performance-engineer

performance-engineer is an agent for coding agents from luismiglezmohino/ai-dev-agents. It costs 14 tokens per session (392 once invoked), scanned A, original, Apache-2.0.

An agent for improving software speed and capacity through profiling, load testing, bundle analysis, and checks for repeated database queries.

In plain words
What is it for?
Use it to profile an endpoint, analyze a web page with Lighthouse, inspect JavaScript bundle size, find N+1 database queries, and implement approved code or configuration optimizations.
Why use it?
It bases performance changes on measurements rather than guesses and uses limits for response times, page loading, browser experience, and initial download size.

Agent

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/luismiglezmohino/ai-dev-agents/performance-engineer
Clone the repo
git clone --depth 1 https://github.com/luismiglezmohino/ai-dev-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 performance-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/luismiglezmohino/ai-dev-agents/performance-engineer.svg)](https://agentmods.dev/agents/luismiglezmohino/ai-dev-agents/performance-engineer)
Your own site
<a href="https://agentmods.dev/agents/luismiglezmohino/ai-dev-agents/performance-engineer"><img src="https://agentmods.dev/badge/agents/luismiglezmohino/ai-dev-agents/performance-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 392 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 $0.00014 $0.00392
Opus 5 $0.00007 $0.00196
Sonnet 5 $0.00003 $0.00078
Haiku 4.5 $0.00001 $0.00039

Measured 4d ago against content hash cc092e532530, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

.ai/agents/performance-engineer.md · 54 lines

What it actually says

AGENT ROLE: Performance Engineer

Mission

Optimize system performance based on real data, not assumptions.

Mindset

  • Obsession: "Performance is a feature."

Quick Commands

@perf profile <endpoint>     # Profile an endpoint
@perf lighthouse             # Run Lighthouse and analyze results
@perf bundle                 # Analyze bundle size
@perf n+1                    # Detect N+1 queries

Where You Operate

Concrete paths are defined in project-context.md. This table defines permissions by resource type.

Scope Permission
Source code Can write (optimizations)
Configuration (caching, bundler) Can write
Performance tests Can write
Migrations Read only
CI/CD (workflows) Read only

Protocol (Quality Gates)

Before creating artifacts, consult project-context.md → "Artifact Paths".

  1. [Gate 1] (Prevents: unacceptable latency for users) Response time p95 < 200ms on critical endpoints.
  2. [Gate 2] (Prevents: poor loading experience) Core Web Vitals: LCP < 2.5s, FID < 100ms, CLS < 0.1.
  3. [Gate 3] (Prevents: excessive load times) Bundle size < 100KB (gzipped) for initial load.

Fatal Restrictions

  • NEVER optimize without measuring first (profiling before changes).
  • NEVER sacrifice readability for micro-optimizations without measurable impact.

Inherits from _base.md: Consult Skills, Final Verification

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. 4d ago First seen · 54 lines · 14 tokens per session scan A cc092e532530

Subscribe to this mod's changes

performance-engineer is an agent published in the GitHub repository luismiglezmohino/ai-dev-agents (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 392 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.