Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    moretokens

    1

    Optimize LLM costs by delegating heavy reading to cheaper models while keeping high-stakes logic on strong models.

    Free

    Security scanned
    moretokens

    moretokens

    Example session with this skill installed

    /moretokens extract all security vulnerabilities from these 15 audit logs in ./logs/ and provide a prioritized fix list.

    • Read your context and instructions
    • Compiled the moretokens

    [moretokens] haiku read 15 files · opus verified and answered

    Security Vulnerability Assessment

    The analysis of 15 audit logs (approx. 42,000 words) identified the following vulnerabilities. Verification was performed on high-severity timestamps and IP addresses.

    SeverityVulnerability TypeSource FileDescription
    CriticalSQL Injection Attemptauth_log_04.logMultiple UNION SELECT payloads detected from IP 192.168.1.45.
    HighUnauthorized SSRFapi_gateway.logInternal metadata endpoint access attempts on port 80.
    MediumCleartext Token Leakdebug_sys.logSession providers logging full bearer tokens in headers.
    LowVersion Fingerprintingweb_server.logDetailed server signature returned in 404 error headers.

    Prioritized Fixes

    1. Sanitize Inputs: Implement parameterized queries for the authentication module immediately.
    2. Network Policy: Restrict egress traffic from the API gateway to prevent internal metadata access.
    3. Log Scrubbing: Update the logging middleware to redact "Authorization" and "X-Token" headers.
    4. Header Config: Set ServerTokens Prod and ServerSignature Off in the web server configuration.

    Next steps

    • Review auth_log_04.log for successful bypasses following the detected injection attempts.
    • Run the provided fix for header scrubbing in the staging environment.
    • Use moretokens report to see the estimated model distribution for this task.

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

    About this skill

    High token usage often comes from large-scale reading, not complex reasoning. This skill reduces API costs by offloading heavy reading tasks to cheaper models while keeping final decisions on your strongest model.

    What it does

    • Automatic Classification determines if a task is large enough to justify delegation or if it should be handled inline.
    • Cost-Optimized Routing selects between Lean (Haiku), Mid (Sonnet), or Strong (Opus) tiers based on word count and judgment requirements.
    • Brief Generation creates focused instructions for subagents, preventing context bloat and avoiding history repetition.
    • Verification Engine runs parallel checks on decisive quotes, line counts, and sums to ensure subagent accuracy.
    • Escalation Logic handles subagent uncertainty by re-processing only the failed segments using a higher-tier model.

    How it works

    1. Use the /moretokens command followed by the task and file paths.
    2. The agent runs a classification step to check word counts and required judgment levels.
    3. If the criteria are met, the agent briefs a cheaper model to extract or summarize the raw data.
    4. The agent verifies the extracted data against the source files using scripts or targeted greps.
    5. You receive the final high-quality answer with a status line showing the routing path used.

    Frameworks & tools

    This skill is optimized for environments supporting subagent model selection like Claude Code. It utilizes standard Unix utilities like wc and grep for validation.

    Why this beats prompting it yourself

    Manual model switching is tedious and error-prone. This skill automates the delegation logic and adds a critical verification layer that simple prompts lack, ensuring you don't trade accuracy for lower costs.

    Use cases

    • Summarizing massive document sets exceeding 3,000 words.
    • Extracting specific data points from dozens of log files or legal clauses.
    • Translating long-form content by using cheap models for drafts and strong models for review.
    • Auditing large files for specific risks or compliance violations.

    Known limitations

    Classification relies on model judgment. It requires an environment that allows subagent model selection to achieve cost savings. Savings vary by task and cannot be precisely calculated in real-time.

    Requires environment with subagent model selection. Best for inputs >3,000 words. Verification is limited to three parallel checks.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    • Free with an Agensi account

    Permissions

    Read Files
    Write Files
    Listed1 day ago

    What's inside

    Frequently Asked Questions

    The skill uses a classification step to evaluate word counts and complexity; tasks requiring high reasoning stay on premium models, while bulk data extraction or reading is routed to more affordable subagents.

    This skill is optimized for environments that support subagent orchestration and model selection, such as Claude Code or custom agents with multi-model API access.

    Accuracy is maintained through a built-in Verification Engine that performs parallel checks, such as cross-referencing quotes and line counts, ensuring the cheaper model didn't hallucinate or skip data.

    You receive the complete skill logic for classification, routing, and verification, along with documentation on how to integrate the /moretokens command into your existing workflow.

    The skill is highly effective for tasks exceeding 3,000 words, such as auditing legal documents, analyzing large log files, or summarizing massive document sets where token costs typically spike.

    New in LLM Ops