| # | Command | Tool | Category | Tool |
|---|---|---|---|---|
| 1 | /agents Manage agent configurations and monitor background agents running in parallel. | Claude Code | parallel-agents | Claude Code |
| 2 | /background Detach the current session to run as a background agent and free this terminal. Optionally pass a final instruction before detaching. | Claude Code | parallel-agents | Claude Code |
| 3 | /batch Orchestrate large-scale changes across a codebase in parallel. Decomposes work into 5–30 independent units, each in its own git worktree with its own PR. | Claude Code | parallel-agents | Claude Code |
| 4 | /btw Ask a quick side question without adding it to the main conversation history. | Claude Code | context-management | Claude Code |
| 5 | /checkup Audit and clean up your Claude Code setup: unused skills, MCPs, and plugins, CLAUDE.md dedup and splitting, slow hooks, auto mode, and permission pre-approval. Confirms before making changes. | Claude Code | diagnostics | Claude Code |
| 6 | /claude-api Load Claude API reference, migrate deprecated model IDs, or onboard Claude Managed Agents (schedules + vaults). | Claude Code | integrations | Claude Code |
| 7 | /clear Start a new conversation with empty context. Previous session stays in /resume; use /rewind (v2.1.191+) to undo a clear in-session. Aliases: /reset, /new. | Claude Code | session-management | Claude Code |
| 8 | /code-review Review the current diff for correctness bugs and for reuse, simplification, and efficiency cleanups. Pass --fix to apply findings, --comment to post as GitHub PR comments, or ultra for a deep cloud review. | Claude Code | code-review | Claude Code |
| 9 | /compact Free up context by summarizing the conversation so far. Optionally pass focus instructions for the summary. | Claude Code | context-management | Claude Code |
| 10 | /context Visualize current context usage as a colored grid. Shows optimization suggestions for context-heavy tools and capacity warnings. | Claude Code | context-management | Claude Code |
| 11 | /diff Open an interactive diff viewer showing uncommitted changes and per-turn diffs. Navigate with arrow keys between the git diff and individual Claude turns. | Claude Code | code-review | Claude Code |
| 12 | /doctor Diagnose and verify your Claude Code installation and settings. Press f to have Claude fix any reported issues. | Claude Code | diagnostics | Claude Code |
| 13 | /effort Set the model effort level: low, medium, high, xhigh, max, or ultracode. Takes effect immediately without waiting for the current response. | Claude Code | configuration | Claude Code |
| 14 | /fork Spawn a forked subagent that inherits the full conversation and works on a directive while you keep going in the main session. | Claude Code | parallel-agents | Claude Code |
| 15 | /goal Set a persistent goal — Claude keeps working across turns until the condition is met. View, pause, resume, or clear with subcommands. | Claude Code | planning | Claude Code |
| 16 | /hooks View hook configurations for tool events. Comma-separated matchers like Bash,PowerShell work correctly as of v2.1.191. | Claude Code | configuration | Claude Code |
| 17 | /init Initialize project with a CLAUDE.md guide covering repo conventions, commands, and agent instructions. | Claude Code | setup | Claude Code |
| 18 | /loop Run a prompt repeatedly on a schedule while the session stays open. Omit the interval and Claude self-paces between iterations. | Claude Code | automation | Claude Code |
| 19 | /mcp Manage MCP server connections and OAuth. v2.1.191 adds retries for capability discovery and OAuth token requests. | Claude Code | integrations | Claude Code |
| 20 | /memory Edit CLAUDE.md memory files, enable or disable auto-memory, and view auto-memory entries. | Claude Code | setup | Claude Code |
| 21 | /model Switch the AI model and save it as your default for new sessions. Adjust effort level with left/right arrows on models that support it. | Claude Code | configuration | Claude Code |
| 22 | /permissions Manage allow, ask, and deny rules for tool permissions. Recently-denied approvals persist on close as of v2.1.191. | Claude Code | configuration | Claude Code |
| 23 | /plan Enter plan mode to design your approach before coding. Claude proposes an execution plan for review before any implementation starts. | Claude Code | planning | Claude Code |
| 24 | /remote-env Set or view the default environment for cloud agents spawned from Claude Code sessions. | Claude Code | configuration | Claude Code |
| 25 | /resume Resume a previous conversation by ID or name, or open the session picker. | Claude Code | session-management | Claude Code |
| 26 | /rewind Rewind code and/or conversation to a checkpoint. As of v2.1.191, restore context from before /clear ran. Aliases: /checkpoint, /undo. | Claude Code | session-management | Claude Code |
| 27 | /schedule Create, update, list, or run Anthropic-managed cloud routines from the CLI. Alias: /routines. | Claude Code | automation | Claude Code |
| 28 | /security-review Analyze pending branch for security vulnerabilities — injection, auth issues, data exposure, and other OWASP risks. | Claude Code | code-review | Claude Code |
| 29 | /simplify Review changed code for cleanup opportunities and apply the fixes. Four review agents run in parallel covering reuse, simplification, efficiency, and abstraction level. | Claude Code | code-review | Claude Code |
| 30 | /skills List available skills and manage which are shown to Claude. Press t to sort by token count, Space to hide a skill. | Claude Code | configuration | Claude Code |
| 31 | /stop Stop the attached background session while keeping its transcript and git worktree. | Claude Code | parallel-agents | Claude Code |
| 32 | /tasks View and manage background work in the current session. Stops from the tasks panel are permanent as of v2.1.191. | Claude Code | parallel-agents | Claude Code |
| 33 | /usage Show session cost, plan usage limits, and activity stats. Includes breakdown by skill, subagent, plugin, and MCP server on paid plans. | Claude Code | diagnostics | Claude Code |