Everything you need in one place
The core workflow for effective AI-assisted development
Let Claude understand the codebase first
"What patterns exist for X in this codebase?"
Use Plan Mode (Shift+Tab) to design
"Plan implementing Y following existing patterns"
Implement following the plan
"Implement the plan"
Verify with tests
"Write tests and run them to verify"
Thinking is always on — control depth with /effort levels
Quick answers, minimal reasoning
Fast responses for simple tasks
Balanced depth (default)
Good for most development work
Deep analysis and thorough exploration
Architecture decisions, security reviews
Multiple ways to enter multi-line prompts
/terminal-setup only if you need to configure other terminals.
Multiple ways to work with images
Clickable PR link in footer with color-coded review state (requires gh CLI)
Approved
Pending review
Changes requested
# One-shot / headless mode
claude -p "prompt" # Non-interactive
claude -p "prompt" --output-format json # JSON output
cat file | claude -p "analyze" # Pipe input
# Session management
claude --continue # Continue last session
claude --resume # Resume named session
claude --fork-session # Fork existing session
claude --add-dir ../other-repo # Add extra directory
# Safety & limits
claude --allowedTools Read,Edit # Restrict tools
claude --max-turns 10 # Limit turns
claude --max-budget-usd 5 # Set spend limit
# Model selection & effort
claude --model claude-opus-4-6 # Pick model
claude --fallback-model claude-haiku-4-5 # Fallback
claude --effort high # Deep reasoning depth
claude --verbose # See thinking
Required for Alt/Option shortcuts (Option+T, Alt+P)
# Add to ~/.zshrc or ~/.bashrc
alias c="claude"
alias cc="claude --continue" # Continue last session
alias cr="claude --resume" # Resume with selection
alias cq="claude -p" # Quick single prompt
alias cplan="claude --permission-mode plan" # Start in Plan Mode
"What X patterns exist in this codebase?"
"Follow existing patterns for Y"
"Write tests first, DO NOT implement yet"
"Run the tests to verify"
"Use X but not Y"
"think hard about the failure modes for..."
# Memory commands
/memory # Opens memory in editor
/init # Bootstrap starter CLAUDE.md
# Project Guidelines
## Tech Stack
- Language/Framework versions
- Key dependencies
## Code Style
@Rule Naming conventions
@Rule Structural patterns
## Error Handling
@Rule Exception strategy
@Rule Logging patterns
DO:
```java
// Good example with context
```
DO NOT:
```java
// Bad example to avoid
```
## Testing
@Rule Test framework patterns
@Rule Naming conventions
## DO NOT
- Anti-patterns to avoid
- Common mistakes
.claude/
skills/
java-testing.md # Skill file
code-review.md # Another skill
refactor.md # Another skill
# Skill file format
---
description: Generate tests following team patterns
---
# Instructions go here
Apply to: $ARGUMENTS
## Instructions
## Reference Examples
@src/test/ExampleTest.java
## DO NOT
/java-testing MerchantService
Automation guardrails that run before/after tool actions
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "echo 'About to run a command'"
}
]
}
],
"PostToolUse": [
{
"matcher": "Write",
"hooks": [
{
"type": "command",
"command": "echo 'File was written'"
}
]
}
]
}
}
Runs before a tool executes
Validate, gate, or log actions
Runs after a tool completes
Notify, transform, or audit results
Session lifecycle
Initialize env, cleanup, reporting
When user submits a prompt
Input validation, logging
Agent lifecycle
Track agent spawning and results
Agent team quality gates
Quality checks, task routing
When settings change
React to config updates
Agent team worktree lifecycle
Setup/teardown for agent worktrees
Extend Claude Code with community-built capabilities
# Plugin commands
claude plugin add <plugin-name> # Install a plugin
claude plugin list # List installed plugins
claude plugin remove <plugin-name> # Remove a plugin
Skills, hooks, MCP servers, and rules in one package
Install once, get everything
Share and reuse team tooling
Publish your own plugins
{
"mcpServers": {
"postgres": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-postgres",
"postgresql://user:pass@localhost:5432/db"
],
"lazyLoad": true
}
}
}
# MCP commands
/mcp # List configured servers
/mcp add # Add a new server
# Config priority: .mcp.json > .claude/settings.json > ~/.claude/settings.json
# SSE transport is deprecated — use HTTP (streamable) transport
# Tool Search: lazy-loads MCP tools on demand (95% context savings)
/helpShow help and available commands/memoryView and manage memory/initGenerate starter CLAUDE.md/mcpManage MCP servers/clearClear conversation context/compactSummarize and compact context/fastToggle 2.5x faster output (same model)/effortSet reasoning depth (low/medium/high)/debugAttach debugger to Claude Code/configOpen Claude Code configuration/costShow token usage and costs/copyInteractive code block picker — select and copy specific blocks/modelSwitch model/planEnter plan mode/permissionsManage tool permissions/renameName sessions for easy finding/resumeResume previous conversations/rewindRewind conversation and/or code/contextVisualize context usage/doctorInstallation health check/statsUsage statistics and streaks/statusShow session status/exportExport conversation/tasksView running background tasks/teleportResume web session locally/terminal-setupConfigure Shift+Enter multiline/themeChange color theme/todosView todo items/vimEnable vim keybindings/skill-nameInvoke a project skill/remote-controlContinue session from phone/browser/mobileDownload QR for Claude app/btwSide question without polluting context/diffInteractive diff viewer/loopRecurring prompts on interval/pluginManage plugins/sandboxConfigure sandboxing/hooksManage hooks/agentsManage agent definitions/output-styleSet output style/keybindingsCustomize keyboard shortcutsBleeding-edge features for the curious — launched in the last 60 days
Continue local Claude Code sessions from your phone, tablet, or any browser. Your machine keeps running locally — the browser is just a window.
claude remote-control — new session with remote access/remote-control or /rc — from existing sessionFirst official MCP extension — tools can return interactive HTML interfaces (dashboards, forms, 3D visualizations) right inside the conversation.
New frontier model with 200K context (1M beta) and 128K max output tokens — double the previous limit.
thinking: {type: "adaptive"}inference_geo parameterExpanded capabilities for multi-agent coordination.
Shift+Down to cycle teammates, type to messageTeammateIdle and TaskCompleted eventsclaude agents CLI — list all configured agentsteammateMode setting: "auto", "in-process", or "tmux"Smaller but useful features from recent releases.
/sandbox — OS-level filesystem & network isolation for untrusted code/loop — recurring prompts on interval (scheduled tasks)/rename — auto-generates session names from contextclaude auth subcommands: login, status, logout/mobile — QR code to download Claude iOS/Android appspinnerTipsOverride — customize loading tipsOfficial Anthropic engineering guide
Full Claude Code documentation
CLAUDE.md and memory docs
Model Context Protocol
Custom skills documentation
Automation guardrails (17 events)
Extend with community plugins
OS-level filesystem & network isolation
Built-in & custom subagents
Multi-agent coordination with worktrees
Build custom agents with TypeScript
/loop recurring prompts & cron
/rewind to restore states
Default, Explanatory, Learning, custom
Latest features and updates