docs: update documentation to reflect simplified CLI usage

- Show help instead of usage when no args provided
- Update all README examples to show implicit encoding
- Document automatic streaming detection
- Add CLI usage section to main README
- Emphasize the intuitive default behaviors

The documentation now reflects the simplified interface:
  tokenizer llama3 "text"        # encodes
  echo "text" | tokenizer llama3 # streams
  tokenizer llama3              # shows help

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: jackspirou

README.md

@@ -56,14 +56,17 @@ make install
 Quick usage:
 
 ```bash
-# Encode text
-tokenizer llama3 encode "Hello, world!"
+# Encode text (implicit - recommended)
+tokenizer llama3 "Hello, world!"
 
 # Decode tokens
 tokenizer llama3 decode 128000 9906 11 1917 0 128001
 
-# Stream large files
-cat document.txt | tokenizer llama3 stream
+# Stream large files (automatic pipe detection)
+cat document.txt | tokenizer llama3
+
+# Get tokenizer information
+tokenizer llama3 info
 ```
 
 See [cmd/tokenizer/README.md](cmd/tokenizer/README.md) for full CLI documentation.
@@ -90,6 +93,29 @@ go get github.com/agentstation/tokenizer/llama3
 
 ## Quick Start
 
+### CLI Usage
+
+```bash
+# Install via Homebrew
+brew install agentstation/tap/tokenizer
+
+# Encode text (simple, intuitive)
+tokenizer llama3 "Hello, world!"
+# Output: 128000 9906 11 1917 0 128001
+
+# Decode tokens
+tokenizer llama3 decode 128000 9906 11 1917 0 128001
+# Output: <|begin_of_text|>Hello, world!<|end_of_text|>
+
+# Stream from files (automatic)
+cat document.txt | tokenizer llama3
+
+# Get help
+tokenizer llama3 help
+```
+
+### Library Usage
+
 ```go
 package main
 

cmd/tokenizer/README.md

@@ -21,7 +21,11 @@ The tokenizer CLI uses a subcommand structure where each tokenizer implementatio
 ### Basic Commands
 
 ```bash
-# Encode text to token IDs
+# Encode text to token IDs (implicit - default action)
+tokenizer llama3 "Hello, world!"
+# Output: 128000 9906 11 1917 0 128001
+
+# Encode text to token IDs (explicit)
 tokenizer llama3 encode "Hello, world!"
 # Output: 128000 9906 11 1917 0 128001
 
@@ -31,6 +35,10 @@ tokenizer llama3 decode 128000 9906 11 1917 0 128001
 
 # Get tokenizer information
 tokenizer llama3 info
+
+# Show help
+tokenizer llama3 help
+# Or just: tokenizer llama3
 ```
 
 ### Encoding Options
@@ -57,16 +65,23 @@ tokenizer llama3 encode -o newline "Hello, world!"
 ### Piping and Streaming
 
 ```bash
-# Pipe text to encode
+# Pipe text to encode (automatic streaming)
+echo "Hello, world!" | tokenizer llama3
+# Output: 128000 9906 11 1917 0 128001
+
+# Pipe text to encode (explicit)
 echo "Hello, world!" | tokenizer llama3 encode
 
 # Pipe tokens to decode
 echo "128000 9906 11 1917 0 128001" | tokenizer llama3 decode
 
 # Round-trip encoding and decoding
-tokenizer llama3 encode "test" | tokenizer llama3 decode
+tokenizer llama3 "test" | tokenizer llama3 decode
+
+# Stream large files (automatic)
+cat large_file.txt | tokenizer llama3
 
-# Stream large files
+# Stream large files (explicit)
 cat large_file.txt | tokenizer llama3 stream
 ```
 
@@ -75,10 +90,11 @@ cat large_file.txt | tokenizer llama3 stream
 For processing large files or real-time input:
 
 ```bash
-# Basic streaming
-tokenizer llama3 stream < input.txt
+# Automatic streaming (detects piped input)
+tokenizer llama3 < input.txt
+cat large_file.txt | tokenizer llama3
 
-# Custom buffer settings
+# Explicit streaming with options
 tokenizer llama3 stream --buffer-size=8192 --max-buffer=2097152 < large_file.txt
 
 # Stream without special tokens

llama3/cmd/llama3/command.go

@@ -74,8 +74,8 @@ Available commands:
 				return streamCmd.Execute()
 			}
 
-			// No args and no piped input, show usage
-			return cmd.Usage()
+			// No args and no piped input, show help
+			return cmd.Help()
 		},
 	}