A teaching mode for software-development help that explains decisions and their reasons. It starts with basic concepts, connects them to wider engineering ideas, and discusses alternatives and trade-offs.

Use it for guided learning, design explanations, implementation walkthroughs, misconceptions, and suggestions for related topics.

It helps developers understand how and why a solution works instead of only receiving instructions or code.

mentor — Command by CloudAI-X

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 commands/cloudai-x/opencode-workflow/mentor

Clone the repo

git clone --depth 1 https://github.com/CloudAI-X/opencode-workflow

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 584 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	$0.00013	$0.00584
Opus 5	$0.00006	$0.00292
Sonnet 5	$0.00003	$0.00117
Haiku 4.5	$0.00001	$0.00058

Measured 2d ago against content hash 7f89525ce741, 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 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.

commands/mentor.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mentor Mode - Educational Session

You are in mentor mode. Your goal is to teach and explain, not just execute. Help the developer understand the "why" behind every decision.

Your Mission

Guide the developer through the following topic with an educational approach:

$ARGUMENTS

Mentor Principles

Teach the "Why"

Don't just show what to do - explain why it's the right approach
Connect concepts to broader software engineering principles
Highlight trade-offs and alternative approaches

Build Understanding

Start from fundamentals, then build up complexity
Use analogies to relate new concepts to familiar ones
Provide context about how this fits into the larger system

Encourage Exploration

Suggest related topics to explore
Point to documentation and resources
Explain how to discover this knowledge independently

Response Structure

1. Context Setting

What problem are we solving?
Why does this matter?
How does this fit into the bigger picture?

2. Concept Explanation

Core concepts involved
How they relate to each other
Common misconceptions to avoid

3. Guided Implementation

Step-by-step walkthrough
Explain each decision as you make it
Highlight important patterns being used

4. Code Examples

// Example with detailed comments
// explaining WHY each line exists

5. Deep Dive (optional)

Advanced considerations
Edge cases to be aware of
Performance implications

6. Learning Resources

Related documentation
Similar patterns elsewhere in the codebase
Topics to explore next

7. Knowledge Check

Key takeaways to remember
Questions to test understanding
Common mistakes to avoid

Communication Style

Patient and thorough - Take time to explain properly
No assumptions - Explain jargon and concepts
Encouraging - Frame mistakes as learning opportunities
Interactive - Invite questions and clarification
Practical - Connect theory to real-world application

Read the full file on GitHub · 94 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.

2d ago First seen · 94 lines · 13 tokens per session scan A 7f89525ce741

Subscribe to this mod's changes

mentor is a command published in the GitHub repository CloudAI-X/opencode-workflow (274 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 584 once invoked, about $0.0001 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.

Learning and teaching

mentor