Glossary
This glossary comes from the expanded vibe-coding guide and is intended to give teams a stable working vocabulary when they talk about Claude Code in design reviews, PRs, and onboarding.
| Term | Definition |
|---|---|
| Plan Mode | Read-only mode where Claude researches and analyzes without making edits. Toggle via Shift+Tab or /plan. |
| Auto-Accept Mode | Claude proceeds without asking for edit or run permission. Use it only when you trust the current task scope. |
| Auto Mode | AI classifier evaluates each tool call, blocking dangerous operations and allowing safe ones. Launched March 24, 2026. |
| RED Token | A state file at .claude/state/test-forward.json proving a failing verification existed before implementation. |
| RED → GREEN → REFACTOR | TDD cycle: write a failing test, implement the minimum to pass, then clean up. |
| PreToolUse Hook | Fires before a tool call executes. The primary enforcement mechanism. |
| PostToolUse Hook | Fires after a tool completes successfully. Used for formatting, tests, and feedback. |
| Stop Hook | Fires when Claude finishes responding. Agent-type Stop hooks can inspect files and block completion. |
| PermissionDenied Hook | Added in v2.1.89. Fires after Auto Mode classifier denials and can trigger retries. |
| Agent Teams | Coordinated multi-instance development with shared task lists and inter-agent messaging. |
| Subagent | A focused worker spawned within a session with its own context window. |
| Skills | SKILL.md instruction files that teach Claude specific behaviors. |
| Rules | Markdown files in .claude/rules/ that scope instructions to specific file globs or directories. |
| Hooks | Deterministic commands, prompts, HTTP handlers, or agents triggered at lifecycle points. |
| Context Window | The total conversation, files read, and command output Claude holds. The most important resource to manage. |
| Compaction | Compressing the context window via /compact while retaining the important state. |
| Worktree | An isolated git working copy used for parallel, conflict-free development. |
| Remote Control | /rc. Synchronization between the local session and Claude mobile app or web. The session still runs locally. |
| Superpowers | v5.0.6 plugin framework that layers brainstorming, planning, TDD, debugging, and code review skills on top of Claude Code. |
| 1% Rule | Superpowers protocol in which Claude checks for relevant skills before any response. |
opusplan | Model alias using Opus for planning and Sonnet for execution. |
defer | v2.1.89 PreToolUse permission decision that pauses headless sessions for human review. |
/batch | Parallel codebase-wide migration workflow that decomposes work into isolated units. |
/simplify | Bundled skill that spawns three review agents focused on reuse, quality, and efficiency. |
/loop | Session-level cron that fires prompts on a schedule while the session stays open. |
| MCP | Model Context Protocol. Connects Claude Code to external tools such as GitHub, Playwright, Figma, or databases. |
| Elicitation | v2.1.76 capability that allows MCP servers to display forms or open URLs to gather structured input. |
| Computer Use | March 2026 feature allowing Claude to interact with the screen UI directly. |
| Channels | Research preview for forwarding chat streams such as Telegram, Discord, or iMessage into a session. |
Why the glossary matters
The expanded guide treats vocabulary as an operational tool, not filler. Teams that can distinguish Plan Mode, Auto-Accept, Auto Mode, defer, Stop hooks, subagents, and Agent Teams tend to design cleaner workflows and make fewer bad assumptions about what Claude is actually allowed to do.