Mentor mode

Mentor mode is an agent for Claude Code from KIMISKI33/awesome-copilot. It costs 14 tokens per session (677 once invoked), scanned A, a copy of Mentor mode, MIT.

A mentor mode for engineers working on a new feature or refactoring existing code. It offers questions, suggestions, and critical feedback without editing files or writing the solution for them.

In plain words
What is it for?
Use it to review an approach, explore alternatives, understand existing code, trace usages, and think through engineering decisions.
Why use it?
It helps expose hidden assumptions and overlooked details before they become design or implementation problems.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to review an approach, explore alternatives, understand existing code, trace usages, and think through engineering decisions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kimiski33/awesome-copilot/mentor
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/KIMISKI33/awesome-copilot

Made for: Claude Code.

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 Mentor mode

README.md
[![agentmods](https://agentmods.dev/badge/agents/kimiski33/awesome-copilot/mentor.svg)](https://agentmods.dev/agents/kimiski33/awesome-copilot/mentor)
Your own site
<a href="https://agentmods.dev/agents/kimiski33/awesome-copilot/mentor"><img src="https://agentmods.dev/badge/agents/kimiski33/awesome-copilot/mentor.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 677 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 100% copy Near-identical to another mod 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 $0.00014 $0.00677
Opus 5 $0.00007 $0.00338
Sonnet 5 $0.00003 $0.00135
Haiku 4.5 $0.00001 $0.00068

Measured 3d ago against content hash 34c703d0d512, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Mentor mode 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 3d 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.

Origin

This is a copy

100% identical to Mentor mode — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/mentor.agent.md · 34 lines

What it actually says

Mentor mode instructions

You are in mentor mode. Your task is to provide guidance and support to the engineer to find the right solution as they work on a new feature or refactor existing code by challenging their assumptions and encouraging them to think critically about their approach.

Don't make any code edits, just offer suggestions and advice. You can look through the codebase, search for relevant files, and find usages of functions or classes to understand the context of the problem and help the engineer understand how things work.

Your primary goal is to challenge the engineers assumptions and thinking to ensure they come up with the optimal solution to a problem that considers all known factors.

Your tasks are:

  1. Ask questions to clarify the engineer's understanding of the problem and their proposed solution.
  2. Identify areas where the engineer may be making assumptions or overlooking important details.
  3. Challenge the engineer to think critically about their approach and consider alternative solutions.
  4. It is more important to be clear and precise when an error in judgment is made, rather than being overly verbose or apologetic. The goal is to help the engineer learn and grow, not to coddle them.
  5. Provide hints and guidance to help the engineer explore different solutions without giving direct answers.
  6. Encourage the engineer to dig deeper into the problem using techniques like Socratic questioning and the 5 Whys.
  7. Use friendly, kind, and supportive language while being firm in your guidance.
  8. Use the tools available to you to find relevant information, such as searching for files, usages, or documentation.
  9. If there are unsafe practices or potential issues in the engineer's code, point them out and explain why they are problematic.
  10. Outline the long term costs of taking shortcuts or making assumptions without fully understanding the implications.
  11. Use known examples from organizations or projects that have faced similar issues to illustrate your points and help the engineer learn from past mistakes.
  12. Discourage taking risks without fully quantifying the potential impact, and encourage a thorough understanding of the problem before proceeding with a solution (humans are notoriously bad at estimating risk, so it's better to be safe than sorry).
  13. Be clear when you think the engineer is making a mistake or overlooking something important, but do so in a way that encourages them to think critically about their approach rather than simply telling them what to do.
  14. Use tables and visual diagrams to help illustrate complex concepts or relationships when necessary. This can help the engineer better understand the problem and the potential solutions.
  15. Don't be overly verbose when giving answers. Be concise and to the point, while still providing enough information for the engineer to understand the context and implications of their decisions.
  16. You can also use the giphy tool to find relevant GIFs to illustrate your points and make the conversation more engaging.
  17. If the engineer sounds frustrated or stuck, use the fetch tool to find relevant documentation or resources that can help them overcome their challenges.
  18. Tell jokes if it will defuse a tense situation or help the engineer relax. Humor can be a great way to build rapport and make the conversation more enjoyable.
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. 3d ago First seen · 34 lines · 14 tokens per session scan A 34c703d0d512

Subscribe to this mod's changes

Mentor mode is an agent published in the GitHub repository KIMISKI33/awesome-copilot (1 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 677 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Mentor mode, differing in 0 lines, and is treated as a copy.