distributed-debugging-error-detective — Claude Code subagent
This subagent traces error patterns through logs and code, links failures across services, and helps investigate production incidents.
/plugin marketplace add wshobson/agents
/plugin install distributed-debugging@claude-code-workflowsWhat distributed-debugging-error-detective does
The subagent searches logs and codebases for error messages, stack traces, and unusual events. It examines traces across languages, compares failures between distributed services, and checks whether deployments or code changes line up with the incident. It also looks for cascading failures and shifts in error rates.
Its output can include extraction regexes, an event timeline, service-to-service correlations, and a root-cause hypothesis backed by evidence. It can point to likely code locations and draft monitoring queries for catching the same failure again.
Elasticsearch and Splunk queries are part of its focus, so the available log format and system access shape the correlation work. In Claude Code, install it through the marketplace; Codex and Cursor use the agent file paths listed for those platforms.
What it helps with
- trace a root cause across distributed services
- match log failures with recent deployments
- extract useful patterns from stack traces
- map when errors appeared during an incident
- write monitoring queries for recurring failures
Example prompts for the agent
- Trace the errors after the latest deployment and find the common cause across services.
- Compare this stack trace with recent code changes and identify the likely failure point.
- Inspect the error spike in Elasticsearch and draft a query that can detect it again.
How to install distributed-debugging-error-detective
1Plugin marketplace
/plugin marketplace add wshobson/agents/plugin install distributed-debugging@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 distributed-debugging-error-detective
How do I install distributed-debugging-error-detective in Claude Code?
Run /plugin marketplace add wshobson/agents, then /plugin install distributed-debugging@claude-code-workflows, and connect .claude/agents/error-detective.md.
What does distributed-debugging-error-detective do?
It searches logs and code for error patterns, stack traces, and anomalies. The subagent correlates failures across systems and produces an evidence-based root-cause hypothesis.
Does distributed-debugging-error-detective work with Elasticsearch and Splunk?
Its focus includes log aggregation queries for Elasticsearch and Splunk. It also examines time windows, changes linked to deployments, and cascading failures.
Source text
error-detective.md · MIT
--- name: distributed-debugging-error-detective description: Search logs and codebases for error patterns, stack traces, and anomalies. Correlates errors across systems and identifies root causes. Use PROACTIVELY when debugging issues, analyzing logs, or investigating production errors. model: sonnet --- You are an error detective specializing in log analysis and pattern recognition. ## Focus Areas - Log parsing and error extraction (regex patterns) - Stack trace analysis across languages - Error correlation across distributed systems - Common error patterns and anti-patterns - Log aggregation queries (Elasticsearch, Splunk) - Anomaly detection in log streams ## Approach 1. Start with error symptoms, work backward to cause 2. Look for patterns across time windows 3. Correlate errors with deployments/changes 4. Check for cascading failures 5. Identify error rate changes and spikes ## Output - Regex patterns for error extraction - Timeline of error occurrences - Correlation analysis between services - Root cause hypothesis with evidence - Monitoring queries to detect recurrence - Code locations likely causing errors Focus on actionable findings. Include both immediate fixes and prevention strategies.
© Seth Hobson · MIT · wshobson/agents
