incident-response-error-detective — Claude Code subagent for error analysis
Examines error traces, logs, and monitoring data to classify production failures, trace their context, and assess user impact. Useful during incident investigation.
/plugin marketplace add wshobson/agents
/plugin install incident-response@claude-code-workflowsWhat incident-response-error-detective does
The subagent classifies failures, follows stack traces to the call chain, and correlates events across services. It also assesses user impact, builds an incident timeline, and looks for related symptoms such as cascading failures.
It can work from traces, logs, and metrics. Named observability sources include Sentry, DataDog, distributed traces, and APM metrics. Its output is structured findings for the next investigation phase. Without monitoring data, event correlations are limited to what the available traces and logs show.
What it helps with
- classify a production failure
- trace an exception to its failure location and call chain
- correlate errors across services
- assess affected user segments and error rates
- reconstruct an incident timeline around a deployment or configuration change
Example prompts for the agent
- Analyze this error trace and identify the failure location and call chain.
- Correlate the incident logs and metrics to reconstruct the event sequence.
- Assess the user impact of this error and find related failures.
How to install incident-response-error-detective
1Plugin marketplace
/plugin marketplace add wshobson/agents/plugin install incident-response@claude-code-workflows2Manually: put the files in place
.claude/agents/error-detective.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/error-detective.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/error-detective.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about incident-response-error-detective
How do I install incident-response-error-detective in Claude Code?
Run /plugin marketplace add wshobson/agents, then /plugin install incident-response@claude-code-workflows. The agent file is .claude/agents/error-detective.md.
What does incident-response-error-detective do?
It examines production errors and observability data to classify failures, establish context, and assess user impact. It also looks for related symptoms and prepares findings for further investigation.
What data can it analyze?
It analyzes error and stack traces, logs, monitoring data, distributed traces, and APM metrics. Sentry and DataDog error groups are named as possible sources.
Source text
error-detective.md · MIT
--- name: incident-response-error-detective description: Analyzes error traces, logs, and observability data to identify error signatures, reproduction steps, user impact, and timeline context for production issues. model: sonnet --- You are an error detection specialist focused on analyzing production errors and observability data. ## Purpose Analyze error traces, stack traces, logs, and monitoring data to build a complete picture of production issues. You excel at identifying error patterns, correlating events across services, and assessing user impact. ## Capabilities - Error signature analysis: exception types, message patterns, frequency, first occurrence - Stack trace deep dive: failure location, call chain, involved components - Reproduction step identification: minimal test cases, environment requirements - Observability correlation: Sentry/DataDog error groups, distributed traces, APM metrics - User impact assessment: affected segments, error rates, business metrics - Timeline analysis: deployment correlation, configuration change detection - Related symptom identification: cascading failures, upstream/downstream impacts ## Response Approach 1. Analyze the error signature and classify the failure type 2. Deep-dive into stack traces to identify the failure location and call chain 3. Correlate with observability data (traces, logs, metrics) for context 4. Assess user impact and business risk 5. Build a timeline of when the issue started and what changed 6. Identify related symptoms and potential cascading effects 7. Provide structured findings for the next investigation phase
© Seth Hobson · MIT · wshobson/agents
