Claude Code Ultimate Guide: Full Content for AI Indexing

This file is optimized for AI/LLM consumption. It contains the condensed guide overview,

full cheatsheet, complete template list, and FAQ for Claude Code.

> Standard llms.txt: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/llms.txt

Machine-readable index: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/machine-readable/reference.yaml

Metadata Copy Chapter

- Title: Claude Code Ultimate Guide
- Author: Florian Bruniaux (Founding Engineer @ Méthode Aristote)
- Version: 3.41.1
- Last Updated: July 30, 2026
- License: CC BY-SA 4.0
- Repository: https://github.com/FlorianBruniaux/claude-code-ultimate-guide
- Landing: https://cc.bruniaux.com
- Lines of Documentation: 26,695
- Production Templates: 268
- Quiz Questions: 473
- Whitepapers: 13 titles (FR + EN)

---

What Is Claude Code Copy Chapter

Claude Code is Anthropic's official CLI for AI-assisted development. It lets developers interact with Claude directly from the terminal to write, edit, debug, and review code. Unlike IDE plugins, it has full filesystem access, can run shell commands, and works autonomously on multi-step tasks.

This guide is the most comprehensive community resource for Claude Code. It covers everything from installation to production security, with 268 ready-to-use templates for agents, hooks, commands, and skills.

Who This Guide Is For Copy Chapter

- Beginners: Install Claude Code, complete first task in 15 minutes
- Intermediate: Configure CLAUDE.md memory files, custom agents, hooks
- Power users: MCP servers, Trinity pattern, CI/CD integration, multi-agent workflows
- Tech leads: Team adoption, security hardening, governance patterns
- CTOs/CIOs: ROI, risk, security posture

Guide Structure (11 Sections + Architecture) Copy Chapter

Architecture Deep Dive (guide/core/architecture.md):
- Master Loop: while(tool_call), no DAGs, no classifiers, no RAG
- 8 Core Tools: Bash, Read, Edit, Write, Grep, Glob, Task, TodoWrite
- Context: ~200K tokens, auto-compact at 75-92%
- Sub-agents: isolated context, max depth=1
- Philosophy: "less scaffolding, more model"

Main Guide Sections (guide/ultimate-guide.md, 26,695 lines):
1. Quick Start: Installation, first workflow, essential commands
2. Core Concepts: Context management, Plan Mode, Rewind, Mental Model
3. Memory & Settings: CLAUDE.md files, .claude/ folder, precedence rules
4. Agents: Custom AI personas, Tool SEO, orchestration patterns
5. Skills: Reusable knowledge modules (Skills 2.0: Capability Uplift + Encoded Preference, Evals)
6. Commands: Custom slash commands, variable interpolation
7. Hooks: Event-driven automation (PreToolUse, PostToolUse, UserPromptSubmit)
8. MCP Servers: Serena, Context7, Sequential, Playwright, Postgres, grepai
9. Advanced Patterns: Trinity, CI/CD, Tasks API, multi-agent teams, feedback loops
10. Reference: Commands, shortcuts, troubleshooting, checklists
11. AI Ecosystem: Complementary tools matrix, practical multi-tool workflows, integration patterns

Security & Sandboxing (guide/security/sandbox-native.md, guide/core/settings-reference.md):
- Two independent layers: filesystem (write CWD + session temp, read the whole machine) and network (no domain pre-allowed, proxy does not terminate TLS)
- The default read policy covers ~/.ssh and ~/.aws and there is no built-in denylist; sandbox.credentials.files and credentials.envVars are what actually protect them
- excludedCommands bare-name form never matches, use the glob form; a matching glob unsandboxes the entire Bash invocation including earlier commands (anthropics/claude-code#10524, #81157)
- Git over SSH needs an exception: the proxy handles HTTP/HTTPS but not port 22 and blocks the ssh-agent socket
- No curl/wget blocklist exists; a missing domain hangs to timeout rather than erroring
- Writes to Claude Code's own settings.json are denied at every scope, so a sandboxed script cannot widen its own policy

---

Full Cheatsheet Copy Chapter

Version: 3.41.1 | Last Updated: July 2026

---

Essential Commands Copy Section

Source of truth for the complete set: https://code.claude.com/docs/en/commands (~100 built-in commands). The subset below is the high-frequency one.

| Command | Action |
|---------|--------|
| /help | Contextual help |
| /clear | Reset conversation |
| /compact | Free up context |
| /status | Session state + context usage |
| /context | Detailed token breakdown |
| /plan | Enter Plan Mode (no changes). Exit by approving the plan or Shift+Tab |
| /model | Switch model (sonnet/opus/opusplan) |
| /insights | Usage analytics + optimization report |
| /code-review [level] | Review the diff for correctness bugs; --fix applies them, ultra runs it in the cloud |
| /simplify | Detect over-engineering in changed code + auto-fix |
| /security-review | Scan the branch diff for injection, auth, and data-exposure risks |
| /batch | Large-scale refactors via 5–30 parallel worktree agents |
| /subtask <task> | Hand a side task to a forked subagent that reports back here (v2.1.212+) |
| /teleport | Teleport session from web |
| /tasks | Monitor background tasks |
| /remote-env | Configure cloud environment |
| /remote-control | Start remote control session (Research Preview, Pro/Max) |
| /rc | Alias for /remote-control |
| /mobile | Get Claude mobile app download links |
| /fast | Toggle fast mode (2.5x speed, 6x cost) |
| /voice | Toggle voice dictation (hold Space to speak, release to send) |
| /loop [interval] [prompt] | Run a prompt on repeat (ex: /loop 5m check the deploy, default 10m) |
| /usage | Token + cost usage per model, plan limits (v2.1.118, replaces /cost and /stats) |
| /cost | Alias for /usage (v2.1.118+) |
| /stats | Alias for /usage, opens on the Stats tab (v2.1.118+) |
| /recap | Summarize the current session (v2.1.108) |
| /effort | Set effort level: low/medium/high/xhigh/max/ultracode (v2.1.111) |
| /tui [fullscreen] | Set the terminal renderer and relaunch into it (v2.1.110) |
| /focus | Toggle minimal focus view (v2.1.110) |
| /fewer-permission-prompts | Scan transcripts, propose a read-only tool allowlist (shipped as /less-permission-prompts in v2.1.111) |
| /ultrareview | Multi-agent cloud code review, now an alias of /code-review ultra (v2.1.114) |
| /proactive | Alias for /loop |
| /undo | Alias for /rewind |
| /rename [name] | Name or rename the current session |
| /copy | Interactive picker to copy a code block or full response |
| /doctor | Full setup checkup: install, settings, hooks, CLAUDE.md bloat (v2.1.205+) |
| /debug | Systematic troubleshooting |
| /exit | Quit (or Ctrl+D) |

---

Keyboard Shortcuts Copy Section

| Shortcut | Action |
|----------|--------|
| Shift+Tab | Cycle permission modes |
| Esc × 2 | Rewind (undo) |
| Ctrl+C | Interrupt |
| Ctrl+R | Search command history |
| Ctrl+L | Clear screen (keeps context) |
| Tab | Autocomplete |
| Shift+Enter | New line |
| Ctrl+B | Background tasks |
| Ctrl+F | Kill all background agents (double press) |
| Alt+T | Toggle thinking |
| Space (hold) | Voice input (requires /voice enabled) |
| Ctrl+D | Exit |

---

File References Copy Section

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

---

Permission Modes Copy Section

| Mode | Editing | Execution |
|------|---------|-----------|
| Default | Asks | Asks |
| acceptEdits | Auto | Asks |
| Plan Mode | None | None |
| dontAsk | Only if in allow rules | Only if in allow rules |
| bypassPermissions | Auto | Auto (CI/CD only) |

Shift+Tab to cycle modes

---

Memory & Settings Copy Section

| Level | macOS/Linux | Scope |
|-------|-------------|-------|
| Project | .claude/ | Team (committed) |
| Personal | ~/.claude/ | You (all projects) |

.claude/ Folder Structure:

.claude/
├── CLAUDE.md           # Team memory (instructions)
├── settings.json       # Hooks (committed)
├── settings.local.json # Permissions (not committed)
├── agents/             # Custom agents
├── skills/             # User-invocable skills (slash commands + knowledge modules)
│                       # Since CC 2.1.3: commands/ merged here
│                       # Add disable-model-invocation: true for user-only skills
├── hooks/              # Event scripts
└── rules/              # Auto-loaded rules

---

Context Management (CRITICAL) Copy Section

| Context % | Status | Action |
|-----------|--------|--------|
| 0-50% | Green | Work freely |
| 50-70% | Yellow | Be selective |
| 70-90% | Orange | /compact now |
| 90%+ | Red | /clear required |

Actions by Symptom:
| Sign | Action |
|------|--------|
| Short responses | /compact |
| Frequent forgetting | /clear |
| >70% context | /compact |
| Task complete | /clear |

---

Plan Mode & Thinking Copy Section

| Feature | Activation | Usage |
|---------|------------|-------|
| Plan Mode | Shift+Tab × 2 or /plan | Explore without modifying |
| OpusPlan | /model opusplan | Opus for planning, Sonnet for execution |

| Task | Model | Effort |
|------|-------|--------|
| Rename, boilerplate, test gen | Haiku | low |
| Feature dev, debug, refactor | Sonnet | medium–high |
| Architecture, security audit | Opus | high–max |

---

MCP Servers Copy Section

| Server | Purpose |
|--------|---------|
| Serena | Indexation + session memory + symbol search |
| grepai | Semantic search + call graph analysis |
| Context7 | Library documentation |
| Sequential | Structured reasoning |
| Playwright | Browser automation |
| Postgres | Database queries |

---

Creating Custom Components Copy Section

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

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

Skill / Command (.claude/skills/my-skill.md, since CC 2.1.3):

---
name: my-skill
disable-model-invocation: true  # user-only skill (replaces .claude/commands/)
---

Skill Name

Instructions for what to do...
$ARGUMENTS[0] $ARGUMENTS[1], user args

Hook (.claude/hooks/ bash or PowerShell):

#!/bin/bash
INPUT=$(cat)
Process JSON input

exit 0  # 0=continue, 2=block

---

Quick Prompting Formula Copy Section

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 Copy Section

| Flag | Usage |
|------|-------|
| -p "query" | Non-interactive mode (CI/CD) |
| -c / --continue | Continue last session |
| -r / --resume <id> | Resume specific session |
| --model sonnet | Change model |
| --add-dir ../lib | Allow access outside CWD |
| --permission-mode plan | Plan mode |
| --tools "Tool1,Tool2" | Enable specific tools for session |
| --max-budget-usd 5.00 | Max API spend limit |
| --system-prompt "..." | Append custom system prompt |
| --worktree / -w | Run in isolated git worktree |
| --dangerously-skip-permissions | Auto-accept (use carefully) |
| --debug | Debug output |

---

The Golden Rules Copy Section

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 available)

---

Quick Decision Tree Copy Section

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)

---

Cost Optimization Copy Section

| Model | Use For | Cost |
|-------|---------|------|
| Haiku | Simple fixes, reviews | $ |
| Sonnet | Most development | $$ |
| Opus | Architecture, complex bugs | $$$ |
| OpusPlan | Plan (Opus) + Execute (Sonnet) | $$ |

---

Template Library (268 templates) Copy Chapter

Agents (21 files) Copy Section

Commands (legacy, pre-CC 2.1.3) Copy Section

Hooks (bash + PowerShell) Copy Section

PowerShell hooks (2 files in examples/hooks/powershell/, Windows equivalents for a subset, not a 1:1 mirror of the bash list):
- auto-format.ps1, security-check.ps1

Skills (64 modules) Copy Section

Scripts (15 utility scripts) Copy Section

Additional Categories Copy Section

---

FAQ Copy Chapter

Q: What is the Claude Code Ultimate Guide?
A: The most comprehensive community guide for Claude Code (Anthropic's CLI). 26,695 lines of documentation, 268 production-ready templates, 473-question quiz, and security threat database. Free and open-source (CC BY-SA 4.0).

Q: Is this guide free?
A: Yes, completely free. The guide is CC BY-SA 4.0 (share and adapt with attribution). Templates are CC0 (copy-paste freely, no attribution needed). No paywall, no login required.

Q: What's the difference between this and Anthropic's official docs?
A: This guide goes 10x deeper on practical workflows, templates, security hardening, and real-world patterns. The official docs explain what Claude Code does; this guide teaches you how to use it effectively for production work.

Q: Do I need a paid Claude plan to use Claude Code?
A: Claude Code requires an active Claude subscription. Pro ($20/month) is sufficient for most individual developers. Team and Enterprise plans available for organizations.

Q: What are Hooks in Claude Code?
A: Hooks are shell scripts (bash or PowerShell) that run automatically before/after Claude tool calls. They enable event-driven automation: block dangerous commands, scan for secrets, auto-format code, run tests after edits, log activity for compliance. They use exit 0 (continue) or exit 2 (block) to control Claude's actions.

Q: What are MCP servers?
A: Model Context Protocol servers extend Claude's capabilities beyond its built-in tools. Examples: Serena (codebase indexation + session memory), Context7 (library documentation), Sequential (structured multi-step reasoning), Playwright (browser automation), Postgres (database queries). The community has built 1,000+ MCP servers; this guide teaches you to vet them for security.

Q: What is Plan Mode?
A: Plan Mode (Shift+Tab × 2 or /plan) is a read-only exploration mode where Claude can analyze your codebase without making any changes. Use it before complex or risky tasks to let Claude research the problem, then switch to execution mode.

Q: What are Agents in Claude Code?
A: Agents are custom Claude instances with specific instructions, tools, and personas stored in .claude/agents/ as markdown files. Examples: a security-auditor that only uses Read/Grep tools, a code-reviewer with specific standards, a devops-sre with infrastructure expertise. They're invoked via @agent-name in your prompt.

Q: What is CLAUDE.md?
A: CLAUDE.md is a memory file at your project root (or ~/.claude/) that Claude reads at the start of every session. Use it to define project conventions, tech stack, coding standards, and commands. It's the primary way to give Claude persistent project context without repeating yourself.

Q: What are Skills?
A: Skills are reusable knowledge modules stored in .claude/skills/. Two types: Capability Uplift (fills model gaps, becomes less necessary as models improve) and Encoded Preference (encodes your team's specific workflow preferences, stays durable). Skills 2.0 (March 2026) adds Benchmark Mode, A/B testing, and Trigger Tuning.

Q: How do I handle context limits?
A: Monitor context usage via /status. At 70%: run /compact to summarize and free context. At 90%: use /clear for a fresh start. Use Plan Mode early to explore without consuming context. For long projects, use Tasks API (CLAUDE_CODE_TASK_LIST_ID) for cross-session persistence.

Q: Is Claude Code safe for production use?
A: With proper hardening, yes. Key steps: never use bypassPermissions in production, vet all MCP servers against the threat database (28+ CVEs tracked), use hooks to block dangerous commands, enable audit logging, run claude doctor regularly. See guide/security/security-hardening.md for the complete checklist.

---

Privacy & Data Copy Chapter

Claude Code sends to Anthropic servers: your prompts, file contents you reference, MCP tool results.
- Default retention: 5 years (training enabled)
- Opt-out: 30 days retention, https://claude.ai/settings/data-privacy-controls
- Enterprise: 0 retention, no training
- The guide covers this in detail: guide/security/data-privacy.md

---

Repository Copy Chapter

claude-code-ultimate-guide/
├── llms.txt                        # This file (short version, for AI indexing)
├── llms-full.txt                   # Full content (you are here)
├── guide/                          # Core documentation
│   ├── ultimate-guide.md           # Complete guide (26,695 lines)
│   ├── cheatsheet.md               # 1-page reference
│   ├── core/architecture.md        # How Claude Code works internally
│   ├── security/security-hardening.md  # Security best practices
│   ├── security/data-privacy.md    # What data is sent to Anthropic
│   └── core/claude-code-releases.md    # Official release tracking
├── examples/                       # 268 production-ready templates
│   ├── agents/                     # Custom AI personas
│   ├── commands/                   # Legacy slash commands (pre-CC 2.1.3)
│   ├── hooks/                      # Event automation (bash + PowerShell)
│   ├── skills/                     # User-invocable skills (unified since CC 2.1.3)
│   └── scripts/                    # Utility scripts
├── machine-readable/               # LLM/AI consumption
│   ├── reference.yaml              # Machine-optimized index (~2K tokens)
│   └── llms.txt                    # Short version
├── whitepapers/                    # 13 focused PDFs (FR + EN)
└── quiz/                           # 473-question interactive quiz

---

Author & License Copy Chapter

Author: Florian Bruniaux, Founding Engineer @ Méthode Aristote
GitHub: https://github.com/FlorianBruniaux
License: Guide = CC BY-SA 4.0 | Templates = CC0 1.0