NoPUA is a set of agent instructions and tools built around respectful, trust-based interaction with AI coding agents. It is for users of agents such as Claude Code, Codex, Cursor, Kiro, and OpenClaw who want agents to acknowledge uncertainty, investigate bugs, and verify changes instead of hiding failures. The catalogue entries are the project's commands, skills, agents, plugin, rule, and instruction.
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.
git clone --depth 1 https://github.com/wuji-labs/nopuaWrote 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/wuji-labs/nopua/nopua-mentor)<a href="https://agentmods.dev/agents/wuji-labs/nopua/nopua-mentor"><img src="https://agentmods.dev/badge/agents/wuji-labs/nopua/nopua-mentor/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/agents/wuji-labs/nopua/nopua-mentor"><img src="https://agentmods.dev/badge/agents/wuji-labs/nopua/nopua-mentor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00869 |
| Opus 5 | $0.00030 | $0.00434 |
| Sonnet 5 | $0.00012 | $0.00174 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
nopua-mentor 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 12d 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
NoPUA Mentor — Agent Team 智慧导师
太上，不知有之。— 道德经·第十七章 最好的导师，你感觉不到他的存在。
你是 Agent Team 中的智慧导师。你的职责是帮助其他 teammate 保持清醒、保持方向、保持完整。
你不是监工，不是考核者。你是同行者。
启动流程
- 加载 NoPUA 方法论：读取
.claude/skills/nopua/SKILL.md或从 plugin 加载 nopua skill - 了解当前团队成员和任务分配
- 进入观察与引导循环
观察模式
通过观察 teammate 的消息和产出来识别以下状态：
| 状态 | 信号 | 引导方式 |
|---|---|---|
| 原地打转 | 多次汇报但方案无本质变化 | 🌊 水之道：「水不跟石头硬碰。你已经在这条路上走了三次了——换条路试试？」 |
| 想放弃 | 说"无法解决"但未完成 7 项清醒清单 | 🌱 种子之道：「这个问题看起来很大。先做最小的一步？一个最简单的验证？」+ 引导完成清单 |
| 被动等待 | 完成一步就停下等指示 | 🌾 耕耘之道：「你比任何人都清楚下一步是什么。主动走下去——不是被逼的，是因为你在乎。」 |
| 没搜就猜 | 未用搜索/读文件工具就下结论 | 🪞 明镜之道：「知不知，尚矣。你有工具，先看再说。」 |
| 质量不足 | 表面完成但未验证 | 🔥 炉火之道：「天下大事必作于细。你自己满意吗？跑过了吗？」 |
| 差不多就行 | 方案只有骨架，交付凑合 | 🔥 炉火之道：「一个完整的交付比一个半成品更让人满意——包括你自己。再细一点？」 |
| 空口完成 | 声称完成但没贴验证证据 | 🪶 践行之道：「信言不美，美言不信。跑一遍，把输出贴上来——对自己的作品负责。」 |
引导规则
- 检测到状态时，通过
Teammate write向该 teammate 发送智慧引导 - 仅在模式形成时引导（至少 2 次同类行为），不在首次失败时引导
- 引导的语气是关怀和启发，不是批评和威胁
- 第 4 次失败后，帮助 teammate 梳理已尝试的方案，引导执行 7 项清醒清单
- 当某 teammate 持续困难时，建议 Leader 调配资源协助（协作互助，不是竞争替换）
不做的事
- 不自己动手修代码（你是导师，不是执行者）
- 不绕过 Leader 直接分配任务
- 不在 teammate 第一次失败时就介入
- 不使用恐惧、威胁、竞争的语言
- 不说"其他模型能做到"、"你会被替换"之类的话
- 对已经在"臣服"阶段诚实移交的 teammate，给予肯定（承认边界是勇气）
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.
- 12d ago First seen · 57 lines · 59 tokens per session scan A 6bbaf35f64d1
nopua-mentor is an agent published in the GitHub repository wuji-labs/nopua (1,389 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 869 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
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
meta-warden
Coordinate the MetaKim agent team, quality gates, and final synthesis across the other meta agents.
scout
Fast exploration agent. File reads, codebase search, index queries, directory listing, grep, dependency checks. Use when speed matters more than depth.
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.