Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Agent Cost Profiler

    1

    Find where an agent's token spend actually goes, separate waste from necessary cost, and cut it without breaking quality.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Agent Cost Profiler

    Agent Cost Profiler

    Example session with this skill installed

    Our LLM bill went from $800 to $6,400 a month and nobody knows why. Here is the usage export: task, model, input tokens, output tokens, retries. Build me a cost model and tell me what to cut.

    • Read your context and instructions
    • Compiled the agent cost profiler

    Cost profile: support agent

    Headline

    Current: $6,400/month across 240k requests. Cost per successful task: $0.027.
    Largest driver: conversation history at 41% of spend.
    Realistic saving: $4,900/month (77%), of which $3,400 is low risk.

    Attribution

    Layer$/moShareNecessary?
    Conversation history2,62041%Reducible
    Classification calls1,45023%Reducible
    Tool payloads1,18018%Reducible
    Retry storms64010%Waste
    Reasoning step5108%Necessary

    Findings

    F1 — History is never trimmed

    Evidence: traces t-1180, t-2044 — 14 turns, 22k input tokens, last 12 unused.
    Cost: $2,620/month.
    Fix: summarise beyond four turns, keep the last two verbatim. Risk: low. Verify: 50 multi-turn eval cases.

    F2 — Retry storm on a deterministic error

    Evidence: 18% of lookup_order calls return the same 404 three times.
    Cost: $640/month. Pure waste.
    Fix: stop on deterministic 4xx and surface the error.

    F3 — Frontier model on classification

    Evidence: 60% of requests are intent labels; a small model matched 40/40 in a parity check.
    Cost: $1,450/month. Saving: $1,180 with low risk.

    Ranked interventions

    #InterventionSavingEffortRisk
    1Cap and summarise history$1,900MLow
    2Route classification to a small model$1,180MLow
    3Filter tool payloads to needed fields$880SLow
    4Stop deterministic retries$640SLow
    5Cache the system prompt$310SLow

    What not to cut

    The reasoning step that produces refund decisions. It is 8% of spend and the source of the product's quality.

    Assumptions

    Rates from the supplied export. Volume assumed flat; at 2x volume the history fix saves $3,800.

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

    About this skill

    Agent Cost Profiler

    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.

    Requires ingestion of usage logs or billing exports. Cannot connect directly to cloud providers. Decisions rely on user-provided pricing rates.

    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 2 days ago

    No dependencies or API access. Works with any token-usage export: traces, logs or a billing CSV.

    Permissions

    Read Files
    Listed3 days ago
    Updated2 days ago

    What's inside

    Frequently Asked Questions

    The profiler analyzes trace data and request logs from your agent sessions to identify patterns like 'retry storms,' redundant context, and unoptimized system prompts that generic monitoring tools often overlook.

    This skill is framework-agnostic; it works with any AI agent that can export raw request logs, billing CSVs, or trace data from platforms like LangSmith, LangFuse, or OpenTelemetry.

    Setup involves providing the skill with your usage data (logs or traces) and your specific model pricing tiers; the skill then performs a structural audit to generate your prioritized savings roadmap.

    You receive the full diagnostic engine, a template for data ingestion, and a structured output framework that ranks potential interventions by cost-savings versus implementation risk.

    While the skill excels at identifying structural waste in existing agents, it also includes a strategy routing module to help you determine which specific tasks in your new agent can safely be handled by cheaper, smaller models.

    The profiler is an audit and planning tool designed for deep analysis; it does not require a persistent API connection to your billing provider or offer real-time monitoring.

    New in LLM Ops