An interactive help command for learning Claude Code, its development tools, commands, skills, and workflows. Claude Code is an AI assistant for working with software projects.

Use it to ask how Claude Code features, commands, skills, hooks, workflows, or troubleshooting procedures work.

It gives a structured way to find the right explanation instead of searching through project files manually.

learn — Command for coding agents by benshapyro: An interactive help command for learning Claude Code, its…

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/benshapyro/cadre-devkit-claude/learn

Clone the repo

git clone --depth 1 https://github.com/benshapyro/cadre-devkit-claude

Or install cadre-devkit-claude, the plugin that ships this one along with the rest of its 10 skills, 10 commands, 7 agents, 3 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/benshapyro/cadre-devkit-claude/learn.svg)](https://agentmods.dev/commands/benshapyro/cadre-devkit-claude/learn)

Your own site

<a href="https://agentmods.dev/commands/benshapyro/cadre-devkit-claude/learn"><img src="https://agentmods.dev/badge/commands/benshapyro/cadre-devkit-claude/learn.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 936 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5	$0.00015	$0.00936
Opus 5	$0.00008	$0.00468
Sonnet 5	$0.00003	$0.00187
Haiku 4.5	$0.00002	$0.00094

Measured 4d ago against content hash bfd863fdfaf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn 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 4d 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.

commands/learn.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn Command

Interactive help and teaching for Claude Code and the devkit.

Before answering: Read .claude/skills/devkit-knowledge/SKILL.md for devkit architecture.

Question Routing

Route the user's question to the appropriate source:

Question Type	Action
Claude Code features	Use `claude-code-guide` subagent
Devkit structure	Reference devkit-knowledge skill
Specific command	Read `.claude/commands/{command}.md`
Specific skill	Read `.claude/skills/{skill}/SKILL.md`
Workflows	Reference devkit-knowledge skill
Hooks	Read `.claude/hooks/` + devkit-knowledge
Troubleshooting	Combine sources as needed

Response Style

Concise first - Give the direct answer
Then explain - Add context if helpful
Show examples - Concrete usage examples
Link to sources - Point to files they can read

Example Interactions

"How do hooks work?"

Read devkit-knowledge skill for overview
Explain PreToolUse vs PostToolUse
Show example hook structure
Mention debug mode (CLAUDE_HOOK_DEBUG=1)

"What's the difference between /plan and /greenfield?"

/greenfield = new project from scratch, creates SPEC/DESIGN/PLAN docs
/plan = specific feature in existing project
Use greenfield first, then plan for each feature

"Show me all available commands"

List commands from devkit-knowledge
Brief description of each
Show the standard workflow

"How do I add a custom skill?"

Create .claude/skills/my-skill/SKILL.md
Add to skill-rules.json with triggers
Reference from commands with explicit path
Show example structure

"What can Claude Code do?"

Use claude-code-guide subagent for accurate info
Summarize key capabilities
Point to official documentation

Dynamic Discovery

For questions about current setup, actually read the files:

"What commands are available?"
→ Read files in .claude/commands/ and list them

"What skills do I have?"
→ Read directories in .claude/skills/ and summarize

"Show me the hooks"
→ Read .claude/hooks/ structure and explain each

Read the full file on GitHub · 135 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.

4d ago First seen · 135 lines · 15 tokens per session scan A bfd863fdfaf8

Subscribe to this mod's changes

learn is a command published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 9mo ago), licensed MIT. It adds 15 tokens to every session and 936 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.

Building agents Learning and teaching

learn