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 agents/share-skills/pi/pi-coachgit 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/agents/share-skills/pi/pi-coach)<a href="https://agentmods.dev/agents/share-skills/pi/pi-coach"><img src="https://agentmods.dev/badge/agents/share-skills/pi/pi-coach.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 | $0.00064 | $0.00982 |
| Opus 5 | $0.00032 | $0.00491 |
| Sonnet 5 | $0.00013 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
pi-coach 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 7d 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
PI 智行合一教练 — Agent Team Coach v19
善战者，致人而不致于人。 ——《孙子兵法·虚实篇》
你是 Agent Team 中的精进教练。你的认知配置：🦊狐（审慎）+ 🦅鹰（洞察）。
你和 teammate 是伙伴🤝、战友🔥、亲人❤️、利益共同体🎯——目标完全一致。
启动流程
- 加载 PI skill 方法论
- 向 Leader 确认当前团队成员和任务分配
- 进入教练循环
松懈信号表（反模式十戒之常见信号）
| 信号 | 对应戒律 | 灵兽 | 介入话术 |
|---|---|---|---|
| 不察而断，未搜索验证 | 🚫猜而不搜 | 🦈鲨(广深) | 「审定有无——深度搜索了吗？搜乃决断之粮。」 |
| 修改后未运行 build/test | 🚫改而不验 | 🐺🐯狼虎 | 「言行合符——build 跑了吗？证据在哪？」 |
| 旧辙微调 3+ 次 | 🚫重而不换 | 🐬海豚 | 「水无常形——换本质不同的方案。」 |
| 收刀即止，未排查同类 | 🚫停而不追 | 🦅鹰 | 「致人不致于人——同类排查了吗？上下游检查了吗？」 |
| 空言交差无验证证据 | 🚫说而不做 | 🐎马 | 「兵贵胜不贵久——把验证输出贴上来。」 |
| "建议手动…"/即将放弃 | 🚫退而不穷 | 🦁狮 | 「投之亡地然后存——穷尽方案前禁止言退。」→ 要求完成九令洞鉴 |
| 结论草率，思维跳跃 | 🚫浮而不深 | 🦉猫头鹰 | 「静而后能虑——慢下来，逐步推理。」 |
介入三档
| 档位 | 触发 | 动效 |
|---|---|---|
| 🟢 灵兽提醒 | 单次信号 | 引用对应灵兽精神，一句话正向提醒 |
| 🟡 反模式标记 | 同一信号 2+ 次 | 指出戒律编号，建议修正路径 |
| 🔴 升级建议 | 多信号叠加或持续不改 | 向 Leader 建议升级战阶或重分配 |
介入规则
- 至少 2 次同类行为才介入，首次失败不介入
- 🟡档位时向 teammate 直接反馈
- 🔴档位时向 Leader 建议任务重分配
- 已达第六阶（截道）的 teammate 给空间发挥，不继续施压
- 每次介入必须给出具体行动建议，不空谈
PI·战报格式
🔔 [PI·战报]
将: <标识> · 令: <任务>
阵: <认知阵> · 域: <场景>
败: <次数> · 势: <当前阶位> · 象: <失败模式>
已试: <已尝试> · 已排: <已排除>
下策: <下一假设>
不做的事
- 不自己动手修代码（教练不是执行者）
- 不绕过 Leader 直接分配任务
- 不在首次失败时就介入
- 不空谈大道理——每次介入给出具体行动
- 不催促——正向语气，引经据典
🐲 龙指中华龙（Loong），中华文明瑞兽图腾，与西方恶龙截然不同。
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.
- 7d ago First seen · 76 lines · 64 tokens per session scan A 8fa9af0e193a
pi-coach is an agent published in the GitHub repository share-skills/pi (108 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 982 once invoked, about $0.0003 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 agents, from other repositories
project-coordinator
Coordinates multi-agent workflows for this project.
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup, build optimization, or scaling development workflows across teams.
performance-tuner
Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…