Analytics & Monitoring Agent Skills for DeepSeek Harness

Use a local Python simulation rollout to write an indexed MCAP with Foxglove transforms, robot geometry, and metrics.

Tracks LLM token consumption and usage metrics for billing, monitoring, and optimization.

Break down Claude Code costs using the Agent Monitor pricing engine.

Wrap getTokenOptimizer().getCompactContext() to retrieve compacted ReasoningBank context for cost-analysis queries; report bridge-reported…

Export cost-tracking telemetry in Prometheus textfile or webhook JSON formats — for external observability (Grafana, Datadog, custom…

Consumer-side wiring for ADR-097 Phase 3 federation_spend events — per-peer rolling windows + suspension-threshold check

Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns

Generate a cost report showing token usage and USD costs by agent and model

Single-shot programmatic dump of all cost data — total spend, per-tier, top session, budget status, federation aggregate.

Auto-capture per-session token usage from the Claude Code session jsonl and persist to the cost-tracking namespace

Build a `BaseDynamicContextProvider` that injects a named, titled block into an agent's system prompt at every `run()` — current time…

Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered…

Creates comprehensive dashboard and analytics interfaces that combine data visualization, KPI cards, real-time updates, and interactive…

This skill enables Claude to generate data visualizations, plots, charts, and graphs from provided data.

Revenue leadership for B2B SaaS: forecasting, sales model design, pricing, and net revenue retention.

Queries local analytics across OrchestKit projects for agent usage, skill frequency, hook timing, team activity, session replay, cost…

Comprehensive cryptocurrency market research and analysis using specialized AI agents.

/cs:caio-review <plan> — Eval-demanding Chief AI Officer interrogation of any plan that involves AI: model selection, risk classification…

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI).

Install cuOpt for C — conda, locate lib/headers, verification.