Glossary of AI Development Terms

You are reading a tutorial and hit a term you have never seen before — AGENTS.md, worktrees, sub-agents, thinking tokens. This glossary defines every piece of jargon you will encounter across Cursor, Claude Code, and Codex so you can get back to shipping code.

A

Agent Mode

A Cursor feature where the AI can autonomously read, modify, and create files across your project. Unlike Ask mode (read-only), Agent mode executes multi-step tasks: editing code, running terminal commands, fixing lint errors, and iterating until the job is done.

Agent Skills

An open standard for extending AI coding agents with reusable, shareable capabilities. Installed via npx skills add <owner/repo> from the Skills.sh marketplace. Skills work across Claude Code, Cursor, Codex, and 35+ other agents. Lighter-weight than MCP servers — they augment a single capability rather than maintaining a persistent connection.

AGENTS.md

A project-level configuration file recognized by Codex (and increasingly by other tools) that defines how AI agents should behave in a repository. Similar in purpose to CLAUDE.md but follows the AGENTS.md convention. Placed at the project root or in subdirectories. Specifies coding standards, test commands, deployment patterns, and tool preferences.

API Key

A secret string used to authenticate requests to an AI provider (Anthropic, OpenAI, Google). Can be personal or organizational. Store securely — never commit to version control.

Ask Mode

Cursor’s read-only conversation mode. The AI can read your codebase and answer questions but cannot modify files. Use it for exploration, planning, and understanding before switching to Agent mode for execution.

@ Symbols

Context references in Cursor and Claude Code that let you include specific files, folders, URLs, or documentation in your AI conversation. Examples: @file.js, @docs, @codebase, @web. Codex uses similar file-referencing patterns in its prompt interface.

Automations

Codex feature that lets you trigger agent runs automatically in response to events — GitHub issues, Slack messages, Linear tickets, or scheduled cron jobs. Runs in the cloud without manual intervention.

B

Background Agent

An agent that runs asynchronously while you continue working. In Cursor, triggered via Cmd/Ctrl+E or from Slack. In Codex, cloud tasks run as background agents by default. The agent completes the task independently and notifies you when done.

BugBot

Cursor’s automated pull request reviewer. Analyzes PRs for bugs, security issues, and code quality problems. Integrates with GitHub and posts inline comments.

C

Checkpoint

A saved state of your working directory created by Cursor before applying AI-generated changes. If the changes break something, you can revert to the checkpoint instantly. Think of it as an automatic git stash for every AI interaction.

CLAUDE.md

A markdown file that Claude Code reads automatically for project-specific context. Place it at the project root (or in subdirectories for scoped rules). Defines coding standards, common commands, architecture notes, and any instructions the AI should always follow. Created with /init and updated with /memory or the # shortcut.

Cloud Agent

An agent that runs on remote infrastructure rather than your local machine. Codex Cloud agents execute in sandboxed environments with their own compute resources. Cursor’s Background Agent can also hand off tasks to the cloud using the & suffix.

Codebase Indexing

The process of analyzing your entire project to enable semantic search. Cursor creates vector embeddings of your code. Claude Code uses agentic search (reading files on demand). Codex indexes repositories when you connect them.

Codex

OpenAI’s multi-surface AI coding agent. Available as a web App, a CLI tool, an IDE extension, and a Cloud service. Powered by GPT-5.3-Codex. Differentiates itself through worktree-based sandboxing, GitHub/Slack/Linear integrations, and automated workflows.

Compact / Compaction

The process of summarizing conversation history to free up context window space. In Claude Code, triggered with /compact. In Codex, compaction happens automatically when the context approaches the model’s limit. Preserves key decisions while discarding verbose intermediate steps.

Composer

Cursor’s multi-file editing interface (now largely merged into Agent mode). Describes changes across multiple files in a unified view before applying them.

config.toml

Codex’s configuration file, typically located at ~/.codex/config.toml. Defines default model, approval mode (on-request/on-failure/never), sandbox settings, and provider credentials.

Context Window

The maximum amount of text (measured in tokens) that a model can process in a single request. Claude Opus 4.6 supports 200K tokens, Sonnet 4.5 supports 1M tokens, GPT-5.3-Codex supports 200K+, and Gemini 3 Pro supports 1M tokens. Managing context effectively is one of the most important skills in AI-assisted development.

Custom Commands

User-defined slash commands. In Claude Code, created as markdown files in .claude/commands/. In Codex, defined through configuration. They let you package frequently used prompts into reusable /my-command shortcuts.

D

Deep Reasoning

Extended thinking modes that allocate more computation to complex problems. In Claude Code: /think, /think hard, /think harder, /ultrathink. In Codex: the model’s internal reasoning chain. In Cursor: Max mode enables extended reasoning.

Diff View

A visual representation of changes between original code and AI-suggested modifications. All three tools provide inline diff views for reviewing changes before accepting them.

E

Effort Parameter

A setting on Claude models (Opus 4.6, Sonnet 4.5) that controls how much reasoning computation the model uses. Lower effort = faster and cheaper; higher effort = deeper analysis. Adjustable via API or through tool interfaces.

Embeddings

Mathematical vector representations of code that enable semantic search. Cursor creates embeddings of your entire codebase so you can search by meaning, not just keywords. Claude Code and Codex use different retrieval strategies but achieve similar results.

Enterprise Mode

Features designed for corporate environments: privacy controls (no training on your code), SSO/SAML authentication, audit logging, SCIM provisioning, and compliance certifications (SOC 2, GDPR, HIPAA).

F

Fast Requests

Priority API calls in Cursor subscription plans that process without rate-limiting delays. Limited by plan tier. When exhausted, requests fall back to slower processing.

Full-Auto Mode

Codex’s highest-trust execution mode, enabled with the --full-auto CLI flag or approval_policy = "never" in config. The agent can read files, write files, and execute commands without asking for permission. Equivalent to combining Claude Code’s --dangerously-skip-permissions with auto-approved file edits. Use with caution — ideally in sandboxed environments.

Fusion Model

Cursor’s specialized Tab completion model capable of multi-line predictions and long-range code jumps across files.

G

Git Integration

Built-in version control capabilities that let AI agents create branches, write commits, resolve merge conflicts, and open pull requests. All three tools integrate deeply with Git and GitHub.

Git Worktrees

A Git feature that lets you check out multiple branches simultaneously in separate directories. Codex uses worktrees to sandbox each agent task in its own isolated working directory, preventing conflicts when running parallel tasks.

H

Headless Mode

Running an AI agent non-interactively, typically in CI/CD pipelines or automation scripts. Claude Code supports this with claude -p "task". Codex supports it through its Cloud API and CLI flags. No human in the loop — the agent executes and exits.

Hooks

Automation triggers at specific points in an agent’s workflow. In Claude Code, hooks run before or after specific tool calls (file edits, command execution). Defined in .claude/settings.json. Used for linting, formatting, validation, or custom logic.

I

IDE (Integrated Development Environment)

A software application for writing code. Cursor is an AI-native IDE (forked from VS Code). Codex offers IDE extensions for VS Code and JetBrains. Claude Code is terminal-native but has a VS Code extension.

Inline Edit

Cursor’s Cmd/Ctrl+K feature for making targeted AI edits to selected code directly in the editor, without opening a chat panel.

Intent Context

The “what you want to achieve” part of a prompt (prescriptive), as opposed to state context which describes the current situation (descriptive). Good prompts balance both: describe the current state, then clearly state the desired outcome.

L

Large Language Model (LLM)

An AI system trained on vast text datasets. The models powering these tools: Claude Opus 4.6, Claude Sonnet 4.5, GPT-5.3-Codex, GPT-5.2, and Gemini 3 Pro.

Long Context Mode

A mode for processing large amounts of text that pushes against context window limits. In Cursor, this is Max mode (token-based pricing). In Claude Code, the model’s 200K window handles most cases natively.

M

Max Mode

Cursor’s enhanced context mode that uses token-based pricing to provide maximum model capabilities and the full context window for complex tasks.

MCP (Model Context Protocol)

An open standard created by Anthropic for connecting AI assistants to external tools and data sources. MCP servers expose capabilities (database queries, API calls, browser automation, file operations) that any MCP-compatible agent can use. All three tools — Cursor, Claude Code, and Codex — support MCP.

MCP Server

A program that implements the MCP specification and exposes one or more tools to AI agents. Examples: GitHub MCP (PR and issue management), Postgres MCP (database queries), Puppeteer MCP (browser automation), Context7 MCP (library documentation).

Memory System

Persistent project-specific knowledge that survives between sessions. Cursor uses the “Memories” feature. Claude Code uses CLAUDE.md files and the /memory command. Codex uses AGENTS.md and its project configuration.

Message Limit

Rate limiting based on the number of interactions within a time window. Claude Code Pro allows roughly 10-40 messages per 5-hour session. Codex and Cursor have their own quota systems tied to subscription tiers.

Multi-file Editing

The ability to coordinate changes across multiple files in a single operation. A core strength of all three tools — Agent mode in Cursor, default behavior in Claude Code, and standard operation in Codex.

N

Notifier Integrations

Codex’s ability to send notifications and receive triggers from external services. Supports GitHub (issues, PRs), Slack (messages, threads), and Linear (tickets). Enables automated workflows where an agent responds to real-world events.

O

Opus 4.6

Anthropic’s most capable model (February 2026). Top SWE-Bench scores, best agentic performance, strongest reasoning. The default recommendation for complex coding tasks. Available in Claude Code, Cursor, and via API.

P

PAT (Personal Access Token)

A secure authentication token for Git services like GitHub. Required for CLI operations and many MCP server integrations.

Permission Mode

Controls what an AI agent is allowed to do without asking. Claude Code offers granular permission settings per tool. Codex offers approval modes including on-request (asks for everything), on-failure (auto-approves, asks on errors), and never (full autonomy), plus the --full-auto flag for maximum automation.

Planning Mode

An explicit phase where the AI breaks down a complex task into structured steps before implementing anything. In Claude Code, triggered by including “plan” or “think” in your prompt. In Cursor, use Ask mode first, then switch to Agent mode. In Codex, the agent plans automatically before execution.

PRD (Product Requirements Document)

A specification of features and functionality. The PRD-to-Plan-to-Todo methodology is a proven pattern for complex features across all three tools: write the PRD, ask the AI to create a plan, convert the plan into a checklist, then execute.

Privacy Mode

A setting that prevents your code from being used for model training. Critical for enterprise compliance and IP protection. All three tools offer privacy guarantees at paid tiers.

Prompt Engineering

The practice of crafting effective instructions for AI models. Includes techniques like few-shot examples, chain-of-thought reasoning, explicit constraints, and structured output formats. The single highest-leverage skill for AI-assisted development.

R

Rules Directory

Cursor’s .cursor/rules/ folder containing project-specific AI behavior guidelines in markdown files. Rules are automatically loaded based on file context, glob patterns, or manual selection. Equivalent in function to CLAUDE.md and AGENTS.md.

S

Sandbox

An isolated execution environment that prevents AI-generated code from affecting your real system. Codex runs every task in a sandboxed worktree by default. Claude Code can be sandboxed via Docker containers. Cursor’s sandboxed terminals (macOS) provide similar isolation.

Semantic Search

AI-powered search that understands meaning rather than just matching keywords. Cursor’s @codebase search uses embeddings. Claude Code uses agentic search (reading and reasoning about files). Both find conceptually relevant code even when the exact terms differ.

Slash Commands

Special commands prefixed with / that trigger built-in or custom actions. Claude Code: /help, /clear, /compact, /think, /model. Codex: /help, /model, /new. Cursor: /Generate Cursor Rules, /Reset Context.

Slow Requests

Rate-limited API calls in Cursor’s free and lower tiers. Unlimited in quantity but processed with increasing delays during peak usage.

SOC 2

A security compliance certification for handling customer data. Both Cursor and Claude Code (Enterprise) maintain SOC 2 Type II certification.

Sonnet 4.5

Anthropic’s cost-effective model with a 1M token context window. Excellent coding performance at roughly one-fifth the cost of Opus 4.6. The default choice for budget-conscious development and tasks requiring very large context.

State Context

Information describing the current state of code, errors, or environment (descriptive). Combined with intent context (what you want to achieve), it forms a complete prompt.

Sub-agent

A separate AI instance spawned by the main agent to handle a specific subtask. In Claude Code, sub-agents run with their own context while the parent agent continues. In Cursor, subagents (v2.4+) can be specialized for testing, documentation, or refactoring. In Codex, parallel cloud tasks function similarly.

T

Tab Autocomplete

Cursor’s predictive code completion feature. Suggests multi-line completions based on surrounding context. Accept with Tab, accept partially with Cmd/Ctrl+Right Arrow, reject with Escape.

Terminal Integration

Direct command-line access within the tool. Claude Code is terminal-native. Cursor integrates terminals in the IDE. Codex CLI runs directly in your shell.

Thinking Tokens

The computational budget allocated for model reasoning. Extended thinking modes (/think, /ultrathink) use more thinking tokens, which improves quality on complex problems but increases cost and latency.

Token

The basic unit of text processed by LLMs. Roughly 3-4 characters in English. Context windows, pricing, and rate limits are all measured in tokens.

Tool Use

The ability of an AI model to call external functions — reading files, executing commands, making API requests, querying databases. The foundation of agentic behavior. MCP standardizes how tools are exposed to models.

U

Ultrathink

Claude Code’s maximum reasoning mode. Allocates the highest computational budget for extremely complex problems requiring deep analysis. Use sparingly — it is slower and more expensive, but significantly more capable on hard problems.

V

Version Control Integration

Built-in Git capabilities: commits, branches, diffs, pull requests, merge conflict resolution. All three tools can operate Git autonomously when permitted.

Vim Mode

An optional keyboard input mode in Claude Code that enables vim-style navigation and editing in the prompt input. Toggle with /vim or configure permanently via /config.

W

Worktree

A Git worktree is a separate working directory linked to the same repository. Codex uses worktrees to give each agent task its own isolated file system, so multiple tasks can run in parallel without interfering with each other. See also: Git Worktrees.

Workspace

The root directory (and subdirectories) of your current project. All three tools scope their operations to the workspace.

Y

YOLO Mode

High-trust mode where the AI agent can execute commands and make changes without requesting permission for each action. In Claude Code: --dangerously-skip-permissions. In Codex: the --full-auto flag or approval_policy = "never". In Cursor: trusting all tool calls in Agent mode. Use with version control and ideally in a sandboxed environment.

Extensibility: Agent Skills | MCP | MCP Server | Skills.sh

Security and Enterprise: Enterprise Mode | Privacy Mode | SOC 2 | Permission Mode