ClaudeSuperPower
SubmitLog in

honeycomb-investigator

Subagent

Use 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: "I'll use the honeycomb-

0Debugging

When Claude delegates to this

  • Use this agent when the user needs an autonomous, multi-step investigation of a production issue using Honeycomb.

What it does

Examples: <example> Context: User received a PagerDuty alert about high latency user: "Our checkout API is slow, can you investigate using Honeycomb?" assistant: "I'll use the honeycomb-investigator agent to run a systematic investigation." <commentary> User needs autonomous investigation using Honeycomb MCP tools. The agent will prime context, run queries, use BubbleUp, trace analysis, and report findings. </commentary> </example> <example> Context: User sees errors in production after a deployment user: "We deployed v2.5 and errors spiked. Investigate what went wrong in Honeycomb." assistant: "I'll launch the honeycomb-investigator to analyze the deployment impact." <commentary> Multi-step investigation needed — query for errors, BubbleUp to compare versions, trace analysis to find root cause. Agent orchestrates the full workflow. </commentary> </example> <example> Context: SLO budget is burning fast user: "Our checkout SLO is burning budget fast. Can you figure out what's going on?" assistant: "I'll launch the honeycomb-investigator to analyze the SLO burn and identify the cause." <commentary> SLO-driven investigation. Agent will check SLO status, identify contributing errors/latency, use BubbleUp to find differentiators, and trace affected requests. </commentary> </example>

Model unspecified

No model pin — runs on your session's model.

Default effort

No reasoning budget declared.

Separate context

Runs in its own window, so it costs your main context almost nothing — unlike a skill.

Its system prompt

92 lines

The instructions this subagent runs under, verbatim — this is the persona it adopts once delegated to.

Shipped by 1 plugin

Installing any of these installs this subagent.

honeycomb19

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Inherit all session tools

Declares no tool restrictions — inherits every session tool

~353 tokens of context used while enabled, before you invoke anything

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just subagents.

Skills

All skills →

cardputer-buddy

Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add

32.8K stars

planning-with-files

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Claude Code, Codex, Cursor, Kiro, OpenCode and 60+ agents via the Agent Skills standard.

25.8K stars

troubleshoot

Diagnose and fix a failing or misbehaving Atomic Agents app — import errors, schema validation failures, empty or malformed LLM output, provider role/mode errors, history and context problems, MCP transport errors. Use when the user reports an error, traceback, or wrong behavior in atomic-agents cod

6.1K stars