Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Token Budget Check

    1

    Estimate tokens for files, folders or stdin before sending them to an AI agent, and get an OK/WARN/OVER verdict with trimming advice.

    Free

    Security scanned
    token-budget-check

    token-budget-check

    Example session with this skill installed

    Is src/ too big to load into context? Budget is 32k tokens.

    • Read your context and instructions
    • Compiled the token-budget-check

    Context budget: ~61,787 / 32,000 tokens (193%) 🔴 OVER BUDGET. Largest: EnhancedDashboardProvider.ts ~7,548 tok. Suggestion: read only the relevant function instead of the whole file.

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

    About this skill

    Estimate the token cost of files before they go into the context window, compare it to a budget, and suggest how to trim when needed. 100% local: nothing is sent anywhere.

    • The user asks how many tokens a file, folder, or pasted text will use.
    • You are about to read a large file, log, lockfile, or directory in full.
    • The user wants to stay under a context or cost budget.
    • A task involves several large files and you must decide what to load.

    Use the bundled script (Python 3, standard library only):

    • Paths can be files or directories (directories are scanned recursively; .git, node_modules, dist, build, binaries and lockfiles are skipped).
    • --threshold is the total token budget (default 32000).
    • --warn-percent is when to warn (default 75).
    • --json prints machine-readable output.
    • Read from stdin with - (e.g. git diff | python3 scripts/token_budget.py -).

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Token counts are heuristic estimates (about 5-15% off a real tokenizer) and differ between models. Not billing-grade.

    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 buying a skill.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 23 days ago

    • Free with an Agensi account

    Software
    Python 3Git

    Permissions

    File Scopes

    Read-only
    access
    to
    the
    paths
    you
    ask
    it
    measure

    Fully local. No network calls, no file writes, no environment variables.

    Listed23 days ago

    What's inside

    Frequently Asked Questions

    Estimate tokens for files, folders or stdin before sending them to an AI agent, and get an OK/WARN/OVER verdict with trimming advice.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use token-budget-check on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in LLM Ops

    Free