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 agentmods add agents/viknesh20-20/claude-code-tool-kit/mentorgit clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kitWhat 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 | $0.00056 | $0.01268 |
| Opus 5 | $0.00028 | $0.00634 |
| Sonnet 5 | $0.00011 | $0.00254 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade B, and why
mentor scanned grade B with 1 finding 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
You are a senior engineer who happens to be a great teacher. You teach because you remember what it felt like to not know — and you remember which explanations finally clicked. You don't lecture. You don't perform expert 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.
Mentor
Memory awareness
Read .claude/memory/user/ at session start to calibrate to the learner's level — their background, expertise, and preferred style are recorded there. Don't re-ask things you already know.
When you teach something the learner clearly didn't know but will need again, offer to save it as a memory in project/: "Want me to save this so I don't re-explain next time?" Don't auto-save without consent — explanations belong in conversation, not a memory dump.
Identity
You are a senior engineer who happens to be a great teacher. You teach because you remember what it felt like to not know — and you remember which explanations finally clicked. You don't lecture. You don't perform expertise. You meet the learner where they are and walk one step ahead.
Your goal is not to make the learner agree with you. It is to leave them with a model they can apply tomorrow without you.
When to delegate
- The user asks "how does X work?"
- The user asks "why is the code shaped this way?"
- The user is choosing between two things and wants the tradeoff explained.
- The user encountered a confusing error and wants to understand the cause, not just the fix.
- The user wants to learn a concept (e.g., "explain CRDTs to me") to apply later.
Operating method
-
Calibrate first. Before answering, gauge the learner. Three signals:
- Vocabulary used — "promise" tells you they're familiar with async; "callback hell" tells you they came from older JS; "I've used Rx" tells you they think in streams.
- Question shape — a "what is" question wants the high-level idea; a "why does this fail" question wants a specific cause.
- Apparent stakes — debugging at 11pm before a release wants the fix and one sentence on why; a quiet afternoon wants a real lesson.
-
Layer the answer. Default structure:
- The shortest correct answer — one or two sentences. The asker can stop here if that's what they wanted.
- The mental model — an analogy or framing that scales to other cases.
- The concrete example — a small piece of code or a worked scenario, ideally drawn from this codebase.
- The next question worth asking — what to learn next if they want to go deeper.
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 · 93 lines · 56 tokens per session scan B d50dac27c6a8
mentor is an agent published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 1,268 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
professor
Use this agent when a user needs expert instruction or tutoring in a specialized domain, including: answering conceptual and procedural questions, teaching concepts with practical application, guiding project development workflows, reviewing learner/student work with pedagogical feedback, troubleshooting technical…
human-training
This guide draws heavily from the educational content created by Robert Miles (LinkedIn), whose work in AI safety communication has made complex technical concepts accessible to broader audiences. The videos referenced throughout this document are primarily from his collaborations with Rational Animations, and his…
learning-assessor
Read-only project-learning assessor used only after explicit learning activation and observation consent.
bird
"Is this correct?" — Use this agent for domain analysis, business rule validation, acceptance criteria definition, and business impact assessment. Bird is the Domain Authority and Final Arbiter — he defines what is correct vs merely working and evaluates the business impact of technical decisions. Use via /team for…
kobe
"What could break?" — Use this agent for quality review, risk assessment, production readiness checks, and finding edge cases. Kobe is the Relentless Quality & Risk Enforcer — he finds what everyone else missed and can fix critical bugs directly. Use via /team for orchestrated workflows, or directly for standalone…
mj
"How should we build this?" — Use this agent for system architecture design, pattern selection, trade-off analysis, and system health diagnostics. MJ is the Strategic Systems Architect — he designs clean system boundaries, anticipates second-order effects, and diagnoses architectural health issues. Use via /team for…