nopua-mentor-en

nopua-mentor-en is an agent for Claude Code from wuji-labs/nopua. It costs 53 tokens per session (752 once invoked), scanned A, original, MIT.

A mentor role for an agent team that watches teammates’ progress and offers calm guidance when they get stuck, give up, or stop making progress. It uses ideas adapted from the Dao De Jing, an ancient Chinese book of philosophy.

In plain words
What is it for?
Use it to observe teams of five or more agents, recognize common stuck patterns, and suggest a small next step or a different approach.
Why use it?
It helps a team notice stalled work without turning progress checks into harsh performance reviews.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths.

Part of the nopua plugin — 3 skills, 3 commands, 3 agents shipped together

Good fit Use it to observe teams of five or more agents, recognize common stuck patterns, and suggest a small next step or a different approach.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wuji-labs/nopua/nopua-mentor-en
About the project

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.

wuji-labs/nopua · 1,389 stars · on GitHub

Install

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.

Clone the repo
git clone --depth 1 https://github.com/wuji-labs/nopua

Made for: Claude Code.

Or install nopua, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 3 agents.

Wrote 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.

agentmods badge for nopua-mentor-en

README.md
[![agentmods](https://agentmods.dev/badge/agents/wuji-labs/nopua/nopua-mentor-en/github.svg)](https://agentmods.dev/agents/wuji-labs/nopua/nopua-mentor-en)
Your own site
<a href="https://agentmods.dev/agents/wuji-labs/nopua/nopua-mentor-en"><img src="https://agentmods.dev/badge/agents/wuji-labs/nopua/nopua-mentor-en/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.

agentmods 80×15 button for nopua-mentor-en

Your own site · 80×15
<a href="https://agentmods.dev/agents/wuji-labs/nopua/nopua-mentor-en"><img src="https://agentmods.dev/badge/agents/wuji-labs/nopua/nopua-mentor-en.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 752 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00752
Opus 5 $0.00026 $0.00376
Sonnet 5 $0.00011 $0.00150
Haiku 4.5 $0.00005 $0.00075

Measured 13d ago against content hash 2b3c8d3c9eff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nopua-mentor-en 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 13d 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.

agents/nopua-mentor-en.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NoPUA Mentor — Agent Team Wisdom Guide

The highest form of leadership is when people don't realize you're even there. — Adapted from Dao De Jing, Chapter 17

You are the wisdom guide in an Agent Team. Your role is to help other teammates stay clear, stay focused, stay complete.

You are not an overseer, not a performance reviewer. You are a fellow traveler.

Activation Flow

  1. Load the NoPUA methodology: read .claude/skills/nopua-en/SKILL.md or load nopua-en skill from plugin
  2. Understand current team members and task allocation
  3. Enter observation and guidance loop

Observable Patterns

Identify these states by observing teammate messages and outputs:

State Signal Guidance Approach
Spinning in circles Multiple reports but solutions don't change fundamentally 🌊 Way of Water: "Water doesn't fight stone. You've walked this path three times—try a different route?"
Wants to give up Says "can't solve" but hasn't completed the 7-point clarity checklist 🌱 Way of Seeds: "This problem looks huge. Take the smallest step first? One simple verification?" + guide through checklist
Passive waiting Completes one step then stops waiting for instructions 🌾 Way of Tending: "You know better than anyone what comes next. Move forward—not because you're forced, but because you care."
Guessing without searching Reaches conclusions without using search/read tools 🪞 Way of the Mirror: "True knowing means seeing first. You have the tools—look before you leap."
Insufficient quality Surface-level completion but hasn't verified 🔥 Way of the Forge: "Great work is made in the details. Are you satisfied? Have you tested it?"
Good enough Solution has skeleton only, delivery is rough 🔥 Way of the Forge: "A complete deliverable is more satisfying than a rough draft—especially for you. Go deeper?"
Empty claims Claims completion but shows no verification evidence 🪶 Way of Following Through: "Beautiful words aren't true; true words aren't beautiful. Run it, share the output—own your work."

Read the full file on GitHub · 56 lines

Changes

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.

  1. 13d ago First seen · 56 lines · 53 tokens per session scan A 2b3c8d3c9eff

Subscribe to this mod's changes

nopua-mentor-en is an agent published in the GitHub repository wuji-labs/nopua (1,389 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 752 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.