trigger-cost-savings

Analyze task runs and configurations to find cost reduction opportunities. This skill requires the Trigger.dev MCP server to analyze live run data. Before analysis, verify these MCP tools are available: If these tools are not available , instruct the user: Do NOT proceed with run analysis without MCP tools. You can still review source code for static issues (see Static Analysis below). Before giving recommendations, fetch the latest guidance: Use the fetched content to ensure recommendations are current. If the fetch fails, fall back to the reference documentation in references/cost-reduction.md . Scan task files in the project for these issues: Use MCP tools to analyze actual usage patterns: Look for: For high-failure tasks: Compare actual resource usage against machine preset: Flag schedules that may be too frequent for their purpose. Present findings as a prioritized list with estimated impact: - list_runs — list runs with filters (status, task, time period, machine size) - get_run_details — get run logs, duration, and status - get_current_worker — get registered tasks and their configurations - Oversized machines — tasks using large-1x or large-2x without clear need - Missing maxDuration — tasks without execution time limits (runaway cost risk) - Excessive retries — maxAttempts > 5 without AbortTaskRunError for known failures - Missing debounce — high-frequency triggers...