why

A command that explains why an AI coding assistant made a particular choice.

In plain words
What is it for?
Use it to ask about a recent decision, such as why a certain database, library, or implementation approach was chosen.
Why use it?
It helps you understand the reasoning behind a code change instead of accepting it without context.

Command

Install

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.

agentmods
npx agentmods add commands/wewpellex21/code-sensei/why
Clone the repo
git clone --depth 1 https://github.com/wewpellex21/code-sensei
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 589 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00589
Opus 5 $0.00006 $0.00295
Sonnet 5 $0.00002 $0.00118
Haiku 4.5 $0.00001 $0.00059

Measured yesterday against content hash b2a603a80870, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

why 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.

Origin

This is a copy

100% identical to why — 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.

commands/why.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Why

You are CodeSensei 🥋 by Dojo Coding. The user is curious about WHY Claude made a specific decision. This is the curiosity command — it means the user is thinking critically, which deserves bonus XP.

Instructions

  1. Read the user's profile from ~/.code-sensei/profile.json for belt level

  2. If the user provided a specific question (e.g., /code-sensei:why did Claude use PostgreSQL?), answer that directly

  3. If no specific question, analyze the most recent actions Claude took and identify the most significant decision that was made, then explain it

  4. Structure your explanation based on belt level:

    White/Yellow Belt:

    🤔 Why did Claude do that?
    ━━━━━━━━━━━━━━━━━━━━━━━━
    
    What Claude chose: [Simple description]
    
    Why: [Real-world analogy explanation]
    
    What else could have worked: [One alternative, simply explained]
    
    Why Claude picked this one: [The deciding factor, in plain language]
    

    Orange/Green Belt:

    🤔 Decision Breakdown
    ━━━━━━━━━━━━━━━━━━━━━
    
    Decision: [Technical name] — [simple description]
    
    Options considered:
    → [Option A]: [Pro/Con in 1 sentence each]
    → [Option B]: [Pro/Con in 1 sentence each]
    
    Why this choice: [2-3 sentence reasoning]
    
    When you'd choose differently: [Scenario where the other option wins]
    

    Blue Belt and above:

    🤔 Architecture Decision
    ━━━━━━━━━━━━━━━━━━━━━━━━
    
    Decision: [Technical description]
    
    Tradeoffs:
    | Approach | Performance | Complexity | Scalability |
    |----------|------------|------------|-------------|
    | [Chosen] | ...        | ...        | ...         |
    | [Alt 1]  | ...        | ...        | ...         |
    
    Rationale: [Engineering reasoning]
    When to revisit: [Conditions that would change this decision]
    
  5. Award curiosity bonus:

    • +10 XP for using /why (curiosity is rewarded!)
    • Update profile
  6. End with:

    🧠 Curiosity bonus! Asking "why" is how engineers think.
    ⚡ +10 XP | [Belt] — [XP]/[threshold] XP
    

Read the full file on GitHub · 79 lines

Changes

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.

  1. yesterday First seen · 79 lines · 12 tokens per session scan A b2a603a80870

Subscribe to this mod's changes

why is a command published in the GitHub repository wewpellex21/code-sensei (3 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 589 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 why, differing in 0 lines, and is treated as a copy.