Maintained by Jaden Razo · RaizHost
Not affiliated with Anthropic, OpenAI, or Google. Data sourced from each provider's public docs, status pages, npm, and GitHub.
Claude Code — LLM Tracker
CLAUDE · LLM TRACKER ·
How to use Claude Code in 2026, Claude Code, MCP, and the Anthropic API — version-pinned and re-verified as releases ship. Every guide is version-pinned and re-verified as new releases ship — so stale advice flags itself instead of quietly misleading you.
NEW TO CLAUDE CODE The best setup for 2026 Skip the feature tour. Shortest path from empty directory to a Claude Code setup that behaves well for real work — native installer, settings.json, skills, and the two MCP servers worth the context tax.
ALREADY A POWER USER Tips worth 10 minutes Ultrareview, forked subagents, skills vs. commands — the things that changed in the last quarter.
BUILDING WITH THE API Claude Code releases & SDKs Version ladder from npm, CHANGELOG, and the GitHub releases of every language SDK — deduped into one timeline.
CONTEXT ENGINEERING Long sessions, sharper Layered CLAUDE.md, auto-memory, compaction. The discipline that makes 1M tokens feel like 100K.
TOP MCP SERVERS
The short list worth your context budget auto-refreshed every 2h
Secure file operations with configurable access controls — lets Claude read, write, and list files on the local machine.
npx -y @modelcontextprotocol/server-filesystemreference
Tools to read, search, and manipulate Git repositories without shelling out.
uvx mcp-server-gitreference
ESSENTIAL COMMANDS & FLAGS
Claude Code reference Slash commands · 24 /fork — Spawn a forked subagent: a background subagent that inherits the full conversation and works on the directive while you keep going. Its result returns to your conversation when it finishes. To switch into a copy of the conversation yourself, use /branch. Before v2.1.161, /fork is an alias for /branch /deep-research — Workflow. Fan out web searches on a question, fetch and cross-check sources, and synthesize a cited report /workflows — Open the workflow progress view to watch, pause, resume, or save running and completed workflows /reload-skills — Re-scan skill and command directories so skills added or changed on disk during the session become available without restarting. Reports how many skills are available and how many were added or removed. Added in v2.1.152 /code-review — Skill. Review the current diff for correctness bugs and for reuse, simplification, and efficiency cleanups. Pass --fix to apply findings to your working tree, --comment to post them as inline GitHub PR comments, or ultra to run a deep cloud review. From v2.1.154, /simplify runs a separate cleanup-only review that applies fixes without hunting for bugs. See Review a diff locally for effort levels and targeting
LATEST GUIDES
Version-pinned, staleness-aware TRACKER FRESHNESS PROOF
The pollers behind this page Web content fetching and conversion for efficient LLM usage.
Knowledge-graph-based persistent memory across sessions.
npx -y @modelcontextprotocol/server-memoryreference
Structured step-by-step reasoning scratch-pad with revision and branching.
npx -y @modelcontextprotocol/server-sequentialthinkingreference
Reference / test server exercising every MCP feature (prompts, resources, tools) — the canonical learning-by-example server.
npx -y @modelcontextprotocol/server-everythingreference
Time and timezone conversion utilities.
uvx mcp-server-timereference
Connect and unify data across various platforms and databases with [MindsDB as a single MCP server](https://docs.mindsdb.com/mcp/overview).
/verify — Skill. Confirm a code change does what it should by building your project’s app, running it, and observing the result, rather than relying on tests or type checks. See Run and verify your app. Requires Claude Code v2.1.145 or later
/run — Skill. Launch and drive your project’s app to see a change working in the running app, not just in tests. See Run and verify your app. Requires Claude Code v2.1.145 or later
/run-skill-generator — Skill. Teach /run and /verify how to build, launch, and drive your project’s app from a clean environment by writing a per-project skill. Requires Claude Code v2.1.145 or later
/usage-credits — Configure usage credits to keep working when you hit a limit. Previously /extra-usage
/scroll-speed — Adjust mouse wheel scroll speed interactively, with a ruler you can scroll while the dialog is open to preview the change. Available in fullscreen rendering only and not in the JetBrains IDE terminal
/goal — Set a goal: Claude keeps working across turns until the condition is met. With no argument, shows the current or most recently achieved goal. clear, stop, off, reset, none, or cancel removes an active goal early
/background — 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. Alias: /bg
/stop — Stop the current background session. Only available while attached to a background session; the transcript and any worktree are kept. To detach without stopping, use /exit or press ←
/radio — Open Claude FM lo-fi radio in your browser. Prints the stream URL when no browser is available. Not available on Bedrock, Vertex, or Foundry
/copy — 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. Press w in the picker to write the selection to a file instead of the clipboard, which is useful over SSH
/debug — 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
/loop — Skill. Run a prompt repeatedly while the session stays open. Omit the interval and Claude self-paces between iterations. Omit the prompt and, where available, Claude runs an autonomous maintenance check or the prompt in .claude/loop.md. Example: /loop 5m check if the deploy finished. See Run prompts on a schedule. Alias: /proactive
/team-onboarding — Generate a team onboarding guide from your Claude Code usage history. Claude analyzes your sessions, commands, and MCP server usage from the past 30 days and produces a markdown guide a teammate can paste as a first message to get set up quickly. For claude.ai subscribers on Pro, Max, Team, and Enterprise plans, also returns a share link teammates can open directly in Claude Code
/clear — Start a new conversation with empty context. The previous conversation stays available in /resume. Pass a name to label the previous conversation in the /resume picker. To free up context while continuing the same conversation, use /compact instead. Aliases: /reset, /new
/compact — 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
/model — Switch the AI model and save it as your default for new sessions. For models that support it, use left/right arrows to adjust effort level. With no argument, opens a picker; press s on a row to switch for the current session only. The picker asks for confirmation when the conversation has prior output, since the next response re-reads the full history without cached context. Once confirmed, the change applies without waiting for the current response to finish
/theme — Change the color theme. Includes an auto option that matches your terminal’s light or dark background, light and dark variants, colorblind-accessible (daltonized) themes, ANSI themes that use your terminal’s color palette, and any custom themes from ~/.claude/themes/ or plugins. Select New custom theme… to create one
/branch — 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 hand a side task to a background subagent instead of switching into a copy yourself, use /fork
/doctor — Diagnose and verify your Claude Code installation and settings. Results show with status icons. Press f to have Claude fix any reported issues
Flags · 12 --exec — Run a shell command as a PTY-backed background job instead of starting a Claude session. Use with --bg to launch from the shell --prompt-suggestions — Emit a prompt_suggestion message after each turn with a predicted next user prompt. Requires --print, --output-format stream-json, and --verbose. See Prompt suggestions --bg — Start the session as a background agent and return immediately. Prints the session ID and management commands. Combine with --exec to run a shell command as a background job instead of a Claude session, or with --agent to run a specific subagent --plugin-url — Fetch a plugin .zip archive from a URL for this session only. Repeat the flag for multiple plugins, or pass space-separated URLs in a single quoted value --exclude-dynamic-system-prompt-sections — Move per-machine sections from the system prompt (working directory, environment info, memory paths, git-repo flag) into the first user message. Improves prompt-cache reuse across different users and machines running the same task. Only applies with the default system prompt; ignored when --system-prompt or --system-prompt-file is set. Use with -p for scripted, multi-user workloads --enable-auto-mode — Removed in v2.1.111. Auto mode is now in the Shift+Tab cycle by default; use --permission-mode auto to start in it --allow-dangerously-skip-permissions — Add bypassPermissions to the Shift+Tab mode cycle without starting in it. Lets you begin in a different mode like plan and switch to bypassPermissions later. See permission modes --fallback-model — Enable automatic fallback to a specified model when the default model is overloaded or not available, for example a retired model. Takes effect in print mode (-p) and in background sessions, which run non-interactively; ignored in an interactive session --remote-control — Start an interactive session with Remote Control enabled so you can also control it from claude.ai or the Claude app. Optionally pass a name for the session --ide — Automatically connect to IDE on startup if exactly one valid IDE is available --init — Run Setup hooks with the init matcher before the session (print mode only) --init-only — Run Setup and SessionStart hooks, then exit without starting a conversation
CLI subcommands · 9 claude daemon stop --any — Stop the background-session supervisor and the sessions it hosts. Pass --keep-workers to leave background sessions running so the next supervisor reconnects to them. --any confirms stopping an on-demand supervisor, which is the default. Use this to recover from an unresponsive supervisor claude daemon status — Print the background-session supervisor’s state, version, socket directory, and worker count for diagnostics. Exits 1 if the supervisor isn’t running claude attach <id> — Attach to a background session in this terminal claude logs <id> — Print recent output from a background session claude stop <id> — Stop a background session. Also accepts claude kill claude respawn <id> — Restart a background session, running or stopped, with its conversation intact. Use --all to restart every running session, e.g. to pick up an updated Claude Code binary claude rm <id> — Remove a background session from the list. The conversation transcript stays on your local machine, available through claude --resume claude project purge [path] — Delete all local Claude Code state for a project: transcripts, task lists, debug logs, file-edit history, prompt history lines, and the project’s entry in ~/.claude.json. Omit [path] to pick from an interactive list. Flags: --dry-run to preview, -y/--yes to skip confirmation, -i/--interactive to confirm each item, --all for every project. See Clear local data claude ultrareview [target] — Run ultrareview non-interactively. Prints findings to stdout and exits 0 on success or 1 on failure. Use --json for the raw payload and --timeout <minutes> to override the 30-minute default
Hook events · 3 MessageDisplay Setup PreCompact