Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    claude code token optimizer

    1

    Built and used daily on real Claude Code sessions, not a theoretical framework.

    $7.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    claude code token optimizer

    claude code token optimizer

    Example session with this skill installed

    Before I start this task, help me figure out what to delegate: find every place we call the old fetchUser API across the repo (~40 files), update each call site to the new fetchUserProfile signature, and write tests for the files most likely to break.

    • Read your context and instructions
    • Compiled the claude code token

    Summary

    Classified the task, delegated the mechanical scan and the rewrite, kept the risk call on the main session.

    StepTaskTierRouted to
    1Find every fetchUser call site (~40 files)T0 MechanicalAgent(scout) - Haiku
    2Rewrite each call site to fetchUserProfileT1 StandardAgent(builder) - Sonnet
    3Write tests for the highest-risk filesT1 StandardAgent(builder) - Sonnet
    4Decide which files are highest-riskT2 HardKept on the main session
    scout: grepped fetchUser( across 40 files - 6.8k tokens (Haiku)
    builder: rewrote 40 call sites to fetchUserProfile() - 41k tokens (Sonnet)
    builder: added tests for auth.ts, session.ts, profile.ts - 29k tokens (Sonnet)
    

    Next steps
    Run the test suite, then review the three new test files before committing. None of the mechanical work touched the expensive top-level model, only the risk call stayed with you.

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

    About this skill

    Same quality, fewer tokens. This skill classifies every task before you touch it, mechanical work (file search, grep, reading logs, formatting) goes to Haiku, standard work (code, tests, content) goes to Sonnet, and only genuinely hard work (architecture, security, irreversible decisions) stays with you on the expensive model.

    What it does

    Classifies tasks into three tiers and tells you exactly when to delegate instead of burning your top-level model on busywork Works with named subagents (Agent(scout), Agent(runner), Agent(builder)) or a plain model: override, zero setup required either way Ships a local, read-only, stdlib-only token-audit script (no network calls) so you can see your actual per-model usage split monthly A token-hygiene checklist covering the small habits that add up: read only the line ranges you need, grep before you read, batch independent tool calls, /clear between unrelated tasks Advisory, not a hook: copy one folder into ~/.claude/skills/, nothing to install, nothing to uninstall

    Install: copy this folder to ~/.claude/skills/token-optimizer (every project) or <project>/.claude/skills/token-optimizer (one project). That’s it.

    Built and used daily on real Claude Code sessions, not a theoretical framework. Full source and the open-source hard-enforcement plugin variant (for anyone who wants a structural guarantee instead of an advisory one) are on GitHub: github.com/HUZ5253/token-optimizer-plugin

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    API savings are higher than subscription savings. Haiku price spikes above 100K tokens. Some environment builds may fail to respect subagent model overrides.

    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

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    Software
    Python 3

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    ~/.claude/projects/**/*.jsonl

    The optional token-audit.py script reads local Claude Code session transcripts (~/.claude/projects/**/*.jsonl) to report real token usage and cost per model. It's read-only, stdlib-only Python with no network calls and no writes. The skill itself (SKILL.md) is advisory instructions only and doesn't touch the filesystem on its own.

    Listed24 days ago

    What's inside

    Frequently Asked Questions

    This skill automatically classifies incoming tasks into tiers, routing mechanical work like log analysis to Claude Haiku while reserving high-tier models for complex architecture, significantly reducing API overhead.

    It's purpose-built for Claude Code, using the Agent tool and named subagents (scout, runner, builder) along with per-agent model routing. The SKILL.md itself is plain markdown and readable by other agents, but the delegation mechanics described in it are Claude Code specific.

    You receive the tier-based routing configurations, subagent definitions, context-pruning logic, and the `token-audit.py` script for local usage analysis.

    No. Install is copying one folder to ~/.claude/skills/token-optimizer (or your project's .claude/skills/ for a project-only install). No hooks, no settings.json edits, no restart needed. It's Claude Code specific, not Cursor.

    The skill includes strict context-pruning rules, such as line-range reads and session compaction, to ensure you aren't sending redundant data or massive files to the API.

    Any update pushed to this listing reaches existing buyers automatically at no extra cost, per Agensi's platform policy. There's no fixed release schedule tied to Anthropic's own pricing or model changes.

    New in Agents & Orchestration