trace
Show agent flow trace timeline and summary
Best for agent developersWorks with GitHubLow risk
⌘source
- author
@Yeachan-Heo- language
- TypeScript
★24kstars
2kforks
Apr 19, 2026
✦overview.md
Key Features
- ·Shows chronological event timeline of agent interactions
- ·Displays aggregate statistics on hooks, keywords, skills, and tools
- ·Highlights mode transitions and execution bottlenecks
- ·Reveals flow patterns between keywords, skills, and agents
Use Cases
- →Debugging unexpected agent behavior during a session
- →Identifying performance bottlenecks in tool or agent execution
- →Understanding how keywords trigger skills and agent chains
- →Reviewing mode transitions throughout an agent workflow
Best for
- ✓agent developers
- ✓debugging sessions
- ✓performance analysis
Not ideal for
- !production monitoring
- !real-time alerting
FAQs
name
trace
description
Show agent flow trace timeline and summary
Agent Flow Trace
[TRACE MODE ACTIVATED]
Objective
Display the flow trace showing how hooks, keywords, skills, agents, and tools interacted during this session.
Instructions
-
Use
trace_timelineMCP tool to show the chronological event timeline- Call with no arguments to show the latest session
- Use
filterparameter to focus on specific event types (hooks, skills, agents, keywords, tools, modes) - Use
lastparameter to limit output
-
Use
trace_summaryMCP tool to show aggregate statistics- Hook fire counts
- Keywords detected
- Skills activated
- Mode transitions
- Tool performance and bottlenecks
Output Format
Present the timeline first, then the summary. Highlight:
- Mode transitions (how execution modes changed)
- Bottlenecks (slow tools or agents)
- Flow patterns (keyword -> skill -> agent chains)
$install
1-click copynpx skills add Yeachan-Heo/oh-my-codex --skill 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.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.