Skill UI

This skill wraps the `getCompactContext` functionality to efficiently retrieve a compacted ReasoningBank context, specifically optimized for cost-analysis queries. It generates a detailed report summarizing critical metrics such as tokens saved, memories retrieved, and agentic-flow availability. It is essential for monitoring and optimizing resource usage in complex AI workflows, providing deep visibility into the efficiency and cost of the context retrieval mechanism.

Lists every session in cost-tracking with start time, message count, top model, and total cost. Use it for per-conversation spend analysis, retrospectives, and project rollups.

This skill performs multi-baseline counterfactual cost analysis for AI model routing. It compares actual session spending against hypothetical scenarios using single models like Haiku, Sonnet, or Opus. It calculates savings percentages to determine if routing decisions are cost-effective. Negative savings indicate over-escalation, while positive savings show router efficiency. Useful for quarterly reviews, CI gates, and validating routing configurations.

This Bash script compares two cost-summary JSON snapshots to detect PR-level cost regressions. It calculates deltas between baseline and current states, categorizing changes as added, removed, or changed. Users can set alerts for percentage increases, absolute USD thresholds, or specific token class growth. Designed for CI/CD workflows to gate PRs based on cost changes.

This skill exports cost-tracking telemetry data in Prometheus textfile or webhook JSON formats for external observability systems like Grafana, Datadog, and custom dashboards. It pulls session and budget records from the cost-tracking namespace, enabling real-time metric updates and ad-hoc reporting. Supports cron scheduling for near-real-time dashboards and one-shot webhook calls for immediate notifications.

Consumer-side wiring for ADR-097 Phase 3 federation_spend events. Aggregates per-peer 1h/24h/7d rolling windows, checks suspension thresholds, and reports peer spend via a Node script.

This skill acts as a composite CI gate for infrastructure cost monitoring. It runs four parallel checks: budget limits, burn rate acceleration, statistical anomalies, and budget exhaustion projections. It returns a single combined health status with the maximum exit code from all subchecks. Useful for DevOps pipelines to prevent overspending. Supports CLI customization for thresholds and skipping specific checks.

Automatically analyzes complex AI operations, including token usage patterns, model tier suitability, cache hit rates, and agent redundancy. It identifies potential waste and provides actionable, prioritized recommendations with estimated dollar savings to significantly reduce operational costs and improve efficiency across LLM pipelines.

Computes USD-per-day burn rate from recent cost-tracking sessions and linearly projects spend to 7d/30d/90d/365d horizons, including days until budget exhaustion.

This skill generates a comprehensive cost report detailing token usage and USD expenses categorized by agent and model. It calculates budget utilization, checks alert thresholds, and provides a breakdown by tier and model type. Useful for monitoring AI spending and ensuring budget compliance.

Per-message cost breakdown within a single session, drilling into flagged outlier sessions to surface expensive messages and reveal cache writes, output tokens, or model escalations.

Single-shot programmatic dump of all cost data including total spend, per-tier breakdown, top session, budget status, and federation aggregate. Outputs JSON or markdown for scripts, dashboards, and other plugins to consume.