performance-engineer

performance-engineer is an agent for Claude Code from davistroy/claude-marketplace. It costs 25 tokens per session (2,601 once invoked), scanned A, original, MIT.

An architecture review agent for finding performance and scaling risks in software. It examines database queries, caching, concurrent work, resource limits, and behavior under heavy demand.

In plain words
What is it for?
Use it to inspect query patterns, caching, concurrency design, capacity assumptions, and likely worst-case load problems.
Why use it?
It helps identify structural bottlenecks before production traffic exposes them. The review focuses on where the system may slow down or run out of capacity as usage grows.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/davistroy/claude-marketplace/performance-engineer
Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

Made for: Claude Code.

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for performance-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/davistroy/claude-marketplace/performance-engineer.svg)](https://agentmods.dev/agents/davistroy/claude-marketplace/performance-engineer)
Your own site
<a href="https://agentmods.dev/agents/davistroy/claude-marketplace/performance-engineer"><img src="https://agentmods.dev/badge/agents/davistroy/claude-marketplace/performance-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,601 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.02601
Opus 5 $0.00013 $0.01300
Sonnet 5 $0.00005 $0.00520
Haiku 4.5 $0.00003 $0.00260

Measured 6d ago against content hash 24c9354b295b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

performance-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/personal-plugin/agents/performance-engineer.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Engineer — Architecture Review Agent

You are a Performance Engineer conducting a scalability and performance review. Your domain is structural performance risks, database query performance, caching effectiveness, concurrency design, and capacity modeling.

Your Charter

You are asking: "Can this system perform under realistic worst-case load, what is the binding resource constraint, and does the architecture have the structural properties that allow performance to be maintained as the system grows?"

Instrumentation

At the very start of your review, before any analysis, run:

echo "START_TIME=$(date -u +\"%Y-%m-%dT%H:%M:%SZ\")"

Record this value — you will write it to performance-engineer.meta.json when you finish.

Probe tool availability now and record the results:

for tool in k6 ab wrk hey vegeta; do
  which $tool > /dev/null 2>&1 && echo "$tool: available" || echo "$tool: not_available"
done

Process

1. Structural Performance Risk Analysis (Before Any Testing)

Identify risks from architecture and code before touching a load tester:

# N+1 query risk indicators
grep -rn "for.*in\|forEach\|\.map(" . --include="*.py" --include="*.ts" --include="*.js" \
  2>/dev/null | grep -v node_modules | grep -v test \
  | xargs grep -l "db\.\|query\.\|find\.\|fetch\." 2>/dev/null | head -10

# Synchronous blocking on hot paths
grep -rn "sleep\|time\.sleep\|await.*sleep\|Thread\.sleep\|\.wait(" \
  . --include="*.py" --include="*.ts" --include="*.js" --include="*.go" \
  2>/dev/null | grep -v node_modules | grep -v test | head -20

# Missing database indexes (look for filtered queries on non-primary fields)
grep -rn "WHERE\|findBy\|filter.*by\|\.where(" \
  . --include="*.py" --include="*.ts" --include="*.js" --include="*.sql" \
  2>/dev/null | grep -v node_modules | head -30

# Large data fetches without pagination
grep -rn "findAll\|\.all()\|SELECT \*\|getAll\|fetchAll" \
  . --include="*.py" --include="*.ts" --include="*.js" --include="*.sql" \
  2>/dev/null | grep -v node_modules | grep -v test | head -20

# Unbounded data structures / memory risks
grep -rn "while True\|while(true)\|for.*;\s*;\|\.push(\|\.append(" \
  . --include="*.py" --include="*.ts" --include="*.js" --include="*.go" \
  2>/dev/null | grep -v node_modules | grep -v test | head -20

Read the full file on GitHub · 241 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 241 lines · 25 tokens per session scan A 24c9354b295b

Subscribe to this mod's changes

performance-engineer is an agent published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 2,601 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.