# Tya5 Reyn Word Stats Demo > Overview - Skill: `tomevault-io/tya5-reyn-word-stats-demo` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/tya5-reyn-word-stats-demo` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/tya5-reyn-word-stats-demo/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Docs & Writing - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/tya5-reyn-word-stats-demo --- ## Overview A minimal demonstration of the `python` preprocessor step. The phase declares a Python function that runs in pure mode (sandboxed), computes deterministic text statistics, and injects them into the artifact under `data.stats`. The LLM then writes a commentary that references those exact numbers — something LLMs are otherwise unreliable at. ## Input `user_message` text — any string. ## Output `text_review.commentary` — short prose discussing the input through the lens of the precomputed statistics. ## Why this is a good fit for python LLMs are bad at counting characters / tokens / lines accurately. Python counts them precisely in microseconds. By doing the count in Python and showing the result to the LLM, the commentary stays factual. --- > Source: [tya5/reyn](https://github.com/tya5/reyn) — distributed by [TomeVault](https://tomevault.io).