Digital Workers
Autonomous security operations framework for reactive alert investigation and proactive threat hunting.
Install in Claude Code
-
Configure your Query MCP server
Create a
.mcp.jsonin your working directory with your Query MCP endpoint and API token. -
Register the plugin marketplace
claude plugin marketplace add https://plugins.query.ai/query-ai/marketplace.json -
Install the plugin
claude plugin install digital-workers@query-ai -
Verify installation
claude plugin list
What It Does
Digital Workers is a Claude Code plugin that provides two workflows powered by FSQL queries against federated security data on the Query Data Mesh.
Reactive: Alert Investigation
A tiered Incident Discovery workflow that scales from a 5-minute triage to a 30-minute deep investigation with specialist analysis and senior review.
Investigation Workflow
- Step 0: Select Tier Triage / Standard / Deep (determined by your prompt)
- Gate 1: Alerts Intake Pull and classify alerts
- Gate 2: Gather Info Enrich IOCs, pivot to telemetry (Triage stops here)
- Gate 3: Analyze Score severity, route depth
- Gate 4: Decide & Act Specialists, disposition
- Gate 5: Build Evidence Assemble evidence
- Gate 6: Notify Report, senior review (Deep), present to analyst
Proactive: Threat Hunting
Sqrrl-inspired hunting loop with hypothesis-driven investigation, confidence-based completion, and detection automation with gap remediation.
Hunting Loop
- Phase 0: Hypothesis Build or receive testable hypothesis, determine hunt tier
- Phase 1: Planning Data availability mapping, connector discovery, query strategy
- Phase 2: Investigation Execute hunt queries, pivot, enrich (confidence-based)
- Phase 3: Patterns Classify findings, detect kill chains, escalate active threats
- Phase 4: Automate FSQL detections, Sigma rules, Query recipes, gap remediation
Investigation Tiers
Your prompt controls how deep the investigation goes. The orchestrator selects a tier based on how you phrase your request.
| Tier | What It Does | Time | Queries |
|---|---|---|---|
| Triage | Pull alerts, classify, scan IOCs across the mesh. Inline summary, no files. | ~5 min | 3-6 |
| Standard | Full 6-gate investigation with enrichment, telemetry pivots, severity scoring, disposition, report. | ~15 min | 10-15 |
| Deep | Everything in Standard + specialist investigators + senior analyst review + prior investigation cross-reference. | ~30 min | 20-30 |
Example Prompts
Investigation
Threat Hunting
Included Skills
| Skill | Purpose |
|---|---|
| alert-investigation | Master orchestrator — runs the 6-gate Discovery workflow |
| fsql-expert | Authors, validates, and executes FSQL queries against the mesh |
| alert-classifier | Maps alerts to OCSF category + MITRE ATT&CK technique |
| severity-scorer | Multi-factor risk scoring for depth routing |
| identity-investigator | User behavior, auth patterns, privilege analysis |
| network-investigator | Lateral movement, C2 beaconing, traffic analysis |
| threat-intel-enricher | IOC reputation and campaign correlation |
| report-writer | Response-ready reports (technical + business summary) |
| evidence-quality-checker | Data completeness and analytical reasoning validation |
| senior-analyst-review | Quality review of completed investigations |
| Hunting Skills | |
| threat-hunt | Master orchestrator — runs the 4-phase Sqrrl hunting loop |
| hypothesis-builder | Transforms raw intel into testable hypotheses |
| hunt-pattern-analyzer | Classifies hunt findings and maps to ATT&CK |
| detection-engineer | Generates FSQL detections, Sigma rules, Query recipes, and gap remediation |