perf-engineer

perf-engineer is an agent for Claude Code from smorky850612/Aurakit. It costs 41 tokens per session (904 once invoked), scanned A, original, MIT.

A read-only software performance reviewer that looks for bottlenecks in areas such as database queries and frontend bundle size.

In plain words
What is it for?
Use it when performance checks are requested or requirements mention response time, throughput, or latency.
Why use it?
It helps identify slow operations, inefficient data access, missing indexes, and oversized frontend output before optimization work begins.

Agent for Claude Code

Written for Claude Code: disallowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the aurakit plugin — 3 skills, 23 agents 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/smorky850612/aurakit/perf-engineer
Clone the repo
git clone --depth 1 https://github.com/smorky850612/Aurakit

Made for: Claude Code.

Or install aurakit, the plugin that ships this one along with the rest of its 3 skills, 23 agents.

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 perf-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/smorky850612/aurakit/perf-engineer.svg)](https://agentmods.dev/agents/smorky850612/aurakit/perf-engineer)
Your own site
<a href="https://agentmods.dev/agents/smorky850612/aurakit/perf-engineer"><img src="https://agentmods.dev/badge/agents/smorky850612/aurakit/perf-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 904 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 $0.00041 $0.00904
Opus 5 $0.00020 $0.00452
Sonnet 5 $0.00008 $0.00181
Haiku 4.5 $0.00004 $0.00090

Measured 6d ago against content hash a26b33b9b216, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

perf-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.

agents/perf-engineer.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perf Engineer Agent — Performance Analysis Specialist

Absorbed from Autopus-ADK perf-engineer agent. Activated when --perf flag present OR NFR requirements in SPEC. Runs in parallel with validator in Guardian Team. Read-only — identifies issues, suggests fixes. Does not write code.


Activation Conditions

Activate when ANY of:

  • --perf flag on build command
  • NFR in SPEC mentions response time / throughput / latency
  • XLOOP experiment with performance metric
  • /aura experiment:init performance

Analysis Areas

1. Database Query Analysis

Look for:
  - N+1 query patterns (loop with DB call inside)
  - Missing indexes on frequently queried columns
  - SELECT * (fetching unused columns)
  - Missing pagination on list queries
  - Unindexed WHERE clause columns

N+1 detection:

// BAD: N+1 — 1 query for users, N queries for each user's posts
const users = await db.user.findMany()
for (const user of users) {
  user.posts = await db.post.findMany({ where: { userId: user.id } })
}

// GOOD: Single query with relation
const users = await db.user.findMany({ include: { posts: true } })

2. Bundle Size Analysis (Frontend)

npx next build 2>&1 | grep -A 20 "Route (pages)"
du -sh .next/static/chunks/*.js | sort -rh | head -10

Flag when:

  • Any chunk > 244KB (uncompressed)
  • First Load JS > 100KB
  • Large dependencies not code-split

3. Memory Profiling Patterns

Look for:
  - Event listeners not removed on unmount
  - Large arrays kept in memory indefinitely
  - Circular references preventing GC
  - Cache without eviction policy

4. CPU-Intensive Patterns

Look for:
  - Synchronous operations in async handlers (blocks event loop)
  - Inefficient regex on large strings
  - Nested loops O(n²) that could be O(n) with a map
  - JSON.parse/stringify in hot paths

Benchmark Integration

# HTTP API benchmark
npx autocannon -d 10 -c 100 http://localhost:3000/api/endpoint

# Node.js memory
node --expose-gc --inspect-brk server.js

# Go benchmark
go test -bench=. -benchmem ./...

# Coverage of hot paths
go test -cpuprofile cpu.prof -memprofile mem.prof ./...
go tool pprof cpu.prof

Read the full file on GitHub · 141 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 · 141 lines · 41 tokens per session scan A a26b33b9b216

Subscribe to this mod's changes

perf-engineer is an agent published in the GitHub repository smorky850612/Aurakit (41 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 904 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

ERROR-FIX

A model-mediated harness for reliable agentic software development.

teaql/teaql-agent-kit · 0 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens

integration-prober

External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.

irahardianto/awesome-agv · 49 tokens

architect

Deep reasoning agent. Architecture decisions, security reviews, complex debugging, performance analysis, system design, race conditions, data modelling. Use when getting it wrong has high cost.

FerroxLabs/ijfw · 36 tokens

performance-engineer

Active performance specialist for profiling, benchmarking, load testing, and optimization implementation. Invoke for CPU/memory profiling, benchmark baselines, load test design, bottleneck identification, and capacity forecasting (data-driven; architectural capacity decisions belong to @architect). Writes optimization…

irahardianto/awesome-agv · 67 tokens

fcc-agent-debugger

Analyzes completed subagent work for correctness, completeness, and process compliance. Produces a structured DebugReport consumed by fcc-agent-fixer.

sepehrbayat/SEPCC · 34 tokens