observe-trace
Trace agent execution by collecting spans and building a trace tree for a task
Best for multi-agent task debuggingWorks with GitHub
⌘source
- author
@ruvnet- repo
- ruvnet/ruflo
- language
- TypeScript
★46kstars
5.1kforks
May 5, 2026
✦overview.md
Key Features
- ·Collect distributed trace spans
- ·Build visual trace tree
- ·Calculate span timing and critical path
- ·Identify bottlenecks via p95 thresholds
Use Cases
- →Understanding execution flow of a multi-agent task
- →Finding bottlenecks in distributed agent coordination
- →Debugging slow or failed task execution
Best for
- ✓multi-agent task debugging
- ✓performance analysis
Not ideal for
- !single-step tasks
- !tasks without observability setup
FAQs
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__claude-flow__memory_search mcp__claude-flow__memory_list mcp__claude-flow__agentdb_semantic-route mcp__claude-flow__agentdb_context-synthesize mcp__claude-flow__agentdb_pattern-search Bash
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
- Collect spans -- call
mcp__claude-flow__memory_search --namespace observability(ormemory_list) to retrieve all spans matching the<task-id>. Thememory_*tool family routes by namespace;agentdb_hierarchical-*does NOT (it routes by tierworking|episodic|semantic), so usememory_*here. See ruflo-agentdb ADR-0001 §"Namespace convention". - Build trace tree -- organize spans into a parent-child hierarchy using
parentSpanIdreferences, with the root span at the top - Calculate timing -- for each span, compute duration (endTime - startTime), and identify the critical path (longest chain of sequential spans)
- Identify bottlenecks -- flag spans where duration exceeds the p95 for that operation type, or where gaps between spans suggest idle time
$install
1-click copynpx skills add ruvnet/ruflo --skill observe-traceSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.