git changed scope lister

Git diffs often become unmanageable when preparing a pull request or feeding context to an AI agent. This micro-skill surveys your working tree to rank file changes by size, providing line counts and token estimates to help you prioritize your review.

What it does

• Diff surveying identifies all changed, added, or deleted files in the working tree.
• Churn ranking sorts files by total line changes so you can find the largest diffs instantly.
• Token estimation calculates a heuristic token count to help manage LLM context windows.
• Context scoping generates a summary of the total impact of your current changes.

How it works

1. Determine scope using git status and git diff for the working tree, staged files, or specific commit ranges.
2. Collect metrics including file paths, git status codes, and specific line addition/deletion counts.
3. Calculate estimates for token usage based on character churn heuristics.
4. Format output into a ranked table showing the most significant changes at the top.

Frameworks & tools

This skill works with any Git repository and is compatible with CLAUDE_CODE, CURSOR, WINDSURF, and standard CLI environments.

Why this beats prompting it yourself

Writing a manual prompt to parse numstat often results in hallucinated line counts or poor sorting. This skill uses a logic-heavy procedure to ensure the math is consistent and the output is formatted for immediate technical decision-making.

Use cases

• Review prioritization to identify which complex files need a human eye before committing.
• Context management to see if a diff is too large to feed into an agent's context window.
• Pre-commit sanity checks to ensure no massive debug logs or unintended files were modified.

Known limitations

The token count is a heuristic estimate based on character churn and not a literal count from a specific model tokenizer.