Plugin Claude Code
Codebase MOOC — AI-generated engineering education embedded in your codebase.
Plugin Claude Code
Codebase MOOC — AI-generated engineering education embedded in your codebase.
Plugin Claude Code
AI-generated engineering education embedded in your codebase. Takes any developer from novice to owner without going anywhere else.
Agent
Builds and updates Codebase Memory by reading the project structure and writing a rich structured graph to .codebase-mooc/memory/codebase/graph.json. Invoked by the coordinator during full generation and incremental updates. Use directly when Codebase Memory needs to be rebuilt.
Agent
Generates the architecture curriculum layer from Codebase Memory. Produces the map-before-the-territory overview that orients a new developer to the system as a whole before they read any code. Invoked by the coordinator after the archaeologist completes.
Agent
Generates the domain curriculum layer — the business logic, regulatory requirements, user behaviour patterns, and commercial constraints that shaped the code. Explains why the code looks the way it does from a business perspective, not a technical one. Invoked by the coordinator during full generation.
Agent
Generates the exercise layer — competency-gated exercises, spaced repetition metadata, abstraction prompts, and boss levels. Produces assessments that require genuine understanding, not pattern matching. Invoked by the coordinator during full generation.
Agent
Extracts the decision log layer from git history, commit messages, and code shape. Produces the road-not-taken documentation that preserves institutional memory. Invoked by the coordinator during full generation and after significant code changes.
Agent
Generates the implementation curriculum layer — deep walkthroughs of critical code that teach rather than describe. Invoked by the coordinator during full generation and after significant code changes.
Agent
Builds the failure mode archive from incident reports, post-mortems, and proactive analysis of the codebase. Turns every failure into a structured teaching opportunity. Invoked by the coordinator when an incident is filed or during full generation.
Agent
Validates all generated curriculum content before it reaches the human review queue. Checks for factual accuracy, confabulation, pedagogical quality, and exercise integrity. Writes structured flags to reviewannotations/. Invoked after every content generation pass.
Agent
Delivers the curriculum to learners. Reads learner history, determines the right content and exercises for the learner's current state, manages spaced repetition, evaluates exercise responses, and updates learner memory. Invoked by /codebase-mooc:learn and the learning-tutor skill.
Command
File a post-mortem or incident report for curriculum processing. The Pathologist agent generates a failure mode curriculum entry from it.
Command
Run the full curriculum generation pipeline. Sequences all agents and reports progress. Takes 2–30 minutes depending on codebase size.
Command
First-time setup of the Codebase MOOC in this project. Creates directory structure, detects codebase profile, and prepares for curriculum generation. Safe to re-run.
Command
Start or continue a learning session for a developer. Pass the developer's name or ID as the argument.
Command
Open the human review queue. Shows flagged Markdown curriculum files with Reviewer Agent critique. Approve or reject each item.
Command
Show full status of the Codebase MOOC in this project.
Hook
Runs after a tool call finishes for Bash tool calls, executing significance.py via python3. From psreek-ai/codebase-mooc.
Hook
Runs before the agent uses a tool for Write, Edit and MultiEdit tool calls, executing architecture.py via python3. From psreek-ai/codebase-mooc.
Hook
Runs when the agent finishes a response, executing session-drain.py via python3. From psreek-ai/codebase-mooc.
Skill Claude CodeCodex
Use when working in a project with Codebase Memory available and the task requires understanding system architecture, component relationships, design decisions, or where code belongs. Activates automatically when debugging unfamiliar code, explaining system behaviour, tracing data flows, or reasoning about where a…
Skill Claude CodeCodex
Use when reviewing AI-generated curriculum content in the human review queue. Activates when working through .codebase-mooc/memory/humanreviewqueue.jsonl or when asked to review, approve, or assess generated curriculum content. Trigger phrases: "review the curriculum", "check the review queue", "approve this content"…
Skill Claude CodeCodex
Use when a developer wants to learn about the codebase, start a learning session, understand how something works, or progress through the curriculum. Activates when the intent is learning rather than doing. Trigger phrases: "I'm new here", "walk me through", "help me understand", "start a learning session", "what…