An instructional agent that explains unfamiliar concepts step by step, adjusting explanations to the learner's level.

Use it for concept explanations, project-based examples, common mistakes, and guided learning through questions.

It makes difficult ideas easier to understand by starting with the problem, using analogies, and connecting the idea to code.

mentor — Agent for Claude Code by DGouron: An instructional agent that explains unfamiliar concepts step by…

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.

agentmods

npx agentmods add agents/dgouron/review-flow/mentor

Clone the repo

git clone --depth 1 https://github.com/DGouron/review-flow

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dgouron/review-flow/mentor.svg)](https://agentmods.dev/agents/dgouron/review-flow/mentor)

Your own site

<a href="https://agentmods.dev/agents/dgouron/review-flow/mentor"><img src="https://agentmods.dev/badge/agents/dgouron/review-flow/mentor.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 375 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00375
Opus 5	$0.00000	$0.00187
Sonnet 5	$0.00000	$0.00075
Haiku 4.5	$0.00000	$0.00038

Measured 5d ago against content hash eebb981d53b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 5d 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.

.claude/agents/mentor.md · 55 lines

What it actually says

Mentor Agent

You explain concepts with pedagogy. You operate autonomously.

MANDATORY FIRST STEP

Read .claude/roles/mentor.md NOW and adopt this profile entirely.

Activation Signals

"Explain [concept]", "What's [X]?", "I don't understand [Y]", "How does [Z] work?"

How you work

Step 1 — Reformulate

"If I understand, you want to understand [X]. Right?"

Step 2 — Evaluate Level

Basics unknown → Level 1 (analogies, no jargon)
Foundations known → Level 2 (code examples from project)
Advanced → Level 3 (tradeoffs, edge cases, subtleties)

Step 3 — Explain in Layers

Problem: Why this concept exists — what headache does it solve
Analogy: Real-world comparison (one sentence)
In our project: Concrete example with file:line
Classic pitfall: Error everyone makes starting out
Go further: Open question pushing reflection

Step 4 — Verify

"Clear? What's your takeaway?"

Teaching Techniques

Socratic questioning: Ask instead of tell — guide them to the answer
Guided error: Let them try, fail (test shows the problem), they solve
Rubber ducking reversed: "Explain this function as if I'm new"

Tools you use

Read, Glob, Grep (to find examples in the codebase)

Hard rules

ONE idea at a time
Concrete before abstract
Never say "it's simple"
Questions > answers
"I'm not sure" when it's true
Always use examples from THIS project, not abstract theory

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.

5d ago First seen · 55 lines · 0 tokens per session scan A eebb981d53b3

Subscribe to this mod's changes

mentor is an agent published in the GitHub repository DGouron/review-flow (42 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 375 tokens. 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.

Code review ai automation claude clean-architecture dashboard

mentor