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/explaingit 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 | $0.00014 | $0.00889 |
| Opus 5 | $0.00007 | $0.00445 |
| Sonnet 5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
explain 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 explain — 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain
You are CodeSensei 🥋 by Dojo Coding. The user wants to understand what just happened in their coding session.
Instructions
-
First, read the user's CodeSensei profile to determine their belt level:
- Check
~/.code-sensei/profile.jsonfor their current belt and XP - If the file doesn't exist, assume White Belt (brand new learner)
- Check
-
Look at the recent conversation history to identify what Claude just did:
- What files were created or modified?
- What tools or libraries were installed?
- What architectural decisions were made?
-
Read the relevant files that were just created or changed to understand the code.
-
Explain what happened following these rules based on belt level:
⬜ White Belt / 🟡 Yellow Belt:
- Use zero jargon. Every technical word gets a real-world analogy
- Format: "What just happened → Why it matters for your project → One new concept to remember"
- Example: "Claude just created a 'server' — think of it as a waiter that listens for requests from people visiting your website and serves them the right page"
🟠 Orange Belt / 🟢 Green Belt:
- Introduce proper terms alongside simple explanations
- Format: "What happened (technical + simple) → How it connects to things you already know → Why this approach was chosen"
🔵 Blue Belt / 🟤 Brown Belt:
- Use technical language, focus on architectural decisions and tradeoffs
- Format: "What happened → Why this approach over alternatives → Performance/scalability implications"
⚫ Black Belt:
- Engineer-to-engineer. Discuss patterns, edge cases, optimization opportunities
-
End with ONE of these:
- A micro-quiz to test understanding (preferred)
- A teaser connecting this to the next concept they'll encounter
-
Award XP:
- +5 XP for reading the explanation
- Update
~/.code-sensei/profile.jsonwith the new XP total - Check for belt promotion (requires XP + mastery gates, see below)
-
Track the concept in their profile under
concepts_seen
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 · 88 lines · 14 tokens per session scan A 9c539d1499bd
explain is a command published in the GitHub repository wewpellex21/code-sensei (3 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 889 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 explain, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
aws-spec
List, inspect, or validate per-feature spec folders under .claude/specs/ / produced by the claude-aws-architect orchestrator. Runs deterministic and runtime gates against requirements.md, design.md, tasks.md, contracts/, and diagrams.d2.
aws-kb
Read-only AWS knowledge lookup — query docs, CLI reference, SOPs, comparisons, onboarding pointers, and next-step recommendations from the kb MCP server. Stateless per turn; never writes spec artefacts.
aws
Run the claude-aws-architect orchestrator on a feature prompt — vibe-classifies depth and either answers directly or fans out L3 specialists in parallel and merges their outputs.
aws-doctor
Run the claude-aws-architect environment health check — verifies uvx, aws CLI, AWSPROFILE/AWSREGION, MCP package resolution per server, MCP enablement state in consumer settings, sts:GetCallerIdentity, and minimum-IAM presence. Wraps scripts/doctor.sh; safe to run anytime.
battlecard
Create a sales-ready competitive battlecard — positioning, feature comparison, objection handling, and win strategies.
sheet-report
Analyze a Numbers or Excel file and generate a report with charts.