From 70d0cdc2125b1de2a2ee3bf832a76345320b553b Mon Sep 17 00:00:00 2001 From: zebbern <185730623+zebbern@users.noreply.github.com> Date: Tue, 24 Jun 2025 18:39:41 +0200 Subject: [PATCH] Update README.md --- README.md | 278 +++++++++++++++++++++++------------------------------- 1 file changed, 117 insertions(+), 161 deletions(-) diff --git a/README.md b/README.md index 3efe0fb..d20dcfb 100644 --- a/README.md +++ b/README.md @@ -63,8 +63,8 @@ ## Quick Start -
-Essential Commands (Click to expand) + +Essential Commands (Click to expand) ```bash # Interactive Mode @@ -81,7 +81,7 @@ claude update # Update to latest claude mcp # Setup MCP servers ``` -
+ --- @@ -155,8 +155,8 @@ claude mcp # Setup MCP servers ### Output Format Control -
-Format Options + +Format Options | Flag | Options | Description | |------|---------|-------------| @@ -176,14 +176,14 @@ claude -p "analyze" --output-format json claude -p "process" --output-format stream-json ``` -
+ ### Permission & Security Flags > ⚠️ **Warning**: Use security flags with extreme caution! -
-Security Controls + +Security Controls | Flag | Risk Level | Description | |------|------------|-------------| @@ -203,12 +203,12 @@ claude --allowedTools "Edit,View" claude --dangerously-skip-permissions ``` -
+ ### Advanced/Hidden Flags -
-Expert-Level Options + +Expert-Level Options #### System Control @@ -235,14 +235,14 @@ claude --dangerously-skip-permissions | `--allow-tool` | Allow specific tool | `claude --allow-tool Edit` | | `--disallow-tool` | Block specific tool | `claude --disallow-tool Bash` | -
+ ### Experimental Flags > **Under Development**: These flags are proposed/experimental -
-Future Features + +Future Features | Flag | Status | Purpose | |------|--------|----------| @@ -250,18 +250,15 @@ claude --dangerously-skip-permissions | `--no-tools` | **Proposed** | Exclude tool context | | `--no-env` | **Proposed** | Disable environment context | -
+ ### Cloud Provider Integration -
- | Provider | Flag | Service | |----------|------|------| | **Amazon Bedrock** | `--use-bedrock` | AWS | | **Google Vertex AI** | `--use-vertex` | GCP | -
```bash # Use AWS Bedrock @@ -334,8 +331,8 @@ claude config set allowedTools "Edit,View,Bash(git:*)" > **MCP**: Model Context Protocol for extending Claude's capabilities -
-MCP Server Management + +MCP Server Management | Command | Purpose | Example | |---------|---------|----------| @@ -355,7 +352,7 @@ claude mcp add browser "browser-mcp-server" claude mcp add fs "filesystem-mcp-server" ``` -
+ ## Slash Commands @@ -363,10 +360,9 @@ claude mcp add fs "filesystem-mcp-server" ### Core Slash Commands -
-Essential Commands -
+Essential Commands + | Command | Purpose | Quick Tip | |---------|---------|--------| @@ -376,12 +372,9 @@ claude mcp add fs "filesystem-mcp-server" | `/cost` | Token usage stats | Monitor spending | | `/exit` | Exit safely | Clean shutdown | -
-
-
-Management Commands +Management Commands | Command | Purpose | When to Use | |---------|---------|-------------| @@ -391,10 +384,10 @@ claude mcp add fs "filesystem-mcp-server" | `/init` | Create CLAUDE.md | New projects | | `/bug` | Report issues | Found a problem? | -
-
-History & Session Commands + + +History & Session Commands | Command | Purpose | Pro Tip | |---------|---------|----------| @@ -403,21 +396,21 @@ claude mcp add fs "filesystem-mcp-server" | `/login` | Switch accounts | Multi-account | | `/logout` | Sign out | Security | -
-
-Interface Commands + + +Interface Commands | Command | Purpose | For Users Who | |---------|---------|---------------| | `/vim` | Enable Vim keybindings | Love Vim | -
+ ### Advanced Slash Commands -
-Workspace Management + +Workspace Management | Command | Purpose | Example | |---------|---------|----------| @@ -425,10 +418,10 @@ claude mcp add fs "filesystem-mcp-server" | `/memory` | Edit memory files | `/memory` | | `/model ` | Change AI model | `/model claude-opus-4` | -
-
-Integration Commands + + +Integration Commands | Command | Integration | Purpose | |---------|-------------|----------| @@ -438,10 +431,10 @@ claude mcp add fs "filesystem-mcp-server" | `/pr-comments` | GitHub | Get PR comments | | `/review` | GitHub | Review pull requests | -
-
-AI Enhancement Commands + + +AI Enhancement Commands | Command | Purpose | Level | |---------|---------|--------| @@ -449,16 +442,16 @@ claude mcp add fs "filesystem-mcp-server" | `/upgrade` | Access Claude Max | **Premium** | | `/user` | Personal commands | **Custom** | -
-
-Experimental Commands + + +Experimental Commands | Command | Status | Purpose | |---------|--------|----------| | `/terminal-setup` | **Proposed** | Terminal optimizations | -
+ ### Custom Slash Commands @@ -500,16 +493,12 @@ claude mcp add fs "filesystem-mcp-server" ### Core Configuration Variables -
- | Variable | Purpose | Example | Required | |----------|---------|---------|----------| | `ANTHROPIC_API_KEY` | API Authentication | `sk-ant-api03-xxx` | **Yes** | | `ANTHROPIC_MODEL` | Default model | `claude-sonnet-4` | No | | `ANTHROPIC_SMALL_FAST_MODEL` | Quick operations | `claude-haiku-3` | No | -
- **Quick Setup:** ```bash # Essential - Add to your ~/.bashrc or ~/.zshrc @@ -521,8 +510,8 @@ export ANTHROPIC_MODEL="claude-sonnet-4" ### Claude Code Specific Variables -
-Cloud Provider Integration + +Cloud Provider Integration | Variable | Cloud | Purpose | |----------|-------|----------| @@ -531,10 +520,10 @@ export ANTHROPIC_MODEL="claude-sonnet-4" | `CLAUDE_CODE_SKIP_BEDROCK_AUTH` | **AWS** | Skip authentication (gateways) | | `CLAUDE_CODE_SKIP_VERTEX_AUTH` | **GCP** | Skip authentication (gateways) | -
-
-Telemetry & Privacy + + +Telemetry & Privacy | Variable | Purpose | Privacy Impact | |----------|---------|----------------| @@ -547,12 +536,12 @@ export ANTHROPIC_MODEL="claude-sonnet-4" export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 ``` -
+ ### Feature Control Variables -
-Privacy & Security Controls + +Privacy & Security Controls | Variable | Feature | Privacy Level | |----------|---------|---------------| @@ -561,10 +550,10 @@ export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 | `DISABLE_ERROR_REPORTING=1` | Error reports | **High** | | `DISABLE_TELEMETRY=1` | Analytics | **High** | -
-
-Cost & Performance Controls + + +Cost & Performance Controls | Variable | Feature | Cost Impact | |----------|---------|-------------| @@ -572,7 +561,7 @@ export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 | `DISABLE_NON_ESSENTIAL_MODEL_CALLS=1` | Extra AI calls | **Saves Money** | | `DISABLE_PROMPT_CACHING=1` | Caching | **Costs More** | -
+ **Recommended Privacy Setup:** ```bash @@ -587,15 +576,11 @@ export DISABLE_NON_ESSENTIAL_MODEL_CALLS=1 ### Network & Proxy Variables -
- | Variable | Protocol | Example | |----------|----------|----------| | `HTTP_PROXY` | HTTP | `http://proxy.company.com:8080` | | `HTTPS_PROXY` | HTTPS | `https://proxy.company.com:8443` | -
- **Corporate Network Setup:** ```bash # Corporate proxy configuration @@ -605,18 +590,18 @@ export HTTPS_PROXY="https://proxy.company.com:8443" ### Advanced Configuration Variables -
-AI Behavior Tuning + +AI Behavior Tuning | Variable | Purpose | Example | |----------|---------|----------| | `MAX_THINKING_TOKENS` | Thinking budget | `MAX_THINKING_TOKENS=50000` | | `MCP_TIMEOUT` | MCP startup timeout | `MCP_TIMEOUT=10000` | -
-
-Regional Configuration + + +Regional Configuration | Variable | Cloud Provider | Purpose | |----------|---------------|----------| @@ -632,12 +617,12 @@ export AWS_REGION="us-east-1" export CLAUDE_ML_REGION="us-central1" ``` -
+ ### Recent Updates (2025) -
-Version 1.0.25 (Latest) + +Version 1.0.25 (Latest) #### New Features - Fixed slash command reliability issues @@ -650,7 +635,7 @@ export CLAUDE_ML_REGION="us-central1" - **Remote MCP**: Cloud MCP functionality - **Enhanced Auth**: Better MCP authentication -
+ --- @@ -660,8 +645,8 @@ export CLAUDE_ML_REGION="us-central1" ### Tool Permission Patterns -
-Precise Tool Control + +Precise Tool Control #### **Allowlist Patterns** @@ -688,14 +673,14 @@ claude --allowedTools "Edit,View,Bash(npm:*),Bash(git:*)" claude --allowedTools "mcp__puppeteer__puppeteer_navigate,mcp__puppeteer__puppeteer_click" ``` -
+ ## Advanced Usage ### Automation Patterns -
-Headless Automation + +Headless Automation ```bash # JSON output for scripts @@ -708,12 +693,12 @@ claude --resume abc123 --dangerously-skip-permissions claude --verbose --mcp-debug ``` -
+ ### AI Behavior Control -
-Prompt Engineering + +Prompt Engineering ```bash # Custom system prompt @@ -728,12 +713,12 @@ claude "think hard about this" # Enhanced claude "ultrathink about this" # Maximum (128K tokens) ``` -
+ ### Interactive Mode Tricks -
-Keyboard Shortcuts + +Keyboard Shortcuts | Shortcut | Mode | Purpose | |----------|------|----------| @@ -748,12 +733,12 @@ claude "ultrathink about this" # Maximum (128K tokens) 3. Describe task → Claude plans without executing 4. Review plan → Exit planning mode to execute -
+ ### Advanced Configurations -
-Power User Setup + +Power User Setup ```bash # Multi-directory workspace @@ -772,12 +757,12 @@ claude --model claude-sonnet-4-20250514 "analyze codebase" claude "ultrathink about this migration and use tools as needed" ``` -
+ ### Power User Aliases -
-Community Shortcuts + +Community Shortcuts > ⚠️ **Warning**: Use dangerous aliases only in safe environments! @@ -796,22 +781,18 @@ alias clp="claude -p" # Print mode alias cls="claude /status" # Quick status ``` -
+ ## Configuration Files ### Settings Files -
- | File | Scope | Purpose | |------|-------|----------| | `~/.claude.json` | **Global** | User-wide settings | | `.claude/settings.json` | **Project** | Project-specific config | | `~/.config/claude-code/auth.json` | **Auth** | Authentication data | -
- ### Custom Commands @@ -834,29 +815,21 @@ alias cls="claude /status" # Quick status ### MCP Configuration -
- | File | Purpose | |------|----------| | `.claude/mcp.json` | MCP server config | | `~/.claude-code-mcp.env` | MCP environment vars | -
- ## Security ### Dangerous Flags > ⚠️ **EXTREME CAUTION REQUIRED** -
- | Flag | Risk Level | Impact | |------|------------|--------| | `--dangerously-skip-permissions` | **CRITICAL** | Bypasses ALL security checks | -
- **Safe Usage Guidelines:** - **Only use in containerized environments** - **Never use with internet access** @@ -865,8 +838,8 @@ alias cls="claude /status" # Quick status ### Safe Usage Patterns -
-Security Best Practices + +Security Best Practices #### **Always Review First** - Review commands before granting permissions @@ -890,7 +863,7 @@ claude /permissions claude --allowedTools "Edit,View" ``` -
+ ## Output Formats @@ -901,14 +874,14 @@ claude --allowedTools "Edit,View" claude -p "explain this function" --output-format text ``` -
-Example Output + +Example Output ``` This function calculates the factorial of a number recursively... ``` -
+ ### JSON Output @@ -917,8 +890,8 @@ This function calculates the factorial of a number recursively... claude -p "analyze this code" --output-format json ``` -
-Example Output + +Example Output ```json { @@ -931,7 +904,7 @@ claude -p "analyze this code" --output-format json } ``` -
+ ### Streaming JSON Output @@ -940,8 +913,8 @@ claude -p "analyze this code" --output-format json claude -p "process large file" --output-format stream-json ``` -
-Example Output + +Example Output ```json {"type": "start", "timestamp": "2025-06-23T10:00:00Z"} @@ -952,14 +925,14 @@ claude -p "process large file" --output-format stream-json > ⚠️ **Note**: Each line is valid JSON, but concatenated output is not valid JSON -
+ ## Integration Examples ### CI/CD Integration -
-Build Pipeline Examples + +Build Pipeline Examples ```bash # Automated fixing in build scripts @@ -977,12 +950,12 @@ else fi ``` -
+ ### Scripting Integration -
-Automation Scripts + +Automation Scripts ```bash # Log analysis @@ -998,14 +971,12 @@ journal_errors=$(journalctl --since "1 hour ago" --priority=err) echo "$journal_errors" | claude -p "analyze system errors" --output-format json > /tmp/error_analysis.json ``` -
+ ## Troubleshooting ### Health Checks -
- | Command | Purpose | When to Use | |---------|---------|-------------| | `claude --help` | 📚 Show all options | Getting started | @@ -1013,12 +984,9 @@ echo "$journal_errors" | claude -p "analyze system errors" --output-format json | `/status` | 📊 Current config | Check settings | | `claude config list` | 📝 List all settings | Audit configuration | -
- ### Debug Mode -
-Debug Commands +Debug Commands ```bash # Detailed logging @@ -1034,12 +1002,12 @@ claude --mcp-debug claude --verbose --debug --mcp-debug ``` -
+ ### Reset & Recovery -
-Emergency Recovery + +Emergency Recovery ```bash # Reset authentication @@ -1057,14 +1025,12 @@ rm -rf .claude/settings.json claude /doctor ``` -
+ ## Beta Features ### Interactive Mode Controls -
- | Shortcut | Action | Mode | |----------|--------|------| | `Shift+Tab` (1x) | Auto-Accept | Skip confirmations | @@ -1072,14 +1038,12 @@ claude /doctor | `Escape` | Interrupt | Stop Claude anytime | | `Escape` (2x) | History | Edit previous prompts | -
- ### Thinking Budget Control > **Secret**: Special phrases control AI thinking depth -
-Thinking Levels + +Thinking Levels | Phrase | Thinking Budget | Use Case | |--------|----------------|----------| @@ -1102,12 +1066,12 @@ claude "think hard about the security implications" claude "ultrathink about this database migration" ``` -
+ ### Extended Thinking Mode -
-Advanced Thinking Controls + +Advanced Thinking Controls ```bash # Slash command trigger @@ -1117,12 +1081,12 @@ claude "ultrathink about this database migration" --thinking-budget 50000 ``` -
+ ### Permission Prompt Tool Integration -
-Custom Permission Handler + +Custom Permission Handler The `--permission-prompt-tool` expects an MCP tool that returns JSON: @@ -1142,12 +1106,10 @@ The `--permission-prompt-tool` expects an MCP tool that returns JSON: } ``` -
+ ### GitHub Integration Features -
- | Feature | Status | Description | |---------|--------|-------------| | `@claude` mentions | **Beta** | PR/Issue mentions | @@ -1156,12 +1118,10 @@ The `--permission-prompt-tool` expects an MCP tool that returns JSON: | IDE extensions | **Beta** | VS Code & JetBrains | | Inline edits | **Beta** | IDE interface edits | -
- ### Experimental Features -
-Cutting-Edge Capabilities + +Cutting-Edge Capabilities #### **AI Enhancements** - **Extended thinking with tool use**: Claude uses tools during thinking @@ -1176,14 +1136,14 @@ The `--permission-prompt-tool` expects an MCP tool that returns JSON: - **IDE integrations**: VS Code and JetBrains extensions - **Advanced memory system**: Multi-tiered contextual memory -
+ --- ## Important Notes -
-Command Precedence & Behavior + +Command Precedence & Behavior ### **Command Precedence** ``` @@ -1201,14 +1161,12 @@ Query > Session > App Config > Environment Variables > Defaults 8. **Latest Version**: 1.0.25 (June 2025) with improved reliability 9. **Real-time Features**: SSE transport enables real-time MCP communication -
+ --- ## ✅ Research Verification -
- ### **COMPLETE RESEARCH CONDUCTED** | Source | Status | @@ -1223,6 +1181,4 @@ Query > Session > App Config > Environment Variables > Defaults | 2025 Updates | **Latest Changelog Reviewed** | | Source Code Analysis | **Completed (pre-DMCA)** | -
-