darkhunt-security

Use this skill when integrating `@darkhunt-security/telemetry` (the Darkhunt trace-hub TypeScript SDK at /Users/sergey/proj/darkhunt/darkhunt-telemetry-ts) into a Node.js / TypeScript service. Covers: install, singleton client setup, trace + generation + span emission, backdated `startTime`, graceful shutdown, routing-field discipline (tenantId / workspaceId / applicationId), in-cluster vs public ingest paths, the masking layer, multi-agent topology + agent handoffs (`trace.handoffToken()` / `handoffFrom`, span links, worker-vs-agent, loops & cycles), and the canonical SDK-field-to-trace-hub mapping (what attributes the backend actually reads). Auto-invoke when the user asks about adding LLM tracing, sending spans to trace-hub, integrating Darkhunt observability, wiring DarkhuntTelemetry / `client.trace()` / `trace.generation()` calls, or building a multi-agent system where agents hand off to each other (agent topology / handoff links / loops).

Use this skill when integrating `@darkhunt-security/telemetry` (the Darkhunt trace-hub TypeScript SDK) into a Node.js / TypeScript service. Covers: install, creating an API key, singleton client setup, trace + generation + span emission, backdated `startTime`, graceful shutdown, routing-field discipline (tenantId / workspaceId / applicationId), the masking layer, multi-agent topology + agent handoffs (`trace.handoffToken()` / `handoffFrom`, span links, worker-vs-agent, loops & cycles), and the canonical SDK-field-to-trace-hub mapping (what attributes the backend actually reads). Auto-invoke when the user asks about adding LLM tracing, sending spans to Darkhunt trace-hub, integrating Darkhunt observability, wiring DarkhuntTelemetry / `client.trace()` / `trace.generation()` calls, or building a multi-agent system where agents hand off to each other (agent topology / handoff links / loops).

Use this skill when integrating `darkhunt-telemetry` (the Darkhunt trace-hub PYTHON SDK at /Users/sergey/proj/darkhunt/darkhunt-telemetry-python) into a Python service. Covers: install (published on PyPI), singleton client setup, trace + generation + span emission via the `with`-based active-context helpers, backdated `start_time`, graceful shutdown, routing-field discipline (tenant_id / workspace_id / application_id), creating an OBSERVABILITY application via the Darkhunt MCP, in-cluster vs public ingest, the masking layer, and — the big part — multi-agent topology + agent handoffs across every Python transport (an in-process contextvars carrier, orchestrator-passed traces, a LangGraph state field, the HTTP `traceparent` header, a queue metadata field, and Temporal Headers via `HandoffInterceptor` + `child_args`). Auto-invoke when the user asks to add LLM tracing/observability to a Python app, send spans to trace-hub, wire `DarkhuntTelemetry` / `client.trace()` / `trace.generation()`, or build a multi-agent

Use this skill when integrating `darkhunt-telemetry` (the Darkhunt trace-hub PYTHON SDK, published on PyPI) into a Python service. Covers: install (published on PyPI), singleton client setup, trace + generation + span emission via the `with`-based active-context helpers, backdated `start_time`, graceful shutdown, routing-field discipline (tenant_id / workspace_id / application_id), creating an OBSERVABILITY application via the Darkhunt MCP, in-cluster vs public ingest, the masking layer, and — the big part — multi-agent topology + agent handoffs across every Python transport (an in-process contextvars carrier, orchestrator-passed traces, a LangGraph state field, the HTTP `traceparent` header, a queue metadata field, and Temporal Headers via `HandoffInterceptor` + `child_args`). Auto-invoke when the user asks to add LLM tracing/observability to a Python app, send spans to trace-hub, wire `DarkhuntTelemetry` / `client.trace()` / `trace.generation()`, or build a multi-agent Python system where agents hand off to