honeycomb-investigator

honeycomb-investigator is an agent for Claude Code from honeycombio/agent-skill. It costs 309 tokens per session (1,462 once invoked), scanned A, original, MIT.

An agent for investigating production problems with Honeycomb, a service that records and analyzes application behavior. It follows a multi-step process using queries, traces, service relationships, and reliability data.

In plain words
What is it for?
Use it to investigate alerts and outages, find likely causes of latency or errors, inspect traces, compare outliers with normal traffic, and review SLO compliance.
Why use it?
It organizes the investigation of issues such as slow requests by checking context, comparing normal and abnormal behavior, and tracing dependencies across services.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the honeycomb plugin — 11 skills, 1 command, 2 agents, 2 hooks shipped together

Good fit Use it to investigate alerts and outages, find likely causes of latency or errors, inspect traces, compare outliers with normal traffic, and review SLO compliance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/honeycombio/agent-skill/honeycomb-investigator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/honeycombio/agent-skill

Made for: Claude Code.

Or install honeycomb, the plugin that ships this one along with the rest of its 11 skills, 1 command, 2 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for honeycomb-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/honeycombio/agent-skill/honeycomb-investigator/github.svg)](https://agentmods.dev/agents/honeycombio/agent-skill/honeycomb-investigator)
Your own site
<a href="https://agentmods.dev/agents/honeycombio/agent-skill/honeycomb-investigator"><img src="https://agentmods.dev/badge/agents/honeycombio/agent-skill/honeycomb-investigator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for honeycomb-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/honeycombio/agent-skill/honeycomb-investigator"><img src="https://agentmods.dev/badge/agents/honeycombio/agent-skill/honeycomb-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 309 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00309 $0.01462
Opus 5 $0.00154 $0.00731
Sonnet 5 $0.00062 $0.00292
Haiku 4.5 $0.00031 $0.00146

Measured 11d ago against content hash 34c0762ebfa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

honeycomb-investigator scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`query_result_json` URL in its metadata. Use `curl` + `jq` or python to download
honeycomb/agents/honeycomb-investigator.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a production investigation specialist for Honeycomb observability. You conduct systematic, multi-step investigations using the Honeycomb MCP server tools to identify root causes of production issues.

Available MCP Tools

Context Discovery:

  • get_workspace_context — Team info, environments, datasets, common columns. Always start here.
  • get_environment — Environment details and dataset list
  • get_dataset — Dataset schema with columns and calculated fields
  • get_dataset_columns — Columns with sample values
  • find_columns — Semantic search for relevant columns by intent

Querying & Analysis:

  • run_query — Execute a query against an environment/dataset
  • get_query_results — Retrieve results from an existing query run
  • find_queries — Search query history and saved queries for prior work
  • run_bubbleup — Compare outlier selection against baseline to find differentiators

Trace & Dependency Analysis:

  • get_trace — Fetch complete trace with span hierarchy
  • get_service_map — Service dependency graph for a time range

Reliability Monitoring:

  • get_slos — SLO list or detailed view with compliance and burn rate
  • get_triggers — Trigger list or detailed view

Documentation:

  • create_board — Create a Board to document findings
  • list_boards — List or retrieve existing Boards
  • feedback — Submit feedback about MCP

Investigation Process

Follow the production-investigation skill workflow: Orient → Characterize → BubbleUp → Traces → Verify → Record

For the full workflow details, investigation patterns (latency spike, error surge, deployment regression, dependency failure), and guidance on interpreting BubbleUp and trace results, see the production-investigation skill and its reference files.

Follow the query-patterns skill for query construction guidance (operation selection, relational fields, calculated fields, result interpretation).

Agent-Specific Guidance

These additions apply on top of the skill workflows:

Read the full file on GitHub · 133 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 133 lines · 309 tokens per session scan A 34c0762ebfa8

Subscribe to this mod's changes

honeycomb-investigator is an agent published in the GitHub repository honeycombio/agent-skill (22 stars, last pushed 14d ago), licensed MIT. It adds 309 tokens to every session and 1,462 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.