Reference

Claude Code cheatsheet

Integrations, commands, menu surfaces, and orchestration — one page. Not Omarchy-specific, but it's the terminal agent doing most of the work on this machine, so it earns a spot in the docs. Audited against Claude Code v2.1.22x, Aug 2026.

Full-viewport infographic — fits a single 1497×946 screen with no scrolling, scales to yours. Esc to close.

Mental model

Four words, four jobs: a Skill is instructions Claude reads and follows. MCP is a live wire to an external system. A Hook is a script that fires on an event, guaranteed, whether or not Claude "decides" to. A Plugin is a zip file bundling any of the above for reuse or sharing. Everything else on this page — subagents, agent teams, workflows, routines, Dispatch — is a different answer to "where does the loop run and what does it share context with."

Claude Code's own built-in tools (file edits, search, shell, web) already cover most coding tasks. Everything below is the extension layer: what you add to teach it your conventions, connect it to systems it can't otherwise reach, and automate what would otherwise be manual.

Integrations: MCP vs Skills vs Plugins

These get lumped together because they're installed and browsed from the same Customize menu, but they solve three different problems and mostly stack rather than compete.

MCP Protocol

The plumbing. Connects Claude to a live external system — auth and the actual API calls live on the server side.

  • Provides tools + data access, not knowledge
  • Config: .mcp.json, managed with /mcp
  • Shows up as regular tools in hook events
Eg: query Postgres, post to Slack, drive a browser, call the GitHub API

Skills Prompt

Knowledge and workflows loaded on demand — either you type /name, or Claude matches your task to its description.

  • Reference material or a multi-step runbook
  • Lives in .claude/skills/<name>/SKILL.md (project) or ~/.claude/skills/ (personal)
  • Can pre-approve tools, fork to a subagent, ship its own hooks
Eg: a /deploy runbook, your API style guide, a code-review checklist

Plugins Package

Not a fourth capability — a directory that bundles skills, hooks, subagents, and MCP servers into one installable, shareable unit.

  • Skills come out namespaced: /my-plugin:review
  • Distributed via marketplaces, installed with /plugin
  • Reuse the same setup across repos or teammates
Eg: a "database helper" plugin = MCP connection + schema-aware skill + a hook blocking unscoped DELETE
AspectMCPSkillPlugin
What it isProtocol for connecting to external servicesKnowledge, workflows, reference materialPackaging layer for the other three
ProvidesTools and data accessInstructions Claude followsA turnkey bundle to install in one step
Triggered byA tool call Claude makesTyping /name, or Claude matching intentInstalling the plugin (activates its parts)
Lives in.mcp.json.claude/skills/*/SKILL.mdA directory with .claude-plugin/plugin.json
Use whenLive data or real-world actions are neededClaude should reason through repeatable stepsThe same setup needs to travel to another repo or person

"MCP vs Skills vs Plugins" is a false trichotomy. You don't pick one — a skill teaches Claude how to use an MCP server well, and a plugin is how you hand both to someone else.

Slash commands

Type / to filter the live list — it's the source of truth over any cheatsheet. Skill commands are prompts Claude can also trigger itself; Workflow commands fan a task out across many background subagents. Everything unmarked is built-in, fixed CLI logic.

Start a project

/initGenerate a starter CLAUDE.md
/memoryEdit CLAUDE.md, manage auto-memory
/mcpManage MCP server connections
/permissionsAllow / ask / deny rules for tools
/pluginInstall & manage plugins
/doctorSetup checkup, can fix issues Skill

During a task

/planEnter plan mode before a large change
/modelSwitch model, set effort with arrow keys
/effortSet reasoning depth: low → max, ultracode
/contextVisualize what's filling the window
/compactSummarize the conversation to free space
/goalKeep working across turns until a condition holds

Parallel & background work

/tasksList background work & finished subagents
/backgroundDetach the session to run unattended
/batchDecompose & parallelize a repo-wide change Workflow
/subtaskFork a background subagent, result returns here
/forkCopy this conversation into a new background session
/branchBranch the conversation to try another direction

Ship it

/diffInteractive viewer for uncommitted changes
/code-reviewDiff review, --fix to apply Skill
/code-review ultraDeep multi-agent cloud review
/security-reviewVulnerability scan of the branch diff
/simplifyParallel cleanup pass, applies fixes Skill

Between sessions

/clearNew conversation, keeps project memory
/resumeReopen an earlier conversation by ID or picker
/rewindRoll code and/or chat back to a checkpoint
/renameName the session for the resume picker
/teleportPull a web session into this terminal
/cdMove the session to a new working directory

Automation & housekeeping

/scheduleCreate/manage routines (schedule-only from CLI)
/loopRepeat a prompt on an interval Skill
/hooksView configured hooks for tool events
/agentsPointer to managing subagents in .claude/agents/
/workflowsWatch/pause/resume dynamic workflow runs
/usageCost, plan limits, per-skill/MCP breakdown

MCP servers can also expose their own commands, discovered dynamically as /mcp__<server>__<prompt>.

Outside the terminal REPL, the Desktop and mobile apps add a few surfaces that aren't slash commands at all.

Artifacts

Publish a session's output as a live, interactive page instead of scrollback — updates in place as the session continues.

  • Private by default; share org-wide or, if enabled, publicly
  • Can pull live data via MCP connectors (separate toggle)
  • Pro/Max/Team/Enterprise; org admins can scope by role
Eg: a PR walkthrough with annotated diffs, an incident timeline that fills in as Claude investigates

Routines

A saved cloud job — prompt, repos, connectors — that runs on Anthropic's infrastructure, not your machine.

  • Trigger by schedule, HTTP API call, GitHub event, or all three
  • Create at claude.ai/code/routines, Desktop "New remote task", or /schedule (schedule-only)
  • Keeps running with your laptop closed
Eg: nightly dependency-audit PR, "review every new pull request" on a GitHub trigger

Dispatch

One persistent chat in the Cowork tab. Describe an outcome; it plans the work and spawns child tasks as separate sessions.

  • Runs on your desktop — needs Desktop open and awake
  • Reaches local files, connectors, plugins, installed apps
  • Spawned Code sessions carry a "Dispatch" badge; push notification on finish
Eg: text a task from your phone, approve the diff later from the notification

Customize

The sidebar hub that unifies Skills, Connectors, and Plugins into one directory instead of three separate menus.

  • Install, toggle, and browse marketplaces from one place
  • Team/Enterprise: org-shared skills surface here too
  • Per-plugin "Customize" opens a task to tune it to your workflow
Eg: Customize → Connectors → add Slack; Customize → Plugins → browse marketplace

Dispatch and cloud routines look similar but differ on one axis: Dispatch needs your desktop awake and can touch local files; routines run headless on Anthropic's servers and can't.

Automation and orchestration

Several features all boil down to "run more Claude." The difference is where the loop executes and what it shares context with.

PrimitiveContextSpawned byRuns whereBest for
Subagent Own isolated context, returns a summary Claude automatically, /subtask, or a skill with context: fork Your session, foreground or background Keeping a noisy side task out of your main context
Agent team (experimental) Independent sessions, shared task list, can message peers You, configuring teammates Your machine, in parallel Agents that need to negotiate or split work themselves
Dynamic workflow A JS script holds the loop; intermediate results never enter Claude's context Ask for "a workflow", or /effort ultracode Background runtime, up to ~1,000 subagents Codebase-wide audits, migrations, cross-checked research
/batch 5–30 independent units, each a fresh subagent You, via /batch <task> One background subagent per unit, its own git worktree, opens a PR Large parallel refactors across a repo
Hook None — a shell command, HTTP call, or prompt, not a conversation A lifecycle event (PreToolUse, Stop, …) Wherever Claude Code runs Guardrails and side effects that must happen every time
Routine A fresh Claude Code run per trigger Schedule, API call, or GitHub event Anthropic's cloud — keeps going if your laptop is off Unattended recurring or event-driven jobs

Hooks: the lifecycle events

Hooks are the one primitive here with a guarantee: they always fire on their event, whether or not Claude "chooses" to. That's what makes them the right tool for anything that must hold every time — PreToolUse can even block the tool call outright.

EventFires
SessionStartSession begins or resumes
UserPromptSubmitYou submit a prompt, before Claude processes it
PreToolUseBefore a tool call runs — can block it
PostToolUse / PostToolUseFailureAfter a tool call succeeds / fails
NotificationClaude Code sends a notification (permission prompt, idle, etc.)
SubagentStart / SubagentStopA subagent is spawned / finishes
PreCompactBefore context compaction
Stop / StopFailureClaude finishes a turn / a turn ends on an API error
SessionEndSession terminates

Put guardrails in hooks, not prose. "Never edit .env" in CLAUDE.md is a request; a PreToolUse hook that blocks the edit is enforcement.

Which do I use?

I want to…Reach for
Give Claude a repeatable, reasoned workflowSkill
Connect to a live external systemMCP
Ship a whole setup to teammates or another repoPlugin
Guarantee something happens the same way, every timeHook
Keep a noisy side task out of my context windowSubagent
Run 10+ agents against a whole codebaseDynamic workflow, or /batch for repo-wide refactors
Run a job on a schedule, from an API, or on a GitHub event — even offlineRoutine
Assign work from my phone using files on my own machineDispatch
Publish a shareable, live view of what a session producedArtifact
Manage all my skills, connectors, and plugins in one placeCustomize

Also worth knowing

A few pieces that don't fit neatly under the four headings above but come up in almost every session — worth having on this page too.

CLAUDE.md & memory

Always-on project context, loaded every session — not a skill, so it costs context whether or not it's relevant this turn.

  • /init generates one, /memory edits it
  • Keep it under ~200 lines; move reference material to skills or .claude/rules/
  • Nested CLAUDE.md files load only when working in that subtree

Permissions & sandboxing

How much Claude can do without asking, ranging from ask-every-time to fully autonomous.

  • /permissions: allow / ask / deny rules by tool
  • /plan: read-only analysis before any edits
  • /sandbox: OS-level isolation on supported platforms

Context & effort

The two dials that trade cost and speed against depth and accuracy.

  • /context visualizes what's filling the window
  • /compact summarizes; /autocompact sets the trigger point
  • /effort low…max, or ultracode to auto-plan workflows

Sessions & worktrees

Parallel work stays isolated because each session/worktree is its own git checkout.

  • /resume, /branch, /fork, /subtask
  • Desktop: split panes, Cmd/Ctrl+N for a new session
  • Changes in one worktree don't affect others until committed

Checkpoints

A safety net that's easy to forget exists mid-task.

  • /rewind rolls conversation and/or code back to any earlier point
  • Also reachable after /clear, to restore the prior conversation

Headless & CI

Claude Code isn't only interactive.

  • claude -p "<prompt>" for scripts and pipelines
  • /install-github-app wires up GitHub Actions
  • Agent SDK drives full sessions from Python/TypeScript

Cost & usage

Worth checking before automation quietly gets expensive.

  • /usage (aliases /cost, /stats)
  • Breaks down spend by skill, subagent, plugin, and MCP server
  • Routines attach every connected connector by default — trim what a job doesn't need

Fastest way to keep this current: run /release-notes in a live session, or ask Claude "what changed in Claude Code recently?" — this page is a snapshot, the CLI's own /help and / menu are never stale.