skills.rest
DojoGenesis
DojoGenesisCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-performance-report

Generate aggregated performance reports from stored trace data.

2|Updated Apr 8, 2026
Search Tags:#performance#monitoring#agent#trace#report#cost
One-click install
npx skills add https://github.com/DojoGenesis/gateway --skill agent-performance-report
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-performance-report
Source: https://github.com/DojoGenesis/gateway/tree/main/plugins/system-health/skills/agent-performance-report
Command: npx skills add https://github.com/DojoGenesis/gateway --skill agent-performance-report

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It creates a concise, actionable markdown report that turns raw agent trace data into a clear summary of tool usage, token consumption, costs, bottlenecks, and recommendations.

Core Features & Use Cases

  • Aggregated Metrics: Summarizes tool call counts, success rates, durations, token usage, and cost breakdowns.
  • DAG Execution Insights: Analyzes plan creation, node parallelism, and execution success.
  • Performance Issue Detection: Highlights slow tools, expensive operations, failed nodes, and budget spikes.
  • Use Cases: End-of-sprint retrospectives, budget alert investigations, or any session cost reporting.

Quick Start

Request a weekly performance report by asking the skill for a report with time_period "last_7_days".

Frequently Asked Questions about agent-performance-report

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an agent performance report from trace data?▼

To generate an agent performance report, query stored trace data with a specified time period to summarize tool call metrics, token usage, costs, and bottlenecks into a markdown report.

What metrics are included in an agent trace performance report?▼

An agent trace performance report includes aggregated metrics such as tool call counts, success rates, execution durations, token consumption, cost breakdowns, and DAG execution insights.

How does bottleneck detection work for agent tool calls?▼

Bottleneck detection for agent tool calls works by analyzing orchestration events and trace data to highlight slow tools, expensive operations, failed nodes, and budget spikes.

Can I use trace data to investigate budget spikes in my agent sessions?▼

Yes, you can investigate budget spikes by querying the BudgetTracker and trace data to compute cost statistics and receive actionable recommendations in a markdown report.

What's the best way to summarize token usage and costs for a sprint retrospective?▼

The best way to summarize token usage and costs for a sprint retrospective is to request a performance report covering the sprint time range to aggregate tool metrics and budget data.

Do I need a BudgetTracker to generate agent cost reports?▼

Yes, the skill queries the BudgetTracker alongside TraceStorage and orchestration events to compute cost statistics and output actionable recommendations for budget alert investigations.

Related Skills

Explore More Software Engineering Skills→
aaaa47080aaaa47080
4

cost-aware-llm-pipeline

Routes LLM calls by task complexity to optimize cost and performance using BudgetTracker and caching.

Community
Advanced
ivegamsftivegamsft

sprint-retrospective

Generate sprint retrospective documents with templates, metrics, and improvement tips.

Community
Intermediate
XeldarAlzXeldarAlz
18

hud-statusline

Monitor and display Unity workflow states, including phase, active agent, and session duration.

Community
Intermediate
SaturateSaturate

stats

Compute Claude Code usage totals, per-tool counts, and session counts from JSONL logs.

Community
Intermediate