Mini Claude
Code.

A coding agent built from scratch in ~500 lines of TypeScript. Six episodes, one working repository. No framework, no hidden layers — every file readable in one sitting.

MIT · runs on Node 20+ · Anthropic SDK only

By the numbers

~500
Lines of code
4
Source files
1
Runtime deps
6
Episodes

The six episodes

Each episode reads like a chapter. Each chapter maps to a file you can open right now.

  1. EP 01
    Mini Claude Code · Episode 01: A 40-Line REPL That Actually Remembers
    Start of a hands-on series where we build a working coding agent from scratch in TypeScript. Episode 1 gets the smallest possible loop running — stdin, streaming, and a conversation that survives turns.
    14 min
  2. EP 02
    Mini Claude Code · Episode 02: Teaching the Agent to Use Tools
    Episode 2 gives our REPL its first three tools — read_file, list_dir, run_bash — and walks through the tool-use loop with the Anthropic SDK. We handle stop reasons, tool errors, and the surprisingly tricky part of what to put back in the conversation.
    16 min
  3. EP 03
    Mini Claude Code · Episode 03: Editing Files Without Wrecking the Repo
    Episode 3 adds the apply_patch tool — the one where most agents quietly destroy your work. We build a strict unified-diff applier with dry-run preview, workspace guardrails, and a confirmation gate that survives a Claude in a bad mood.
    17 min
  4. EP 04
    Mini Claude Code · Episode 04: Making the Agent Forget on Purpose
    Episode 4 attacks the token bill head-on. We implement observation masking (the JetBrains-style trick that beats LLM summarization on cost and quality) and add an auto-continue path so max_tokens truncation stops silently breaking tool sequences.
    16 min
  5. EP 05
    Mini Claude Code · Episode 05: Spawning Sub-Agents With Their Own Context
    Episode 5 splits the agent in two. We add a spawn_subagent tool that dispatches a scoped task to a fresh Claude with its own tool set and its own context window, then returns a compact summary. The pattern behind Anthropic's 'token usage explains 80% of variance' finding, in ~90 lines.
    17 min
  6. EP 06
    Mini Claude Code · Episode 06: The Eval Loop That Finally Tells You If You Made It Worse
    Season finale. We build a 15-task SWE-lite harness that runs the agent end-to-end against verifiable code tasks, then wire in prompt caching so iteration is cheap. Pass rate, mean turns, and cost per task — pinned as a baseline you can regress against.
    18 min

Run it in three commands

Clone, install, launch. Then talk to it.

git clone https://github.com/claude-community/mini-claude-code
cd mini-claude-code
cp .env.example .env    # add ANTHROPIC_API_KEY
npm install
npm start

Built for real repositories

What's next

The eval harness ships with three seed tasks. The plan is to grow it toward a 15-task SWE-lite subset and pin a baseline you can regress against. If you want to add tasks, open a PR.