Text analysis

Full text analysis — word/sentence stats, keyword extraction, and token count in one pass.

When to use this pack

An agent evaluating text content needs the complete picture: how long is it (words, sentences, paragraphs), what are the key topics (keyword extraction), and how many LLM tokens would it consume? Useful for content pipelines, RAG prep, and prompt budgeting.

Tools in this pack

• Text statistics $0.001 POST /api/text-stats Characters, words, sentences, paragraphs, average word length, reading time, and an LLM token estimate for any text.
• Keyword extraction $0.002 POST /api/keywords Top keywords and two-word phrases by frequency (stopwords removed). Cheap, deterministic signal for routing, tagging, and dedup.
• Token count $0.001 POST /api/token-count Count exact LLM tokens for a string using the real OpenAI BPE (o200k_base for gpt-4o/o-series, cl100k_base for gpt-4/gpt-3.5). Deterministic, offline — budget context windows without calling a model.

Workflow

1. Call text-stats to get word count, sentence count, paragraph count, and reading time.
2. Call keywords to extract the top terms and their frequency.
3. Call token-count to estimate the LLM token consumption (useful for prompt budgeting).

Run it in Claude

claude mcp add agent402 -s user -- npx -y agent402-mcp@latest

Then paste this prompt into Claude:

Analyze this text using Agent402's text-analyze skill pack: 'The x402 protocol enables pay-per-call API payments using USDC stablecoins on Base and other chains.' (1) Text stats, (2) keywords, (3) token count. Report the full analysis.

← All skill packs