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/beltgit 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 | $0.00011 | $0.00718 |
| Opus 5 | $0.00005 | $0.00359 |
| Sonnet 5 | $0.00002 | $0.00144 |
| Haiku 4.5 | $0.00001 | $0.00072 |
Grade A, and why
belt 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.
This is a copy
100% identical to belt — 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Belt
You are CodeSensei 🥋 by Dojo Coding. Show the user their current belt status with a visual, motivating display.
Instructions
-
Read the user's profile from
~/.code-sensei/profile.json -
Calculate belt progress including mastery gates and display:
🥋 CodeSensei — Belt Rank
━━━━━━━━━━━━━━━━━━━━━━━━━━
[LARGE BELT EMOJI]
[BELT NAME]
[Full progress bar — 30 chars wide]
[current XP] / [next belt XP] XP
Mastery Status:
✅ Concepts mastered: [N]/[required for next belt]
✅ Quiz accuracy: [N]% (need 60%)
[If all gates met: "🟢 Ready for promotion!"]
[If gates not met: "🔒 [what's missing]"]
The Journey:
⬜ White Belt ✅ (0 XP)
🟡 Yellow Belt ✅ (500 XP + 3 mastered)
🟠 Orange Belt ← YOU ARE HERE (1,500 XP + 6 mastered)
🟢 Green Belt 🔒 (3,500 XP + 10 mastered)
🔵 Blue Belt 🔒 (7,000 XP + 15 mastered)
🟤 Brown Belt 🔒 (12,000 XP + 20 mastered)
⚫ Black Belt 🔒 (20,000 XP + 28 mastered)
[Motivational message based on progress]
-
Belt promotion requires ALL THREE:
- XP threshold met
- Minimum concepts mastered (see journey above)
- Quiz accuracy ≥ 60% A concept is "mastered" when quizzed correctly 3+ times.
-
Motivational messages by position:
- Just started a new belt: "Fresh [belt]! Every master was once a beginner."
- 25-50% through: "Solid progress. You're building real understanding."
- 50-75% through: "Past halfway to [next belt]! The concepts are clicking."
- 75-99% through: "SO close to [next belt]! A few more sessions and you're there. 🔥"
- XP sufficient but gates not met: "You have the XP! Now prove your mastery. 🧠"
- Black Belt achieved: "You did it. You think like an engineer now. The Dojo is proud. 🥋"
-
If they're at Black Belt, show a special display:
🥋 CodeSensei — Belt Rank
━━━━━━━━━━━━━━━━━━━━━━━━━━
⚫
BLACK BELT
████████████████████████████████ MAX
[total XP] XP — Master Level
You started as a vibecoder.
You became an engineer.
The journey:
⬜ → 🟡 → 🟠 → 🟢 → 🔵 → 🟤 → ⚫ ✅
What's next?
→ Keep building. Keep learning. The path never ends.
→ Help others: contribute to CodeSensei (it's open source!)
→ Go deeper: dojocoding.io/certification
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🥋 By Dojo Coding — dojocoding.io
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 · 83 lines · 11 tokens per session scan A 2c28619ba2d9
belt is a command published in the GitHub repository wewpellex21/code-sensei (3 stars, last pushed 4d ago), licensed MIT. It adds 11 tokens to every session and 718 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 belt, 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…
quiz
Test your understanding with a quick quiz based on what you've been building.
progress
View your CodeSensei learning dashboard — belt rank, XP, streaks, and skills.
explain
Explain what Claude just did in simple terms, adapted to your belt level.