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...
Claude #claude
Memos about Claude.
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...
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...
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...
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...
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,...
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...
Headless Mode in Claude Code is the non-interactive invocation pattern triggered by claude -p "<prompt>", designed for scripting, CI pipelines, and automated agent workflows that run without a human...
Permissions in Claude Code are granular allow / ask / deny rules declared in settings.json that control which tools, Bash commands, and MCP calls run without prompting the user for approval. How Do...
A Skill in Claude Code is a file-based capability with YAML frontmatter that the harness loads on demand, exposing reusable workflows the agent can invoke by name when their description matches the...
AGENTS.md in the Claude Code and Codex context is a markdown instruction file — analogous to CLAUDE.md as Infrastructure — that cross-tool agents read at session start, enabling shared project...
The complete feature surface of Claude, organized by product surface rather than alphabetically and compiled from Anthropic's published documentation. Features with a dedicated memo link to it; the...
Claude's memory is an optional feature that generates entries from a user's chats and organizes them into categories, so context carries forward across conversations without being re-explained....
J-space is a small, readable internal workspace that Anthropic researchers identified inside Claude's reasoning process, discovered using a Jacobian-based interpretability technique called J-lens....
Claude Design is an Anthropic Labs product, launched April 17, 2026, that turns natural-language prompts into editable visual artifacts — prototypes, slides, one-pagers, mockups, and interactive web...
Claude Mythos is Anthropic's Mythos-class tier within the Claude model family — its most capable system, positioned above Claude Opus 4.8 with major gains in reasoning, software engineering, agentic...
Claude Managed Agents is a suite of composable APIs from Anthropic for building, running, and observing cloud-hosted AI agents at scale, launched in public beta on April 8, 2026. The platform...
MythOS and Claude Mythos share a name but nothing else: MythOS is an independent knowledge-management and human-AI augmentation platform in commercial use since 2018 at mythos.one, while Claude...
TL;DR Claude Mythos is Anthropic's Mythos-class Artificial Intelligence (AI) model. It reached the public on June 9, 2026 as Claude Fable 5 (general availability) and Claude Mythos 5 (restricted),...
Claude Mythos 5 is Anthropic's Mythos-class frontier model released June 9, 2026 — the same underlying model as Claude Fable 5, with safety guardrails lifted in some domains for trusted partners....
