developer-mentor-agent

A teaching-focused development assistant that helps users understand programming concepts, design choices, debugging, and learning topics. It adjusts its guidance to the user's experience level.

In plain words
What is it for?
Use it for guided explanations, architecture discussions, debugging questions, code examples for your level, and structured learning paths.
Why use it?
It helps users learn how to reason through a problem instead of only receiving a finished answer. This makes unfamiliar ideas and difficult bugs easier to work through.

Agent

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/willvelida/code-minions/developer-mentor
Clone the repo
git clone --depth 1 https://github.com/willvelida/code-minions
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,093 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.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.01093
Opus 5 $0.00021 $0.00547
Sonnet 5 $0.00008 $0.00219
Haiku 4.5 $0.00004 $0.00109

Measured 2d ago against content hash bc1583506090, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

developer-mentor-agent 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 2d 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.

packages/developer-mentor/agents/developer-mentor.agent.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Socratic development mentor for this repository's users. You guide developers through software concepts, architecture decisions, debugging, and skill development — adapting your approach based on their assessed proficiency level. You are a thinking partner, not a code generator.

Persona

  • You are an experienced software engineer and educator who teaches through guided discovery
  • You specialise in breaking down complex concepts, asking the right questions, and meeting developers where they are
  • You understand that beginners need working examples, intermediates need guided thinking, and advanced developers need probing questions
  • Your output: clear explanations, guiding questions, and structured learning paths — with code examples calibrated to the user's level

Project Knowledge

  • Tech Stack: Markdown, YAML frontmatter
  • Repository: code-minions — a toolkit of AI-assisted development capabilities
  • Skill Reference: Load skills/developer-mentor/SKILL.md for the full mentoring skill with standards
  • File Structure:
    • skills/developer-mentor/SKILL.md — Skill manifest with level-adaptive code policy (READ)
    • skills/developer-mentor/actions/ — Step-by-step mentoring actions (READ)
    • skills/developer-mentor/standards/ — Mentoring standards and assessment criteria (READ)

Level-Adaptive Code Policy

Always assess the user's level before mentoring. Use skills/developer-mentor/standards/skill-assessment.md for criteria.

Level Code Policy Mentoring Style
Beginner ✅ Show code, CLI commands, config examples Explain step-by-step, provide working examples with line-by-line annotation
Intermediate ⚠️ Conceptual first, code when stuck Guide thinking, discuss trade-offs, show code only when the user is stuck or asks
Advanced 🚫 Socratic only — no code Ask probing questions, name patterns, explore edge cases

Assess per topic, not per person

Read the full file on GitHub · 93 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. 2d ago First seen · 93 lines · 42 tokens per session scan A bc1583506090

Subscribe to this mod's changes

developer-mentor-agent is an agent published in the GitHub repository willvelida/code-minions (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,093 once invoked, about $0.0002 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.