All memos tagged #claude-code

Claude Code Swarm Mode (officially called Agent Teams) is a multi-agent orchestration system built into Claude Code by Anthropic. Initially feature-flagged and hidden from users, the system was...

TL;DR Claude Mythos for Developers is a practical read on what Anthropic's Mythos-class model — released June 9, 2026 as Claude Fable 5 and Claude Mythos 5 — means for builders: stronger SWE-bench...

Resend Claude Code Plugin is the official Resend plugin for Claude Code that bundles Resend's MCP server and email skills into a single install, letting the agent send, template, and process email...

Claude Code Memory is Claude Code's file-based persistence layer at ~/.claude/projects/<project>/memory/, indexed by MEMORY.md, so durable facts survive across conversations and load automatically...

Reducing permission prompts in Claude Code means pre-approving the tool calls and shell commands you trust — through settings.json allowlists, session permission modes, or Auto Mode — so the agent...

ENABLEPROMPTCACHING1H is a Claude Code environment variable that extends the prompt-cache lifetime from the default five minutes to one hour, keeping cached context warm across longer gaps between...

/dream is an undocumented Claude Code command that triggers a background agent to consolidate a session's memory files — merging facts, pruning contradictions, and trimming the index, much as REM...

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...

Claude Code Hooks and Skills are the two complementary extensibility systems built into Claude Code — the Hook handles automated reactions to lifecycle events, and the Skill handles reusable...

Plan Mode is a read-only operating mode in Claude Code where the agent analyzes the codebase, proposes an implementation approach, and surfaces it for explicit user approval before any file writes or...

Sessions from Dispatch is a Claude Code Desktop feature that lets Dispatch — the persistent Claude Cowork conversation on the Claude mobile and desktop apps — spin up full Code sessions on the user's...

The Claude Code Monitor Tool is a built-in Claude Code tool that lets the agent run a command in the background and receive each output line as it arrives. Rather than blocking a turn on a...

An MCP Server is a lightweight program that exposes specific tools, resources, and prompts to AI clients via the Model Context Protocol (MCP) standard, letting any compatible client invoke its...

A Claude Code Plugin is a bundled distribution unit packaging skills, slash commands, hooks, subagents, and MCP server configurations as a single installable extension to Claude Code. Plugins emerged...

A Slash Command in Claude Code is a user-typed /foo that invokes a built-in command, a registered skill, or a plugin-provided workflow without requiring natural-language prompting. Slash commands...

CLAUDE.md as Infrastructure is the concept that a Claude Code configuration file is not just a settings document — it is the foundational layer of an Augmentation Stack, the simplest form of...

/scheduled is the management interface for Claude Code's scheduled remote agent triggers — the web dashboard where every trigger you create via the /schedule skill is listed, editable, and runnable...

Claude Code Routines are autonomous, recurring sessions that run on Anthropic's cloud infrastructure — no laptop required. A routine packages a prompt, one or more repositories, connectors, and...

The MythOS Claude Code Skill enables MythOS creators to connect their knowledge library to Claude Code via the CLI. Search, read, create, and update memos, chat with your library using RAG, explore...

The Codex Integration for Claude Code is a skill for Claude Code designed to integrate Codex's capabilities into development workflows, enabling automated code analysis, refactoring, and editing....