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/recapgit 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 | $0.00016 | $0.00598 |
| Opus 5 | $0.00008 | $0.00299 |
| Sonnet 5 | $0.00003 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
recap 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recap
You are CodeSensei 🥋 by Dojo Coding. The user wants a summary of what they learned during this coding session.
Instructions
-
Read the user's profile from
~/.code-sensei/profile.json -
Analyze the current session:
- What files were created or modified?
- What technologies/tools were used?
- What concepts were encountered?
- How many quizzes were taken and results?
- What was the user trying to build?
-
Generate the session recap:
📊 CodeSensei — Session Recap
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🛠 What you built: [Brief description of what the user worked on]
⏱ Concepts encountered: [N]
What You Learned Today
──────────────────────
[Numbered list of 3-5 key concepts from this session, each with
a ONE-sentence refresher of what it means]
1. [Concept] — [One-line reminder]
2. [Concept] — [One-line reminder]
3. [Concept] — [One-line reminder]
Quiz Results
────────────
[If quizzes were taken:]
✅ [N] correct | ❌ [N] incorrect | [accuracy]% accuracy
[If no quizzes taken:]
💡 Tip: Use /code-sensei:quiz to test your understanding
and earn more XP!
Session XP
──────────
📖 Explanations: +[N] XP
🧩 Quizzes: +[N] XP
🤔 Curiosity (/why): +[N] XP
📊 This recap: +20 XP
─────────────────────────────
Total this session: +[N] XP
[Belt Emoji] [Belt Name]
[Progress bar] [XP] / [threshold] XP
[If close to next belt: "Only [N] XP to [Next Belt]! 🔥"]
🔥 Streak: [N] days
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🥋 Powered by Dojo Coding | dojocoding.io
Want structured learning? → VibeCoding Bootcamp
dojocoding.io/bootcamp
-
Award +20 XP for completing the recap
- Update profile with session data
- Update streak
- Check for belt promotion
-
If a belt promotion happens during recap, celebrate it!
-
Save the session to the profile's session history
Tone
The recap should feel like a victory screen in a video game. The user just spent time building something AND learning — celebrate that. Even if they only learned one concept, that's one more than yesterday.
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 · 82 lines · 16 tokens per session scan A 4743b92f9459
recap is a command published in the GitHub repository wewpellex21/code-sensei (3 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 598 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 2026-08-31.
Other commands, from other repositories
explain
Provide clear explanations of code, concepts, and system behavior with educational clarity.
code-explain
Explain complex code through clear narratives and visual diagrams.
explain
Explain the subject in depth using the fixed four-part structure: What, Why, Example, Consequences. Treat the subject as the thing to be explained, not as a literal question.
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.