# Code Learning Dojo

> Seven free programming sites, rebuilt for developers who work alongside coding agents. Foundations, agent configuration, and how to review what the machine wrote.

## Sites

- [Learn Python](https://learn-python.com/): Python for people whose code is half-written by an agent. Machine index at https://learn-python.com/llms.txt
- [Learn JavaScript](https://learn-javascript.org/): JavaScript fundamentals, and the agent workflows built on top of them. Machine index at https://learn-javascript.org/llms.txt
- [Learn TypeScript](https://learn-typescript.org/): The type system is the best prompt you will ever write. Machine index at https://learn-typescript.org/llms.txt
- [Learn Go](https://learn-go.org/): A small language an agent can hold entirely in its head. Machine index at https://learn-go.org/llms.txt
- [Learn C](https://learn-c.net/): The language where you cannot afford to skip the review. Machine index at https://learn-c.net/llms.txt
- [Learn Bash](https://learn-bash.net/): The language your agent runs the most and understands the least. Machine index at https://learn-bash.net/llms.txt
- [Learn NestJS](https://learn-nestjs.com/): A framework with enough structure that an agent can't get lost. Machine index at https://learn-nestjs.com/llms.txt

## Cross-network guides

- [Which language should you hand to an agent?](https://codelearningdojo.com/languages-for-agents/): Seven languages, ranked by how much of a generated mistake survives to production. The answer is mostly about what the toolchain refuses to accept.
- [Customizing your coding agent](https://codelearningdojo.com/customizing-harnesses/): Instructions, slash commands, subagents, skills, output styles, plugins. Six ways to shape a harness — and a rule for which to reach for, so you build capability instead of clutter.
- [Agent hooks: preprocess prompts, allow and deny, audit](https://codelearningdojo.com/harness-hooks/): Instructions are advice. Hooks are enforcement. A working reference for the extension points in Claude Code and Codex, and what to build with them.
- [Sandboxing a coding agent](https://codelearningdojo.com/sandboxing/): Hooks are policy: they stop what you anticipated. A sandbox is containment: it bounds what you did not. You want both, and most people have neither.
- [Prompt injection is the guardrail problem](https://codelearningdojo.com/prompt-injection/): Every other guardrail assumes the threat is the model doing something odd. This one is different: the instructions come from the data, and the model is doing exactly what it was told.
- [Reading the record of what your agent did](https://codelearningdojo.com/agent-observability/): Every session you run is already recorded in full. Almost nobody reads it — and the record is the fastest way to find out why a run went sideways.
- [What tokens actually cost, and where the money goes](https://codelearningdojo.com/token-economics/): The pricing model has five moving parts, and most bills are dominated by the two nobody thinks about. Here is the mental model, before the language-specific implementation.