Token Saver (English) — Cut Your AI Context Cost

    2

    Audit and reduce token consumption by slimming standing instructions and throttling runtime file reads.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Token Saver (English) — Cut Your AI Context Cost

    Example session with this skill installed

    My CLAUDE.md is getting huge and the agent is starting to ignore my project rules. Can you audit the standing context and suggest how to slim it down?

    • Read your context and instructions
    • Compiled the token saver english

    I have audited your project instructions using the token_meter.py script against the Claude Code guidance.

    Standing-context audit

    Current harness: Claude Code
    Budget: 200 lines (Guideline)

    FileBytesEst. TokensCurrent LinesRisk
    CLAUDE.md8,4202,105245High (Truncation)
    AGENTS.local.md1,20030035Normal

    Expected after slimming: 8,420 -> 3,150 bytes (estimated)

    Edit proposals awaiting confirmation

    1. CLAUDE.md lines 110-165: Move the "Legacy API Documentation" section to a new file docs/legacy_api.md.

      • Expected saving: 2,800 bytes / 55 lines.
      • Reason: This content is rarely accessed and crowds out active coding rules.
    2. CLAUDE.md lines 12-40: Consolidate redundant style rules.

      • Current: 5 separate bullets for indentation and spacing.
      • Suggested: "Follow Prettier config; use 2-space indents, no semicolons."
      • Expected saving: 450 bytes.
    3. CLAUDE.md lines 180-210: Move troubleshooting tables to references/errors.md.

      • Expected saving: 2,020 bytes / 30 lines.

    Next steps

    • Provide a yes to apply the migration of legacy docs to docs/legacy_api.md.
    • Confirm if I should proceed with the phrasing compression for style rules.
    • Run python3 scripts/token_meter.py doctor to ensure measurement precision.
    CLAUDE.md

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

    About this skill

    The problem

    Large project instruction files like CLAUDE.md or AGENTS.md grow until they hit context limits or crowd out working memory. Coding agents often waste tokens by reading entire files when only a small range is needed.

    What it does

    • Audits standing context files against specific harness budgets for Codex, DeepSeek, and Claude Code.
    • Generates diff proposals to slim down instructions by removing duplication and moving details to reference files.
    • Throttles runtime token usage by using Grep to locate specific lines before reading large files.
    • Intercepts large command outputs by redirecting to disk and slicing results instead of flooding the chat.
    • Provides a Python-based token meter to accurately measure usage or provide weighted estimates when tokenizers are unavailable.

    Frameworks & tools

    Works with Claude Code, DeepSeek Harness, Codex, and WorkBuddy. Uses Python 3.10 standard library, tiktoken for precision, and shell utilities like grep, sed, and jq.

    Why this beats prompting it yourself

    Standard agents naturally default to reading full files and dumping long logs, which rapidly exhausts context windows. This skill enforces a "slice-first" strategy and budget-aware auditing that prevents silent truncation of critical instructions.

    Use cases

    • Compressing a bloated CLAUDE.md that has exceeded the 200-line recommended limit.
    • Reducing API costs by preventing the agent from re-reading files already in the session.
    • Auditing project instructions to see which files are at risk of being ignored by the harness.
    • Managing long-running test suites by capturing logs to disk and only surfacing error traces.

    Known limitations

    Never modifies session history or instruction files directly. Edits require human confirmation. Measurement accuracy drops for CJK characters if tiktoken is not installed.

    Requires manual confirmation for all file edits. Measurement is an estimate if tiktoken is missing. Cannot modify session history files.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    Requires

    Python

    Permissions

    Terminal / Shell
    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This skill identifies and removes duplication in your standing instruction files (like CLAUDE.md) and enforces a 'slice-first' approach to file reading, preventing your AI agent from wasting tokens on irrelevant data or bloated logs.

    Token Saver is optimized for Claude Code, DeepSeek Harness, Codex, and WorkBuddy, but its Python-based auditing tools and shell utilities work with any agent that relies on local markdown instructions or file-read permissions.

    No, for security and precision, the skill generates diff proposals and slimmed-down versions of your instructions that you must review and approve before any changes are applied to your project files.

    You will receive the complete Python-based token meter utility, the 'slice-first' shell integration scripts, a set of budget-aware auditing templates, and a setup guide for integrating these tools into your agent's workflow.

    The skill utilizes the `tiktoken` library for high-precision measurement of OpenAI and Anthropic models; if `tiktoken` is unavailable, it falls back to a weighted estimation algorithm to ensure you always have a baseline for your context budget.

    New in LLM Ops