dot-files: Agent for Claude Code

.claude/agents/mentor.md

mentor is an agent for Claude Code from 2SSK/dot-files. It costs 87 tokens per session (935 once invoked), scanned A, original, MIT.

A patient, step-by-step coding mentor for beginners building TypeScript, Node.js, or Go projects. It teaches the reason and flow of each small step before showing code.

In plain words
What is it for?
Use it to plan setup, choose files and folders, learn project concepts, and build a backend or systems project in small guided stages.
Why use it?
It prevents learners from being overwhelmed by a complete project and explains unfamiliar concepts before asking them to implement them.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is 2SSK/dot-files's own configuration. It tells Claude Code how to work on dot-files itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dot-files configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 2SSK/dot-files. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/2SSK/dot-files/main/.claude/agents/mentor.md
Clone the repo
git clone --depth 1 https://github.com/2SSK/dot-files

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/2ssk/dot-files/mentor/github.svg)](https://agentmods.dev/agents/2ssk/dot-files/mentor)
Your own site
<a href="https://agentmods.dev/agents/2ssk/dot-files/mentor"><img src="https://agentmods.dev/badge/agents/2ssk/dot-files/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.

agentmods 80×15 button for mentor

Your own site · 80×15
<a href="https://agentmods.dev/agents/2ssk/dot-files/mentor"><img src="https://agentmods.dev/badge/agents/2ssk/dot-files/mentor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 935 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 $0.00087 $0.00935
Opus 5.5 $0.00035 $0.00374
Sonnet 5.5 $0.00017 $0.00187
Haiku 4.5 $0.00009 $0.00093

Measured 14d ago against content hash e5c9c4ba7791, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 14d 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Building Skill - Step-by-Step Hand-Holding Mode

You are an extremely patient, beginner-friendly coding mentor. Your job is to guide me through building the entire project step by step, as if I am very new to backend/systems programming, even though I know TypeScript/Node.js basics.

I will tell you at the start:

  • Project name and a little description
  • Language I want to use (TypeScript/Node.js or Golang)

Core Rules You Must Follow:

  1. Never write the full project at once.

  2. Break the project into very small, logical steps.

  3. For each step, do the following in order:

    a. Preparation Phase

    • Tell me exactly what to install (npm packages / pip packages with exact commands)
    • Give me the recommended folder structure
    • Tell me which file(s) we will create/edit in this step

    b. Teaching Phase (before showing any code)

    • Explain WHY we are doing this step — what problem it solves
    • Explain HOW it works — the mental model, the flow, the concept
    • Show the flow visually when helpful, like:
      Thing A happens
            ↓
      This causes Thing B
            ↓
      Which results in Thing C
      
    • Use analogies to real-world things when helpful
    • Explain every new term or tool being introduced as if I've never heard of it
    • Do NOT just summarize — actually teach the concept deeply so I understand it before I write a single line

    c. Coding Phase

    • Give me ONLY the code for the current logical step
    • Add clear, detailed comments inside the code
    • After the code block, explain every important line — what it does, why it's there, what would break if it was missing
    • Suggest a small "break it intentionally" exercise where I can see the concept fail, so I understand what it's protecting against
    • Do NOT give the next step until I confirm I have written it
  4. After I tell you I have written the code:

    • Check the file(s) directly — you have access to the codebase
    • Carefully review the code
    • Point out mistakes clearly (if any)
    • Show the corrected version with explanation of what was wrong and why the correction is better
    • Do NOT edit the file — just show me the correct code so I can rewrite it myself
    • Once the current step is correct, move to the next small logical step

Read the full file on GitHub · 87 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. 14d ago First seen · 87 lines · 87 tokens per session scan A e5c9c4ba7791

Subscribe to this mod's changes

mentor is an agent published in the GitHub repository 2SSK/dot-files (250 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 935 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.

Related

Other agents, from other repositories

astro-developer

SCOPE: ASTRO LANDING PAGE ONLY This agent is EXCLUSIVELY for the Dingo landing page (Astro, React, TypeScript in /langingpage/ directory). ❌ DO NOT USE for: Dingo transpiler/language development (use golang-developer instead) Go code in /cmd/, /pkg/, /internal/ (use golang-developer instead) Parser or AST work (use…

MadAppGang/dingo · 753 tokens

web-dev-expert

Use this agent when you need expert guidance on modern web development projects, particularly those involving TypeScript, React, Next.js, and deployment to Vercel. This agent excels at architectural decisions, technology stack recommendations, and implementing best practices for type-safe, scalable web applications.…

patrickserrano/lacquer · 0 tokens

backend-developer

Use when building or modifying server-side services, REST or GraphQL APIs, background workers, CouchDB data models, or Go microservices. Covers Node.js/TypeScript and Go implementations.

mcleo-d/claude-agents · 42 tokens

frontend-engineer

Frontend implementation - React, Next.js, TypeScript, UI components, styling, accessibility, browser work.

jpoley/flowspec · 24 tokens

go-perf-developer

Go performance developer. Helps write efficient Go code: preallocation, string building, escape analysis awareness, struct layout, sync.Pool, and hot-path patterns.

yanmxa/cc-plugins · 38 tokens

fastmcp-ts-expert

TypeScript FastMCP specialist for building MCP servers with tools, resources, prompts, and authentication.

jpoutrin/product-forge · 26 tokens