Agent Token Saver: Trim Context, Ignore Junk, Digest Logs

    1

    Scripts that make coding agents spend fewer tokens: audit CLAUDE.md/AGENTS.md/rules bloat, suggest ignore entries, and compress huge logs to just the errors.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    About this skill

    Three offline commands plus a concise-output mode. audit flags duplicate rules, pasted code blocks and filler in always-loaded context files. map shows where tokens live in the repo and which lockfiles, build output and media to ignore. log collapses thousands of repeated lines into errors-first summaries with line numbers. It reports before/after estimates. A free, script-backed option in a category of mostly paid, prompt-only listings.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    • Free with an Agensi account

    Requires

    Node 18+
    Node.js

    Permissions

    Terminal / Shell
    Read Files
    Listed23 days ago

    What's inside

    Frequently Asked Questions

    Any coding agent that loads context files or reads logs, such as Claude Code, Cursor and Codex.

    It reports findings and before/after token estimates so you or your agent can decide what to change.

    No. It runs offline with no keys.

    New in Productivity

    Free