How do you compact the context in Claude Code?
/compact instructions — Free up context by summarizing the conversation so far
Type /compact to summarize the conversation so far and free up context. You can pass focus instructions after the command (for example /compact keep the test failures) to steer what the summary preserves. Cursor's equivalent is /summarize and Codex CLI's is /compact.
Related Claude Code shortcuts: Built-in Slash Commands (first 25 of 106)
| Command / Syntax | What it does | Notes |
|---|---|---|
| /add-dir <path> | Add a working directory for file access during the current session | Type a partial path to see matching directory suggestions; press Tab to accept one. Most .claude/ configuration is not discovered from the added directory. |
| /advisor model|off | Enable or disable the advisor tool, which consults a second model for guidance at key moments during a task | Accepts fable, opus, sonnet, or a full model ID. fable requires Fable 5 access. |
| /agents | As of v2.1.198, running /agents prints a reminder to ask Claude to create or manage subagents, or to edit .claude/agents/ or... | On v2.1.197 and earlier, opens an interactive interface for creating and managing subagent configurations |
| /autocompact auto|<tokens> | Set the auto-compact window: how full the context window gets before Claude Code compacts automatically | Pass a size such as 500k, or auto to return to the window tuned for your model. Claude Code saves the value to user settings and applies it to the current session. |
| /autofix-pr prompt | Spawn a Claude Code on the web session that watches the current branch's PR and pushes fixes when CI fails or reviewers leave comments | Detects the open PR from your checked-out branch with gh pr view; to watch a different PR, check out its branch first. By default the cloud session is told to fix every CI failure and review... |
| /background prompt | Detach the current session to run as a background agent and free this terminal | Pass a prompt to send one more instruction before detaching. Monitor the session with claude agents. |
| /batch <instruction> | Skill. Orchestrate large-scale changes across a codebase in parallel | Researches the codebase, decomposes the work into 5 to 30 independent units, and presents a plan. Once approved, spawns one background subagent per unit in an isolated git worktree. |
| /branch name | Create a branch of the current conversation at this point, so you can try a different direction without losing the conversation as it stands | Switches you into the branch and preserves the original, which you can return to with /resume. To run a copy as a separate background session instead of switching into it, use /fork; to hand a... |
| /btw question | Ask a side question about the current session without adding to the conversation | If you run /btw without a question, Claude Code shows your most recent side question so you can browse earlier answers; if you haven't asked one yet, Claude Code prints a usage line. Before... |
| /bug report | Report a bug or share your conversation | You choose how much session history to include and confirm on a consent screen before anything is sent. When you're signed in to Anthropic on a first-party connection, the report goes to... |
| /cd <path> | Move this session to a new working directory, keeping the conversation and its prompt cache | Type a partial path to see matching directory suggestions; press Tab to accept one. Claude Code prompts you to trust the workspace if you haven't worked in it before, and --resume finds the moved... |
| /chrome | Configure Claude in Chrome settings | Type the command in the Claude Code prompt. |
| /claude-api migrate|managed-agents-onboard|prompt-audit | Skill. Load Claude API and Managed Agents reference material for your project's language | Also activates automatically when your code imports anthropic or @anthropic-ai/sdk. Run migrate to upgrade existing Claude API code to a newer model, managed-agents-onboard for a walkthrough that... |
| /clear name | Start a new conversation with empty context | Pass a name to label the previous conversation in the /resume picker. To free up context while continuing the same conversation, use /compact instead. |
| /code-review low|medium|high|xhigh|max|ultra --fix --comment pr#|branch|path | Skill. Review the current diff, or a PR number, branch, or path you pass, for correctness bugs and cleanup opportunities | Pass --fix to apply findings, --comment to post them as inline GitHub PR comments, or ultra to run a deep cloud review. With ultra on a github.com PR target, --post preselects posting the finished... |
| /color color|default | Set the prompt bar color for the current session | Available colors: red, blue, green, yellow, purple, orange, pink, cyan. Use default to reset, or run with no argument to pick a random color. |
| /compact instructions | Free up context by summarizing the conversation so far | Optionally pass focus instructions for the summary. See how compaction handles rules, skills, and memory files |
| /config key=value ... | Open the Settings interface to adjust theme, model, output style, and other preferences | From v2.1.181, pass one or more key=value pairs to set a setting directly without opening the interface, for example /config thinking=false. From v2.1.182, named shorthand keys are also accepted,... |
| /context all | Visualize current context usage as a colored grid | Shows optimization suggestions for context-heavy tools, memory bloat, and capacity warnings. When the conversation exceeds the context window, the output includes a warning showing how far over... |
| /copy N | Copy the last assistant response to clipboard | Pass a number N to copy the Nth-latest response: /copy 2 copies the second-to-last. When code blocks are present, shows an interactive picker to select individual blocks or the full response. |
| /cost | Alias for /usage | Type the command in the Claude Code prompt. |
| /dataviz request | Skill. Design guidance for charts, graphs, and dashboards | Claude picks the chart form for the data, assigns color by role, validates the palette for colorblind safety and contrast with a bundled script, and applies mark, interaction, and accessibility... |
| /debug description | Skill. Enable debug logging for the current session and troubleshoot issues by reading the session debug log | Debug logging is off by default unless you started with claude --debug, so running /debug mid-session starts capturing logs from that point forward. Optionally describe the issue to focus the analysis |
| /deep-research <question> | Workflow. Fan out web searches on a question, fetch and cross-check sources, and synthesize a cited report | Type the command in the Claude Code prompt. |
| /design-login | Authorize design-system access for /design-sync with your claude.ai account | Type the command in the Claude Code prompt. |
From the Claude Code reference (111 entries) · all how-to answers
Why compacting exists
Claude Code keeps the whole conversation — every file it read, every command output — in the model's context, and long sessions eventually hit the limit or slow down. /compact asks the model to write a summary of the session so far and replaces the history with that summary, keeping the working state (which files matter, what was decided, what is left) while discarding the transcript. Claude Code also compacts automatically when the context nears its limit; running it by hand at a natural checkpoint produces a better summary than an automatic one in the middle of a task.
Steering the summary
Text after the command becomes instructions for the summary: /compact focus on the failing tests and the API changes tells the model what to preserve. Use this when a session has wandered — the summary keeps the thread you name and drops the detours. A good moment to compact is after finishing one sub-task and before starting the next, so the summary reads like a handover.
Related commands
/clear discards the conversation entirely and starts fresh in the same directory, which is faster when nothing needs to carry over. /cost shows the tokens consumed so far, a useful prompt for when to compact. CLAUDE.md, the project instructions file, is re-read after compaction, so anything that must always be known belongs there rather than in the conversation.