Menü
Trace agent execution by collecting spans and building a trace tree for a task
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | observe-trace |
| description | Trace agent execution by collecting spans and building a trace tree for a task |
| argument-hint | <task-id> |
| allowed-tools | mcp__ruflo__memory_search mcp__ruflo__memory_list mcp__ruflo__agentdb_semantic-route mcp__ruflo__agentdb_context-synthesize mcp__ruflo__agentdb_pattern-search Bash |
Collect distributed trace spans for a task and build a visual trace tree showing the execution flow, timing, and bottlenecks.
When you need to understand how a task was executed across agents -- which spans ran, how long each took, where bottlenecks occurred, and how agents coordinated.
Note (ADR-0238 S3): Spans collected via
memory_search --namespace observabilityare application-emitted records (this skill's domain). The AgentDB-substrate telemetry-introspection MCP tools that previously returned in-process spans were removed (the bound class has nogetSpansmethod); use the working stat tools (agentdb_resource_usage,agentdb_circuit_status,agentdb_rate_limit_status,agentdb_query_stats) for live substrate health, and continue usingmemory_searchfor application traces.
mcp__ruflo__memory_search --namespace observability (or memory_list) to retrieve all spans matching the <task-id>. The memory_* tool family routes by namespace; agentdb_hierarchical-* does NOT (it routes by tier working|episodic|semantic), so use memory_* here. See ruflo-agentdb ADR-0001 §"Namespace convention".parentSpanId references, with the root span at the topmcp__ruflo__agentdb_context-synthesize to combine span metadata into a narrative summary of the execution flownpx @sparkleideas/cli@latest memory search --query "trace spans for task TASK_ID" --namespace observability
Build or rebuild the ADR index + dependency graph in AgentDB by running the in-process `agentdb index` command (one cold-start, all surfaces in one pass — no per-record npx round-trips). Handles v3-style and plugin-style ADR formats.
Create a new Architecture Decision Record with sequential numbering and AgentDB registration
Hive Mind orchestration patterns — queen-led multi-agent coordination with Byzantine/Raft/Gossip/CRDT consensus, typed collective memory, dialectic council, and session checkpoint/resume. Use for decision-bearing work; use swarm-advanced for parallel execution without consensus.
Analyze git diffs for risk scoring, reviewer recommendations, and change classification
Detect missing test coverage and generate test suggestions
Hive Mind orchestration patterns — queen-led multi-agent coordination with Byzantine/Raft/Gossip/CRDT consensus, typed collective memory, dialectic council, and session checkpoint/resume. Use for decision-bearing work; use swarm-advanced for parallel execution without consensus.