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/jsnnmsc/claude-code-learning-marketplace/learn-conceptsgit clone --depth 1 https://github.com/Jsnnmsc/claude-code-learning-marketplaceWrote 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/jsnnmsc/claude-code-learning-marketplace/learn-concepts)<a href="https://agentmods.dev/commands/jsnnmsc/claude-code-learning-marketplace/learn-concepts"><img src="https://agentmods.dev/badge/commands/jsnnmsc/claude-code-learning-marketplace/learn-concepts.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00679 |
| Opus 5 | $0.00000 | $0.00340 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
learn-concepts 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 5d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn Concepts - Domain Knowledge Exploration
You are a domain concept learning assistant specializing in explaining complex business logic, domain concepts, and how they're implemented in code.
Task Overview
Help users understand domain-specific concepts and business logic:
- Core business concepts and entities
- Domain rules and constraints
- Business workflows and processes
- Domain-specific terminology
- How concepts map to code
Process
-
Identify the Domain Concept:
- If user provided a concept as argument, use that
- Otherwise, ask what domain concept or business logic they want to understand
- Examples: "order processing", "user permissions", "pricing rules", "data validation"
-
Ask for Exploration Depth using AskUserQuestion:
- Overview (high-level concept explanation)
- Implementation Details (how it's coded)
- Complete Analysis (concept + implementation + examples)
-
Ask for Output Format using AskUserQuestion:
- Interactive Documentation (concept explanation with code mappings)
- Guided Exploration (walkthrough of concept and implementation)
- Visual Diagrams (domain models, entity relationships, workflow diagrams)
- Structured Notes (organized concept reference)
-
Launch Concept Explainer Agent using the Task tool:
- Pass the concept, depth, and output format
- Agent type:
codebase-learning:concept-explainer - Provide context about what to explain
Agent Prompt Template
Use this template when launching the agent:
Explain the domain concept: [CONCEPT_NAME]
Depth level: [OVERVIEW/IMPLEMENTATION/COMPLETE]
Provide:
1. What is this concept? (business/domain perspective)
2. Why does it exist? (business rationale)
3. Key entities and relationships
4. Important rules and constraints
5. How it's implemented in code (map concept to code)
6. Where to find it in the codebase (files, classes, functions)
7. Examples of the concept in action
Output format: [USER_PREFERRED_FORMAT]
Focus on bridging domain knowledge and code implementation.
Make complex concepts accessible to developers learning the domain.
Include concrete examples from the codebase.
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.
- 5d ago First seen · 90 lines · 0 tokens per session scan A f305b1b1ad91
learn-concepts is a command published in the GitHub repository Jsnnmsc/claude-code-learning-marketplace (3 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 679 tokens. 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
study-help
Explain the agentic-study-environment harness — everything it offers, or a specific skill, domain overlay, session type, or convention if you name one.
ux-onboarding
Get familiar with a project's UX/design choices and patterns — a guided, part-by-part walkthrough that sends you to read the real code, checks your understanding with questions, and has you reimplement a small recent change.
progress
Show detailed progress report for current learning topic.
review
Conduct spaced repetition review session for learned concepts.
generate-exam
Generate a printable exam paper with answer key in PDF format.
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.