Slash commands (custom commands)
Saved prompts stored as files in a repository and run in a coding agent by typing a short command such as /review or /plan.
A team that types the same instructions every day turns them into a file: a review checklist, a release procedure, “create a PRP for this issue”. The agent runs it when someone types the command, with arguments. In Claude Code custom commands have been merged into skills, which can also be loaded automatically when the task fits; other agents keep a commands folder.
Commands are how workflows such as PRP creation and execution spread across a team: the know-how is versioned with the code and reviewed like code. They differ from AGENTS.md, which the agent reads every session, and from agent skills in general, which the agent may pick on its own. Sets of commands are often shared as plugins.
Sources
- Claude Code Docs: Extend Claude with skills code.claude.com
Related terms
- Agent Skills: Folders with instructions, scripts and references that an agent loads only when the task needs them.
- AGENTS.md and CLAUDE.md: Files in a repository with the rules a coding agent reads at the start of every session.
- Agent plugins (marketplaces): Installable packages that add commands, skills, subagents, hooks and MCP servers to a coding agent, shared through public or company marketplaces.
- PRP (Product Requirement Prompt): A PRD rewritten for a coding agent: the goal and why, plus the exact files, patterns to follow and commands that prove the work is done.
