Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    git changed scope lister

    1

    Rank changed git files by line churn and estimated token size to scope reviews and agent context.

    Free

    2 usesSecurity scanned
    git changed scope lister

    git changed scope lister

    Example session with this skill installed

    list changed files and show the biggest diffs first

    • Read your context and instructions
    • Compiled the git changed scope
    • Generated the document

    I have surveyed the working tree and ranked the changes by line churn. Here is the scope of your current diff, including token estimates for LLM context planning.

    Git Change Scope

    #pathstatus+add-del~tokens
    1services/auth_provider.tsM245181,052
    2components/Login/LoginForm.tsxM8245508
    3styles/globals.cssM605260
    4package.jsonM12256
    5src/utils/logger.tsD0832

    Scope: 5 files, 475 changed lines (~1.9k tokens est.)

    Top Files to Review

    1. services/auth_provider.ts: Major logic changes (245 lines added). High risk.
    2. components/Login/LoginForm.tsx: Significant churn in UI logic and validation.
    3. styles/globals.css: Moderate style additions.

    Next steps

    • Review the logic in services/auth_provider.ts for security edge cases.
    • Run git add on the verified components to narrow the next scope check.
    • Use a lean-context tool to feed the top 2 files to the agent for a detailed audit.

    LoginForm.tsx

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    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.

    Token estimate is a heuristic, not a literal tokenizer count. Requires a local Git repository.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Git

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill helps you avoid 'context overflow' by ranking changed files by line churn and token size, allowing you to selectively feed only the most relevant diffs to your AI agent rather than overwhelming it with a massive, unorganized diff.

    Yes, while optimized for standard CLI environments, it is fully compatible with agentic editors like Claude Code, Cursor, and Windsurf, enabling these tools to better self-regulate the data they ingest from your repository.

    The token count is calculated using a high-fidelity character-based heuristic designed to approximate standard LLM tokenizers, giving you a reliable 'safety margin' for context management.

    No complex setup is required; as long as you have Git installed and are within a repository, the skill can immediately survey your staged changes, working tree, or specific commit ranges.

    Unlike a basic prompt that might misinterpret raw 'git diff' output, this skill uses a structured logic procedure to parse file metrics, ensuring that line counts and rankings are mathematically precise every time.