Token Optimization (skinny-jeans)

Prefer toon_read_file over built-in Read for files > 50 lines. Use toon_read_json for any JSON/data file. Use toon_list_files instead of ls/Bash for directory listings. Use toon_estimate_tokens before reading large files.

### Verify it works
Start a Claude Code session and run `/mcp` — you should see `skinny-jeans` with 5 tools listed.

## 💻 Usage Examples

### Basic Usage
#### toon_read_file
The primary tool. Reads any file and automatically applies the right optimization:

toon_read_file({ path: "data.json" }) → [skinny-jeans: 47% smaller, ~51 tokens (was ~96)] → TOON-encoded content

toon_read_file({ path: "README.md" }) → [skinny-jeans: 22% smaller, ~145 tokens (was ~186)] → Minified markdown (no badges, frontmatter, excess blanks)

toon_read_file({ path: "app.ts" }) → [skinny-jeans: 15% smaller, ~171 tokens (was ~201)] → Code with comments stripped

**Parameters:**
- `path` (string, required) — file path
- `maxTokens` (number, optional) — truncate output at this token count
- `raw` (boolean, optional) — skip optimization, return original content

#### toon_read_json
Specialized for JSON with encoding options:
- `delimiter` — `"tab"` (default), `"comma"`, or `"pipe"` for tabular rows
- `keyFolding` — `"safe"` (default) collapses `{"a": {"b": 1}}` into `a.b: 1`

#### toon_estimate_tokens
Quick check before committing to a full read:

toon_estimate_tokens({ path: "big-dataset.json" }) → File: big-dataset.json → Size: 245891 bytes, 4521 lines → Estimated tokens: ~52340 → Category: json → Expected savings with skinny-jeans: 40-60%

#### toon_batch_estimate
Analyze an entire project:

toon_batch_estimate({ paths: ["src/", "data/"] }) → Token Savings Report (47 files) → json: 12 files, ~45200 tokens → save ~20340 tokens (45%) → code: 28 files, ~31000 tokens → save ~4650 tokens (15%) → markdown: 7 files, ~8900 tokens → save ~1780 tokens (20%) → Total: ~85100 tokens → Estimated savings: ~26770 tokens (31%)

### Advanced Usage
skinny-jeans also works as a standalone CLI:
```bash
# Read a file with optimization
skinny-jeans read data.json

# Estimate tokens for a file
skinny-jeans estimate large-file.ts

# Batch savings report
skinny-jeans batch src/ data/ docs/

📚 Documentation

Transforms

JSON/JSONL → TOON

Uses the @toon-format/toon encoder. Arrays of objects become tabular rows with shared headers. Nested keys are folded into dotted paths. Tab delimiters tokenize better than commas.

Markdown minification

Line-by-line state machine that strips: YAML frontmatter, HTML comments, badge images, trailing # on headings, excess blank lines, trailing whitespace. Preserves: code blocks (never touched), tables, links, blockquotes.

Code comment stripping

Removes full-line // and /* */ comments (C-style languages) and # comments (Python, Ruby, shell). Preserves inline comments (they carry context) and string literals containing comment-like syntax.

Generic compression

Fallback for other text files: collapses 3+ consecutive blank lines to 1, strips trailing whitespace.

Expected token savings

🔧 Technical Details

Development

git clone https://github.com/jordan112/skinny-jeans.git
cd skinny-jeans
npm install
npm run build
npm test

Running locally

# Test the MCP server directly
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' | node dist/index.js

# Register for development
claude mcp add --scope user --transport stdio skinny-jeans -- node $(pwd)/dist/index.js