Agent Run Monitor

AI coding agents fail in predictable ways: they loop, stall, and burn tokens while making no progress. Karpathy's observation holds up in practice: a single well-scoped context file (a CLAUDE.md) plus tight run budgets fixes most of it. Estimate your spend, visualize the run, and unstick the agent below. All numbers here are estimates, not real billing.

Token Spend Calculator

Model preset

Run steps

Tokens in per step

Tokens out per step

Price per 1K in ($)

Price per 1K out ($)

Retries (wasted steps)

Seconds per step

$0.00Estimated total cost

$0.00Cost of retries

0mEstimated wall time

Estimates assume uniform steps. Real billing varies with caching, tool calls, and context growth. Always confirm against your provider's usage dashboard.

Burn Rate and Run Timeline

Cumulative costRetry steps

Simulated Run Timeline

ProductiveRetry loopStall

Stuck-Agent Checklist

Match the failure pattern you see in the timeline to a corrective prompt. Copy it straight into the agent session.