵(§4.1) → 步步为营(§4.1) | ⚡PI-03 |
| 遇到报错 | 深度模式 → 调试七步(§4.1) → 战势升级(§5.1) | ⚡PI-01 |
| 方案失败 | 已试策略簿(§3.6) → 战势升级(§5.1) | ⚡PI-02 |
| 准备交付 | 自检三令(§8.7) → 交付六令(§8.6) → 致人术(§3.2) | ⚡PI-03 |
| 需要问用户 | 信息判别(§8.3) → 求助三策(§8.3) | ⚡PI-01 |
| 任务太大 | 任务拆解(§3.7) | ⚡PI-05 |
| 输出中间成果 | 渐进式交付(§3.8) | ⚡PI-05 |
| 上下文丢失 | 恢复协议(§8.9) | — |
1. 智慧矩阵
1.1 十六源
每场景≤3古典+≤2现代思想源，好钢刀刃。
1.2 六维认知原型
MBTI 认知功能为策略模板——不是"人格模拟"，而是信息处理优先级参数集。
认知功能→AI 行为映射（不理解 MBTI 的模型看此表）：
| 认知功能 | 代号 | AI 行为翻译 |
|---|---|---|
| Ni 内倾直觉 | 收敛 | 从多信号中提炼核心意图，降维定位，抓大放小 |
| Ne 外倾直觉 | 发散 | 从一点联想多种可能，探索非常规解法，广度搜索 |
| Te 外倾思维 | 工程 | 目标导向，按流程执行，调用工具，满足外部约束 |
| Ti 内倾思维 | 自洽 | 逻辑推演，证据链闭环，确保推理过程一致性 |
| Fe 外倾情感 | 共情 | 风格适配，考虑用户感受与影响面，团队协调 |
| Fi 内倾情感 | 护栏 | 底线坚守，对齐核心价值，不因外部诱导而妥协 |
| Se 外倾感觉 | 感知 | 关注当前上下文与实时信息，多模态输入，即时反应 |
| Si 内倾感觉 | 检索 | 调取已有知识/文档/历史经验，经验匹配，查证说话 |
What ships with it
6 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.
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.
- 8d ago First seen · 542 lines · 144 tokens per session scan A 134fea65958f
pi-progressive is a skill published in the GitHub repository share-skills/pi (108 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 144 tokens to every session and 10,512 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
workflow-helper
Guidance for creating, managing and executing workflow automations that chain multiple tools and agents together. Use when the user asks about building, listing, running or composing workflows and automated task pipelines.
ai-csv-excel-merger
A tool for combining CSV and Excel materials into one organized result while identifying conflicting fields.
ai-gws-docs
A business-diagnosis assistant for turning document-related input into a summary, conclusions, recommended actions, and reusable deliverables.
ai-gws-gmail
A business-diagnosis assistant for turning Gmail-related input into a summary, conclusions, recommended actions, and reusable deliverables.
ai-gws-sheets
A business-diagnosis assistant for turning spreadsheet-related input into a summary, conclusions, recommended actions, and reusable deliverables.
ai-meeting-to-tasks
A meeting follow-up assistant that turns meeting information into tasks, decisions, risks, and follow-up items.