mcpField
O
observe-trace

observe-trace

github.com/ruvnetAgent workflows80.0k732 installsUpdated today
Repository

About observe-trace

observe-trace is a Ruflo skill for reconstructing a task's distributed execution from trace spans. It builds a timed parent-child tree, identifies critical paths and bottlenecks, and summarizes coordination across agents.

Key features

  1. 01Retrieves spans for a task
  2. 02Builds a parent-child trace tree
  3. 03Calculates durations and critical path
  4. 04Flags slow spans and idle gaps
  5. 05Summarizes execution flow

Use cases

  1. 01Inspect how a task ran across agents
  2. 02Find slow operations in a trace
  3. 03Review agent coordination and execution timing

MCP support

Uses Ruflo MCP tools to retrieve span records from the observability namespace and synthesize span metadata into a narrative summary.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ruvnet/ruflo --skill observe-trace

After installing, type/observe-tracein Claude Code to confirm it loaded.

Details

From the project README

Observe Trace

Collect distributed trace spans for a task and build a visual trace tree showing the execution flow, timing, and bottlenecks.

When to use

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.

Steps

  1. Collect spans -- call mcp__plugin_ruflo-core_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".
  2. Build trace tree -- organize spans into a parent-child hierarchy using parentSpanId references, with the root span at the top
  3. Calculate timing -- for each span, compute duration (endTime - startTime), and identify the critical path (longest chain of sequential spans)
  4. Identify bottlenecks -- flag spans where duration exceeds the p95 for that operation type, or where gaps between spans suggest idle time
  5. Synthesize -- call mcp__plugin_ruflo-core_ruflo__agentdb_context-synthesize to combine span metadata into a narrative summary of the execution flow
  6. Report -- display the trace tree with: span name, agent, duration, status (OK/ERROR), and bottleneck flag; include total trace duration and critical path duration

CLI alternative

npx @claude-flow/cli@latest memory search --query "trace spans for task TASK_ID" --namespace observability

Comments

Markdown supported