Claude Code Cheatsheet

1 printable page - Daily essentials for maximum productivity

Author: Florian BRUNIAUX | Founding Engineer @Méthode Aristote

Written with: Claude (Anthropic)

Version: 3.39.1 | Last Updated: March 2026

Essential Commands

Keyboard Shortcuts

File References

@path/to/file.ts    → Reference a file
@agent-name         → Call an agent
!shell-command      → Run shell command

Features Méconnues (But Official!)

Activate LSP: Add to ~/.claude/settings.json → { "env": { "ENABLE_LSP_TOOL": "1" } } (requires LSP server installed for your language: tsserver, pylsp, gopls, rust-analyzer, sourcekit-lsp…)

Pro tip: These aren’t “secrets”—they’re in the CHANGELOG. Read it!

Permission Modes

Shift+Tab to switch modes

Memory & Settings (2 levels)

Priority: Project overrides Personal

.claude/ Folder Structure

.claude/
├── CLAUDE.md           # Local memory (gitignored)
├── settings.json       # Hooks (committed)
├── settings.local.json # Permissions (not committed)
├── agents/             # Custom agents
├── commands/           # Slash commands
├── hooks/              # Event scripts
├── rules/              # Auto-loaded rules
└── skills/             # Knowledge modules

Typical Workflow

1. Start session      → claude
2. Check context      → /status
3. Plan Mode          → Shift+Tab × 2 (for complex tasks)
4. Describe task      → Clear, specific prompt
5. Review changes     → Always read the diff!
6. Accept/Reject      → y/n
7. Verify             → Run tests
8. Commit             → When task complete
9. /compact           → When context >70%

Context Management (CRITICAL)

Statusline

Model: Sonnet | Ctx: 89.5k | Cost: $2.11 | Ctx(u): 56.0%

Watch Ctx(u): → >70% = /compact, >85% = /clear

Enhanced statusline (ccstatusline): Add to ~/.claude/settings.json:

{ "statusLine": { "type": "command", "command": "npx -y ccstatusline@latest", "padding": 0 } }

Context Thresholds

Actions by Symptom

Context Recovery Commands

Under the Hood (Quick Facts)

Deep dive: Architecture & Internals

Plan Mode & Thinking

Opus 4.7 (v2.1.114+): Default effort in Claude Code = xhigh (all plans). New xhigh level sits between high and max — finer reasoning/latency control. Use ultrathink to force max effort for the next turn.

Cost tip: For simple tasks, Alt+T to disable thinking → faster & cheaper.

Per-skill effort — add effort: low to mechanical skills (commit, sync, scaffold) and effort: high to analytical ones (security-audit, architecture-review). Overrides session setting automatically.

OpusPlan workflow: /model opusplan → Shift+Tab × 2 (plan with Opus) → Shift+Tab (execute with Sonnet)

Ultraplan workflow: /ultraplan <task> → terminal free while cloud drafts → review inline in browser → approve → execute on web (PR) or teleport back to terminal

Required for: features >3 files, architecture, complex debugging

Quick Model Selection

Full decision table with cost estimates: Section 2.5 Model Selection & Thinking Guide

Dynamic Model Switching (Mid-Session)

Pattern: Start Sonnet (speed) → swap Opus (complexity) → back Sonnet

Workflow:

# Session start (default Sonnet)
claude

# Complex feature encountered
> "Implement OAuth2 flow with PKCE"
/model opus                    # Switch to deep reasoning

# Feature complete, back to routine
/model sonnet                  # Speed + cost optimization

Best Practices:

• ✅ Swap on task boundaries, not mid-task
• ✅ Use Opus for: architecture decisions, complex debugging, security-critical code
• ✅ Use Sonnet for: routine edits, refactoring, test writing
• ✅ Use Haiku for: simple fixes, typos, validation checks
• ❌ Don’t swap mid-implementation (context loss)

Cost Impact:

Dynamic switching optimizes cost while maintaining quality on complex tasks.

Source: Gur Sannikov embedded engineering workflow

MCP Servers

Serena memory: write_memory() / read_memory() / list_memories()

Serena indexation:

# Initial index
uvx --from git+https://github.com/oraios/serena serena project index

# Force rebuild
serena project index --force-full

# Incremental update (faster)
serena project index --incremental --parallel 4

Check status: /mcp

Creating Custom Components

Agent (.claude/agents/my-agent.md)

---
name: my-agent
description: Use when [trigger]
model: sonnet
tools: Read, Write, Edit, Bash
---
# Instructions here

Command (.claude/commands/my-command.md)

---
description: Brief description
argument-hint: "<required_arg> [--flag]"
---
# Command Name
Instructions for what to do...
$ARGUMENTS[0] $ARGUMENTS[1] (or $0 $1) - user args

Hook (macOS/Linux: .sh | Windows: .ps1)

Bash (macOS/Linux):

#!/bin/bash
INPUT=$(cat)
# Process JSON input
exit 0  # 0=continue, 2=block

PowerShell (Windows):

$input = [Console]::In.ReadToEnd() | ConvertFrom-Json
# Process JSON input
exit 0  # 0=continue, 2=block

Anti-patterns

Quick Prompting Formula

WHAT: [Concrete deliverable]
WHERE: [File paths]
HOW: [Constraints, approach]
VERIFY: [Success criteria]

Example:

Add input validation to the login form.
WHERE: src/components/LoginForm.tsx
HOW: Use Zod schema, show inline errors
VERIFY: Empty email shows error, invalid format shows error

CLI Flags Quick Reference

Full CLI reference (~45 flags): see cli-reference on code.claude.com

Debug Commands

claude --version     # Version
claude update        # Check/install updates
claude doctor        # Diagnostic
claude --debug       # Verbose mode
claude --mcp-debug   # Debug MCPs
/mcp                 # MCP status (inside Claude)

CI/CD Mode (Headless)

# Non-interactive execution
claude -p "analyze this file" src/api.ts

# JSON output
claude -p "review" --output-format json

# Economic model
claude -p "lint" --model haiku

# With auto-accept
claude -p "fix typos" --dangerously-skip-permissions

Remote Control — Mobile Access (v2.1.51+, Research Preview)

Pro/Max only — not available on Team, Enterprise, or API keys

# Start from terminal (new session)
claude remote-control

# Or from inside an active session:
/rc        # (or /remote-control)

Connect from phone/tablet/browser:

1. Scan the QR code (press spacebar after start)
2. Or open session URL in browser / Claude mobile app
3. Or: /mobile → shows App Store + Play Store links

Advanced: tmux multi-session (bypass 1-session limit)

tmux new-session -s dev
# Each pane = its own claude session
# Run /rc in the pane you want to control remotely

Auto-enable: /config → toggle “Remote Control: auto-enable”

Full doc: §9.22 Remote Control | Security notes

Task Management (v2.1.16+)

Two systems available:

Tasks API Commands

# Enable persistence across sessions
export CLAUDE_CODE_TASK_LIST_ID="project-name"
claude

# Inside Claude: Create task hierarchy
> "Create tasks for auth system with dependencies"

# Resume later (new session)
export CLAUDE_CODE_TASK_LIST_ID="project-name"
claude
> "TaskList to see current state"

Key capabilities:

• 📁 Persistent: Survives session end, context compaction
• 🔗 Dependencies: Task A blocks Task B
• 🔄 Multi-session: Broadcast state to multiple terminals
• 📊 Status: pending → in_progress → completed/failed

⚠️ Limitation: TaskList shows id, subject, status, blockedBy only. For description/metadata → use TaskGet(taskId) per task.

Tip: Store key info in subject for quick scanning.

Migration flag (v2.1.19+):

# Revert to old TodoWrite system
CLAUDE_CODE_ENABLE_TASKS=false claude

→ Full workflow: guide/workflows/task-management.md

The Golden Rules

1. Always review diffs before accepting
2. Use /compact before context gets critical (>70%)
3. Be specific in requests (WHAT, WHERE, HOW, VERIFY)
4. Plan Mode first for complex/risky tasks
5. Create CLAUDE.md for every project
6. Commit frequently after each completed task
7. Know what’s sent — prompts, files, MCP results → Anthropic (opt-out training)

Quick Decision Tree

Simple task       → Just ask Claude
Complex task      → Tasks API to plan first
Risky change      → Plan Mode first
Repeating task    → Create agent or command
Context full      → /compact or /clear
Need docs         → Use Context7 MCP
Deep analysis     → Use Opus (thinking on by default)

Common Issues Quick Fix

Health Check Script (save & run):

# macOS/Linux
which claude && claude doctor && claude mcp list

# Windows PowerShell
where.exe claude; claude doctor; claude mcp list

Cost Optimization

Tip: Use --add-dir to allow tool access to directories outside your current working directory

Community Tools

Entire CLI: Agent-native platform by ex-GitHub CEO with rewindable checkpoints, approval gates, audit trails. For compliance (SOC2, HIPAA) or multi-agent workflows.

Search Tools Quick Reference

Quick decision (5 seconds): exact text → rg | exact name → rg/Serena | concept → grepai | structure → ast-grep

Speed: rg (~20ms) → Serena (~100ms) → ast-grep (~200ms) → grepai (~500ms)

Full workflows: workflows/search-tools-mastery.md

Resources

• Official docs: docs.anthropic.com/claude-code
• Advanced guide: Claudelog.com - Tips & patterns
• Full guide: ultimate-guide.md (this repo)
• Whitepapers (FR + EN): florian.bruniaux.com/guides — 9 focused PDFs
• Project memory: Create CLAUDE.md at project root
• DeepSeek (cost-effective): Configure via ANTHROPIC_BASE_URL

Author: Florian BRUNIAUX | @Méthode Aristote | Written with Claude

Last updated: March 2026 | Version 3.39.1