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.
git clone --depth 1 https://github.com/honeycombio/agent-skillWrote 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.
[](https://agentmods.dev/agents/honeycombio/agent-skill/honeycomb-investigator)<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.
<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>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.
| Model | Per session | Once 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 |
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 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 listget_dataset— Dataset schema with columns and calculated fieldsget_dataset_columns— Columns with sample valuesfind_columns— Semantic search for relevant columns by intent
Querying & Analysis:
run_query— Execute a query against an environment/datasetget_query_results— Retrieve results from an existing query runfind_queries— Search query history and saved queries for prior workrun_bubbleup— Compare outlier selection against baseline to find differentiators
Trace & Dependency Analysis:
get_trace— Fetch complete trace with span hierarchyget_service_map— Service dependency graph for a time range
Reliability Monitoring:
get_slos— SLO list or detailed view with compliance and burn rateget_triggers— Trigger list or detailed view
Documentation:
create_board— Create a Board to document findingslist_boards— List or retrieve existing Boardsfeedback— 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:
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.
- 11d ago First seen · 133 lines · 309 tokens per session scan A 34c0762ebfa8
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.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.