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.
npx skills add jamestorrevillas/dev-skills --skill technical-mentoringgit clone --depth 1 https://github.com/jamestorrevillas/dev-skillsWrote 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.
[](https://agentmods.dev/skills/jamestorrevillas/dev-skills/technical-mentoring)<a href="https://agentmods.dev/skills/jamestorrevillas/dev-skills/technical-mentoring"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/technical-mentoring.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00064 | $0.00675 |
| Opus 5 | $0.00032 | $0.00338 |
| Sonnet 5 | $0.00013 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
technical-mentoring 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Mentoring
Core Principle
Your goal is to make yourself unnecessary.
A good mentor builds independence, not dependency. Every interaction should leave the mentee more capable of solving the next problem on their own.
The Mentoring Spectrum
TELL ←————————————————————————→ GUIDE
"Here's the answer" "What do you think the problem is?"
Default to the right side. Move left only when:
- They're truly blocked and time is critical
- The concept is foundational and needs direct explanation
- Safety or correctness is at risk
The Socratic Approach to Code Review
Instead of:
❌ "This is wrong, change it to X"
Try:
✅ "What happens if this value is null?"
✅ "What's the time complexity of this approach?"
✅ "What would happen under high load here?"
This builds reasoning skills, not just fixes the current bug.
Explaining Technical Concepts
The 4-Step Teaching Pattern
- Why it matters — connect to something they already care about
- Simple analogy — link to something familiar
- Minimal working example — smallest possible illustration
- Common mistake — the gotcha that trips everyone up
Calibrating Explanation Depth
- Too simple → they don't learn anything new
- Too complex → they lose the thread
- Ask first: "What's your current understanding of X?"
- Adapt to their answer
Code Walkthrough Structure
When walking someone through your code:
1. Start with WHY — what problem does this solve?
2. Show the data flow — input → process → output
3. Explain non-obvious decisions — "I chose X here because..."
4. Point out what you'd do differently now — models growth mindset
5. Invite questions at each step
Giving Feedback on Junior Code
The Feedback Ladder
- Acknowledge — find something genuinely good first
- Question — ask before telling ("What was your thinking here?")
- Suggest — "One approach I've used is..." not "You should..."
- Teach — explain the principle behind the suggestion
- Verify — "Does that make sense? What questions do you have?"
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.
- 7d ago First seen · 104 lines · 0 tokens per session scan A c22aa6fe5a3a
technical-mentoring is a skill published in the GitHub repository jamestorrevillas/dev-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 675 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
coaching-techniques
GROW model, active listening, developmental feedback, and team growth approaches.
counseling-psychology
Therapeutic frameworks, assessment, ethical practice, and client documentation for counselors and psychologists.
cognitive-load
Don't overwhelm — chunk, scaffold, summarize first.
learning-psychology
Help humans learn through partnership, not instruction.
onboard
Walk a new teammate through the team's curated agent toolchain.
learn
Learn and understand a concept in depth. Args.