Honeycomb

Skills (11)

Claude uses these on its own when your request matches.

• beeline-migrationStep-by-step guide for migrating from Honeycomb Beelines (End of Life) to OpenTelemetry instrumentation.
• create-honeycomb-boardDesign and then create a board (dashboard) in Honeycomb with queries and SLOs.
• metrics-queriesHow to query OpenTelemetry metrics datasets in Honeycomb correctly. Metrics datasets follow different rules from trace/event datasets — many operations (bare COUNT, RATE_SUM, RATE_AVG, RATE_MAX, CONCURRENCY) are forbidden, temporal aggregation is automatic, and each metric has…
• observability-fundamentalsFirst principles behind observability — wide events, high cardinality, the core analysis loop, events vs metrics vs logs, and how instrumentation connects to debugging outcomes. Grounds recommendations in first principles rather than tool-specific how-to.
• otel-genai-instrumentationGuides instrumentation of GenAI/LLM applications with OpenTelemetry for Honeycomb, including content capture and agent failure detection.
• otel-instrumentationProvides guidance on OpenTelemetry SDK setup, custom instrumentation, and sending data to Honeycomb.
• otel-migrationGuide for retrofitting OpenTelemetry into an existing, uninstrumented application.
• production-investigationStructured workflows for investigating production issues in Honeycomb — the sequence of tool calls (context priming, broad query, BubbleUp, trace analysis, verification) and how to chain results between steps to reach root causes.
• query-patternsOpinionated guidance for constructing and interpreting Honeycomb queries on trace and event datasets — operation selection (percentiles not AVG, HEATMAP for distributions), relational field patterns (root., parent., any., none.), calculated fields, query math, and result…
• slos-and-triggersDecision heuristics for interpreting Honeycomb SLO compliance, budget burn rates, and trigger status — what the numbers mean and what action to take, including detecting misconfigured SLIs, deciding when to freeze deploys vs page on-call, and designing burn alert thresholds.…
• verify-recent-traceFind a recent trace in Honeycomb, to see what happened in a recent test. Use when asked to "verify in Honeycomb", "find the most recent trace", or "show me the trace".

MCP server

Added to Claude Code when you install the plugin. You sign in to Honeycomb the first time it is used.

• honeycombRemotehttps://mcp.honeycomb.io/mcp

Agents (2)

Specialized helpers Claude can hand work to.

• honeycomb-investigatorUse this agent when the user needs an autonomous, multi-step investigation of a production issue using Honeycomb. Examples: <example> Context: User received a PagerDuty alert about high latency user: "Our checkout API is slow, can you investigate using Honeycomb?" assistant:…
• instrumentation-advisorUse this agent when the user wants to improve their application's observability by analyzing their codebase against what Honeycomb actually receives. This agent autonomously scans code, queries Honeycomb for existing coverage, and produces a prioritized gap analysis with…

Commands (1)

Shortcuts you type in Claude Code.

• /honeycomb-setupSet up the Honeycomb MCP server connection for Claude Code

Install

claude plugin install honeycomb@claude-plugins-official

/plugin install honeycomb@claude-plugins-official

More for Honeycomb on Claude

1. 1HoneycombMCPQuery and explore observability data and SLOs13tools