Stats
Actions
Tags
From token-calculator
Estimate token consumption of files before uploading to Claude. Use when the user wants to know how much context a file will consume, whether a file fits in the context window, or needs to plan which files to include in a conversation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/token-calculator:file-analysisThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Help users understand how much context window their files will consume.
Help users understand how much context window their files will consume.
| File type | Estimation method |
|---|---|
| Plain text (.txt, .md) | Characters / 4 (English) or / 3 (Spanish) |
| ~1500 tokens per page (text-heavy), ~800 per page (sparse) | |
| Images (PNG, JPG) | ~1600 tokens per image (fixed overhead for vision) |
| Code files | Characters / 3.5 |
| CSV/spreadsheet | Characters / 3 (includes structural overhead) |
| DOCX | Similar to plain text after extraction |
When users have multiple files:
For each file:
Summary:
npx claudepluginhub novanoticia/token-calculator-suite --plugin token-calculatorSummarizes files by reading content, extracting key passages, and applying size-based strategies with type-specific handling for code, config, data, docs, markup, binaries.
Converts heavy document formats (PDF, Word, Excel, PowerPoint, and others) to token-efficient Markdown/CSV with structurally-aware digest compression. Use when Claude needs to read documents without excessive context budget.
Evaluates .claude/ directory token efficiency by scanning files, estimating tokens, categorizing load types, detecting issues like long CLAUDE.md or duplicates, and generating scored report.