The Ultimate Claude Code Tips Collection (Advent of Claude 2025)

Source: Dev.to

Full credit: This article is a summary of Ado’s fantastic Advent of Claude series, where he shared daily Claude Code tips throughout December 2025. Ado is a Developer Relations professional at Anthropic. All tips originate from his Twitter/X posts – I’m simply organizing them into a single reference guide.

Note: Throughout December 2025, Ado (@adocomplete) posted daily Claude Code tips in his Advent of Claude series. This article consolidates all 31 tips into a comprehensive reference guide.

! Prefix – Instant Bash Execution

# Instead of: "Can you run git status?"
!git status

# Or check test results directly:
!npm test

# View logs:
!tail -50 app.log

Why it matters: No model processing, no delay, no wasted tokens. The output goes straight into context.

Rewind with Esc Esc

Esc Esc

You can rewind:

• Just the conversation
• Just the code
• Both

Try experimental approaches freely – an escape hatch is always available.

Enable “Thinking” for API Usage

const response = await client.messages.create({
  model: "claude-sonnet-4-20250514",
  max_tokens: 8000,
  thinking: {
    type: "enabled",
    budget_tokens: 5000
  },
  messages: [{ role: "user", content: "…" }]
});

Claude shows step‑by‑step reasoning in thinking blocks before responding.

claude --continue / --resume – Never Lose Your Work

# Pick up your last conversation instantly
claude --continue

# Choose from past sessions with a picker
claude --resume

Context is preserved, conversation stays intact, and you can keep going where you left off.

# Prefix – Save to Memory

# Always use pnpm instead of npm in this project
# The API endpoint is https://api.example.com/v2
# Run tests with: pytest -v --cov

Claude will ask where to store it (e.g., CLAUDE.md, user settings, etc.). Memory is updated and stays available for future prompts.

/vim – Vim‑Mode for Prompt Composition

/vim

Key bindings

Stop reaching for the mouse.

-p Prefix – Run Claude Code in Scripts, CI/CD, or Automation

# Direct prompt execution
claude -p "Fix the lint errors"

# Pipe input for context
git diff | claude -p "Explain these changes"

# Use in CI/CD
cat error.log | claude -p "Diagnose this error and suggest fixes"

/context – Visualize Token Usage

/context

Displays a breakdown of:

• System prompt size
• MCP server overhead
• Memory files loaded
• Conversation history
• Remaining available space

Pro tip: MCP tools can consume 8‑30 % of the context just by being available. Remove unused ones.

& Prefix – Send to Cloud

# Send a task to run in the cloud
& Refactor the authentication module

# Later, pull it back locally
claude --teleport session_abc123

Work continues locally while Claude works remotely – the best of both worlds.

/stats – Usage Analytics

/stats

Shows an activity graph of your usage. “Orange is the new green.”

Naming Sessions for Easy Retrieval

# Name your current session
/rename api-migration

# Resume by name later
/resume api-migration

Or from the command line:

claude --resume api-migration

Your branches have names; your sessions should too.

Magic Thinking Words

Example

ultrathink - Review this architecture and identify potential scaling issues

More thinking → more thorough analysis for complex problems.

Prompt Stash – Like git stash

Ctrl+S  → Saves your current draft
          → Send something else
          → Draft auto‑restores

No more copying to a scratchpad. No more losing your train of thought.

/statusline – Custom Status Bar

/statusline

Configure via settings to display:

• Git branch and status
• Current model
• Token count
• Custom metrics (weather, Bitcoin price, anything)

Skip Permission Prompts

claude --dangerously-skip-permissions

Auto‑approves all actions. Use with caution – great for trusted, repetitive workflows.

Lifecycle Hooks

/hooks

Or in .claude/settings.json:

{
  "hooks": {
    "PreToolUse": ["./scripts/check-secrets.sh"],
    "PostToolUse": ["./scripts/format-code.sh"],
    "UserPromptSubmit": ["./scripts/validate-prompt.sh"]
  }
}

Use cases

• Block dangerous commands (rm -rf)
• Auto‑format after edits
• Filter sensitive data from prompts
• Send notifications

@ Mentions – Context on Demand

# Add files to context
@src/api/auth.ts
@package.json

# List directory contents
@src/components/

# Manage MCP servers
@mcp-server enable
@my-subagent invoke

Add one or many files instantly, list directories, enable/disable MCP servers, and invoke sub‑agents.

Predictive Follow‑Ups

• Finish a task → a grayed‑out follow‑up suggestion appears.
• Tab → Accept and edit the suggestion.
• Enter → Accept and run immediately.

Just as Tab autocompletes code, it now autocompletes your workflow.

/chrome – Browser Integration

/chrome

Let Claude interact directly with your browser, enabling tasks such as:

• Navigating pages
• Extracting data
• Performing clicks and form fills

(Further details omitted for brevity.)

Claude Code Cheat‑Sheet

Core Capabilities

• Navigate to URLs
• Click buttons & links
• Read console errors
• Inspect the DOM
• Fill forms
• Take screenshots
• “Fix the bug and verify it works” → one prompt

Skills (Folder Structure)

.claude/skills/
├── api-design/
│   ├── SKILL.md
│   └── templates/
├── testing/
│   ├── SKILL.md
│   └── examples/

• Packaged once → usable everywhere.
• Agent skills are now an open standard.

Best practices

• Keep SKILL.md ≤ 500 lines.
• Include concrete examples.
• Use progressive disclosure.
• Test across models.

Plugins & Set‑ups

/plugin install my-setup

Plugins bundle

• Commands
• Agents
• Skills
• Hooks
• MCP configurations

Discover new workflows via the marketplace.

Prompt History Search

Don’t retype – recall with /init (auto‑generate documentation).

Auto‑Generated Onboarding Docs

/init

Creates a CLAUDE.md containing:

• Build commands
• Test instructions
• Key directories
• Project conventions
• Common workflows

Everybody needs onboarding docs – Claude writes them for you.

Export Conversation

/export

• Dumps the entire conversation to Markdown:

  • Every prompt you sent
  • Every response received
  • Every tool call made

• Ideal for documentation, training, or proof of work.

Parallel Sub‑agents

• Each sub‑agent gets:

  • Its own 200 k context window
  • Independent execution
  • Results merged back to the main conversation

• Perfect for:

  • Parallel code exploration
  • Concurrent review operations
  • Multi‑file analysis

Reusable Slash Commands

Create a markdown file in .claude/commands/:

---
description: Review code for best practices
arguments:
  - name: file
    description: File to review
---

Review {{file}} for:
1. Security vulnerabilities
2. Performance issues
3. Code style

Use it with:

/review src/api/auth.ts

Sandbox Mode – Controlled Freedom

/sandbox

• Define boundaries once.
• Claude works freely inside them.
• “YOLO speed” with real security.

Usage Monitoring

/usage

Shows current usage vs. plan limits – avoid surprise caps.

Plan Mode (Read‑Only)

Shift+Tab, Shift+Tab   →   Plan mode

In Plan mode Claude can:

• Read files
• Search code
• Analyze patterns
• Explore the codebase

It will not edit anything.

“Think twice. Execute once.” – Ado

LSP Integration

Claude Code now integrates with the Language Server Protocol:

• Instant diagnostics – errors & warnings as they happen
• Navigation – go to definition, find references, etc.

Claude understands your code like an IDE.

Agent SDK

The same agent loop, tools, and context management that power Claude Code are available as an SDK.

Build agents that work like Claude Code in as little as 10 lines of code.

Feature Timeline

Acknowledgements

Massive thanks to Ado for creating and sharing the Advent of Claude series. These tips have leveled up how developers use Claude Code.

• Follow Ado on X: @adocomplete for the latest tips and updates.

This article is a community summary of Ado’s original Advent of Claude series. All credit for these tips goes to Ado and the Claude Code team at Anthropic.