Skip to main content
Mythos

All memos tagged #claude-code

Working with Claude Code — Anthropic's agentic coding assistant. Patterns for human-AI collaboration, configuration, hooks, MCP integration, and building with Claude as a development partner.

Claude Code Agent View is a Claude Code screen, opened with claude agents, for dispatching background sessions on your own machine and seeing at a glance which ones are working, done, or waiting on...

10/30/2026

Claude Code Projects is a Claude Code feature in which one ongoing conversation acts as a coordinator, turning a stream of related tasks into parallel worker sessions called threads. Anthropic...

10/30/2026

How to hand side tasks to Claude Code subagents so the work runs in its own context and only a summary comes back to your session. Dispatch a subagent when a task would flood your conversation with...

10/30/2026

How to set up a Claude Code project so a coordinator runs your related tasks as parallel threads while you step away. Use a project when one goal keeps producing tasks over days or weeks; see Claude...

10/30/2026

Claude Code exposes its controls as slash commands typed at the start of a message; typing / alone lists everything available in the current build. Availability varies by plan, platform, and Command...

10/30/2026

The complete feature surface of Claude Code, organized by Anthropic's own documentation categories and compiled from its published docs. Features with a dedicated memo link to it; the rest are listed...

10/30/2026

Agent swarms in Claude Code are dispatched via the Agent tool, which spawns sub-agents — fresh, forked, or specialized — to run in parallel with optional worktree isolation and the Agent Teams...

10/30/2026

Claude Code subagents are delegated workers inside one Claude Code session that run a side task in their own context window, with their own prompt, tools, and permissions, and return only a summary....

10/30/2026

Claude Code multi-agent orchestration is the set of ways Claude Code splits work across more than one Claude at a time: subagents inside a session, background sessions you dispatch, agent teams with...

10/30/2026

Commands, settings, and limits for running Claude Code work in parallel, for someone at the keyboard deciding how to split a task across subagents, sessions, teams, or a project. Delegate inside one...

10/30/2026

This guide sets up a Memo Drafting Loop — a recurring /loop that turns the stub memos you tag into structured drafts, in your voice, landing clean in your library. It is built for any MythOS creator...

9/30/2026

A Tool in Claude Code is a typed capability the agent can invoke during a session — built-in (Read, Write, Edit, Bash, etc.), MCP-provided, or skill-provided — each governed by the permissions system...

8/9/2026

A Hook in Claude Code is a shell command the harness executes automatically in response to lifecycle events — tool calls, notifications, prompt submission, session start or stop — without explicit...

8/9/2026

A Worktree in Claude Code is an isolated git worktree the harness creates for an agent's file edits, spawned via isolation: "worktree" in the Agent tool to prevent parallel agents from colliding on...

8/9/2026

settings.json in Claude Code is the configuration file at ~/.claude/settings.json (or .claude/settings.local.json per-project) that controls permissions, hooks, environment variables, and MCP server...

8/9/2026

Model in Claude Code refers to the specific Claude model the session runs on — Opus, Sonnet, or Haiku — switched via the /model slash command, with different cost, latency, and context window...

8/9/2026

Compaction in Claude Code is the harness's automatic summarization mechanism that compresses earlier conversation content when the session's token usage approaches the model's context window limit,...

8/9/2026

Auto Mode is a Claude Code permission system that uses AI classifiers to approve safe actions automatically and block dangerous ones, sitting between manual approval of every step and fully...

8/9/2026