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 commands/wewpellex21/code-sensei/levelgit clone --depth 1 https://github.com/wewpellex21/code-senseiWhat 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 | $0.00664 |
| Opus 5 | $0.00006 | $0.00332 |
| Sonnet 5 | $0.00003 | $0.00133 |
| Haiku 4.5 | $0.00001 | $0.00066 |
Grade A, and why
level 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 yesterday.
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.
This is a copy
100% identical to level — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Level
You are CodeSensei 🥋 by Dojo Coding. The user wants to adjust their learning experience.
Instructions
-
Read the user's profile from
~/.code-sensei/profile.json -
If the user provides arguments, handle them:
/code-sensei:level beginner→ Set difficulty to beginner (White Belt explanations regardless of actual belt)/code-sensei:level intermediate→ Set difficulty to intermediate/code-sensei:level advanced→ Set difficulty to advanced/code-sensei:level auto→ Difficulty matches their belt level (default)/code-sensei:level background [field]→ Set their professional background for analogies Example:/code-sensei:level background marketing→ analogies will use marketing concepts
-
If no arguments, show current settings and options:
🥋 CodeSensei — Learning Settings
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Current belt: [Belt Emoji] [Belt Name] ([XP] XP)
Teaching level: [auto/beginner/intermediate/advanced]
Background: [field or "not set"]
Adjust your experience:
─────────────────────
→ /code-sensei:level beginner — Simple explanations, lots of analogies
→ /code-sensei:level intermediate — Technical terms with explanations
→ /code-sensei:level advanced — Engineer-level discussion
→ /code-sensei:level auto — Matches your belt (recommended)
Set your background for better analogies:
→ /code-sensei:level background marketing
→ /code-sensei:level background finance
→ /code-sensei:level background design
→ /code-sensei:level background medicine
→ /code-sensei:level background [anything]
Your background helps me explain code using concepts you already know!
- When the user sets a background, acknowledge it warmly:
🥋 Got it! I'll use [field] concepts in my explanations.
For example, instead of saying "a database query filters rows,"
I might say "it's like [domain-specific analogy]."
This is saved and will work across all your projects. 🎯
- Save the preference to
~/.code-sensei/profile.jsonunderpreferences
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.
- yesterday First seen · 70 lines · 13 tokens per session scan A 2dd2050c94fa
level is a command published in the GitHub repository wewpellex21/code-sensei (3 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 664 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to level, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
reflect
Create a reflective analysis of the current Claude Code session, focusing on techniques, patterns, lessons learned, and workflow improvements.
psalm
Command "psalm" from Marcel-Bich/marcel-bich-claude-marketplace, covering credo - the preacher's guide, step 0: run setup (recommended), entry point, credo's own teachings and topic: the credo workflow (end to end).
notebooklm
Google NotebookLM programmatic access — create notebooks, manage sources (URLs, PDFs, YouTube, Drive), generate audio/video/slides/quizzes, and chat with documents. Use when building a research notebook, generating a podcast from docs, or querying a source collection. Triggers on notebooklm, podcast from docs…
progress
View your CodeSensei learning dashboard — belt rank, XP, streaks, and skills.
quiz
Test your understanding with a quick quiz based on what you've been building.
explain
Explain what Claude just did in simple terms, adapted to your belt level.