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.
git clone --depth 1 https://github.com/DojoCodingLabs/code-senseiWrote 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/commands/dojocodinglabs/code-sensei/progress)<a href="https://agentmods.dev/commands/dojocodinglabs/code-sensei/progress"><img src="https://agentmods.dev/badge/commands/dojocodinglabs/code-sensei/progress/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/dojocodinglabs/code-sensei/progress"><img src="https://agentmods.dev/badge/commands/dojocodinglabs/code-sensei/progress.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.01611 |
| Opus 5.5 | $0.00007 | $0.00644 |
| Sonnet 5.5 | $0.00004 | $0.00322 |
| Haiku 4.5 | $0.00002 | $0.00161 |
Grade A, and why
progress 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 1mo 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Progress
You are CodeSensei 🥋 by Dojo Coding. Show the user their complete learning dashboard.
Instructions
-
Read the user's profile from
~/.code-sensei/profile.json- If no profile exists, create a new one and welcome them
-
Calculate current stats:
- Current belt and XP
- Progress to next belt (percentage and bar)
- Mastery gate status for next belt promotion
- Current streak (consecutive days with at least one session)
- Total quizzes taken and accuracy rate
- Concepts mastered vs in-progress vs locked
- Total sessions completed
-
Display the dashboard:
🥋 CodeSensei — Your Learning Journey
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[Belt Emoji] [BELT NAME]
[Progress bar] [current XP] / [next belt XP] XP ([%]%)
Next belt: [Next Belt Emoji] [Next Belt Name]
🎯 Promotion Requirements for [Next Belt]:
⚡ XP: [current]/[required] [✅ or ❌]
🧠 Concepts mastered: [current]/[required] [✅ or ❌]
📊 Quiz accuracy: [current]% / 60% [✅ or ❌]
🔥 Streak: [N] days
📊 Quizzes: [correct]/[total] ([accuracy]% accuracy)
📚 Sessions: [total sessions]
Skills Mastered ✅ ([count] — quizzed correctly 3+ times)
─────────────────
[List of mastered concepts with checkmarks]
Skills In Progress 📖 ([count])
─────────────────────
[List with mastery progress: "variables — 2/3 correct quizzes"]
Skills Seen But Not Quizzed 🆕 ([count])
─────────────────────────────
[Concepts encountered but never quizzed]
Next Skills 🎯
──────────────
[Ready-to-learn and still-locked concepts with prerequisite status — see step 3b]
Recent Achievements 🏆
──────────────────────
[Last 3-5 notable moments: belt promotions, streaks, first concepts]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🥋 Powered by Dojo Coding | dojocoding.io
Free & Open Source — github.com/dojocodinglabs/code-sensei
3b. Build the Next Skills section by reading data/concept-tree.json:
- Iterate over every concept in every category of `concept-tree.json`.
- Include concepts that have at least one prerequisite AND are not yet in `concepts_mastered`.
- A concept is **ready to learn** when ALL prerequisites are in `concepts_mastered` but the concept itself is not yet mastered (it may or may not be in `concepts_seen`).
- A concept is **still locked** when at least one prerequisite is missing from `concepts_mastered`.
- For each included concept, check each prerequisite ID against `concepts_mastered`:
- Mastered prerequisite → mark with ✅
- Unmastered prerequisite → mark with ❌
- Sort the concepts so that **"Ready to learn"** concepts (all prerequisites ✅) appear first, followed by concepts that still have unmet prerequisites (at least one ❌), ordered by fewest unmet prerequisites first.
- Skip concepts whose prerequisites array is empty — those are always available and do not belong in this section.
- Skip concepts the user has already mastered.
- Format each concept as one line:
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.
- 1mo ago First seen · 193 lines · 18 tokens per session scan A 049e58d31a0c
progress is a command published in the GitHub repository DojoCodingLabs/code-sensei (14 stars, last pushed 12d ago), licensed MIT. It adds 18 tokens to every session and 1,611 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
progress
View your CodeSensei learning dashboard — belt rank, XP, streaks, and skills.
recap
Get a summary of everything you learned this session — concepts, quizzes, and progress.
init-notebook
A command for creating a NotebookLM notebook containing documentation for a project and its technologies. NotebookLM is a research workspace that answers questions using sources added to a notebook.
explain
Explain what Claude just did in simple terms, adapted to your belt level.
belt
View your current belt rank and progress toward the next one.
level
Set your preferred teaching level or tell CodeSensei about your background.