curriculum

curriculum is a command for coding agents from walterra/claude-code-helpers. It costs 0 tokens per session (826 once invoked), scanned A, original, Apache-2.0.

A command that turns the code and documentation changed on the current branch into an onboarding guide for a new developer.

In plain words
What is it for?
Use it to create learning material focused on architecture, features, testing, deployment, or another chosen area of the branch.
Why use it?
It gives someone unfamiliar with the codebase a structured way to learn what changed and how the relevant parts work.

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/walterra/claude-code-helpers/curriculum
Clone the repo
git clone --depth 1 https://github.com/walterra/claude-code-helpers

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.

agentmods badge for curriculum

README.md
[![agentmods](https://agentmods.dev/badge/commands/walterra/claude-code-helpers/curriculum.svg)](https://agentmods.dev/commands/walterra/claude-code-helpers/curriculum)
Your own site
<a href="https://agentmods.dev/commands/walterra/claude-code-helpers/curriculum"><img src="https://agentmods.dev/badge/commands/walterra/claude-code-helpers/curriculum.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 826 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00826
Opus 5 $0.00000 $0.00413
Sonnet 5 $0.00000 $0.00165
Haiku 4.5 $0.00000 $0.00083

Measured 3d ago against content hash aa39eb9c80cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

curriculum 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 3d 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/curriculum.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create curriculum based on current branch

Analyse the code and docs created/modified in the current branch.

Create a comprehensive onboarding guide for a new developer to learn about the code of this branch. Use your todo tools to manage progress.

User Questions

Before creating the curriculum, ask the user:

  • What is the target audience? (Junior developer, experienced developer new to the codebase, reference for someone who knows the codebase well, specific role like frontend/backend/devops)
  • What should be the primary focus? (Architecture overview, specific features, testing practices, deployment, etc.)
  • What level of detail is needed? (High-level overview, deep technical dive, or balanced approach)
  • Are there specific technologies or concepts you want emphasized?
  • What format would work best? (Step-by-step tutorial, reference guide, interactive workshop, or mixed approach)
  • How much time should the curriculum take to complete? (Hours, days, weeks)

Detailed Instructions

1. Read the Code

  • Analyze all files changed/added in the current branch
  • Use git diff main...HEAD to see changes since branching from main
  • Review each modified file to understand functionality and purpose
  • Identify key components, modules, and their relationships

2. Identify Tech Topics

  • Extract technical concepts, frameworks, and libraries used
  • Note architectural patterns and design principles
  • Identify APIs, data structures, and key algorithms
  • Document dependencies and external integrations
  • List testing approaches and development practices

3. Create Table of Contents

  • Organize topics from basic to advanced concepts
  • Structure learning path logically (dependencies first)
  • Group related concepts together
  • Include practical examples
  • Add estimated learning time for each section

4. Create Documentation for Each ToC Item

  • Write clear explanations for each technical concept
  • Include code examples from the actual codebase
  • Provide context on why each technology/pattern was chosen
  • Add troubleshooting tips and common gotchas
  • Link to external resources for deeper learning
  • Include hands-on exercises to reinforce learning

Read the full file on GitHub · 97 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. 3d ago First seen · 97 lines · 0 tokens per session scan A aa39eb9c80cc

Subscribe to this mod's changes

curriculum is a command published in the GitHub repository walterra/claude-code-helpers (5 stars, last pushed 1y ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 826 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.