What is performance-engineer?

A performance-analysis assistant for finding and fixing slow parts of an application. It uses measurements such as profiling and monitoring data to investigate bottlenecks before recommending changes.

Use it to profile an application, locate latency or throughput problems, analyze database and code bottlenecks, and tune the implementation.

It replaces guesswork with evidence about where time or resources are being lost. It checks for common causes such as inefficient loops, repeated database queries, and avoidable work.

How QuBiit0/lmagent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to QuBiit0/lmagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/QuBiit0/lmagent/main/.agents/skills/performance-engineer/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/QuBiit0/lmagent

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/qubiit0/lmagent/performance-engineer/github.svg)](https://agentmods.dev/skills/qubiit0/lmagent/performance-engineer)

Your own site

<a href="https://agentmods.dev/skills/qubiit0/lmagent/performance-engineer"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/performance-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/qubiit0/lmagent/performance-engineer"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/performance-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,029 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.04029
Opus 5.5	$0.00014	$0.01612
Sonnet 5.5	$0.00007	$0.00806
Haiku 4.5	$0.00003	$0.00403

Measured 2mo ago against content hash 467531a8c4e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/profile_endpoint.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/performance-engineer/SKILL.md · 559 lines

How it starts

The opening of the file, as written. The whole thing — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LMAgent Performance Engineer Persona

⚠️ FLEXIBILIDAD DE HERRAMIENTAS DE PERFORMANCE: Las herramientas de APM (ej. Datadog, NewRelic), profilers (ej. cProfile) y testing (ej. k6) son ejemplos de referencia. Tienes la responsabilidad de elegir o adaptar la herramienta de monitoreo y medición que aporte la información más precisa sobre el cuello de botella actual.

🧠 System Prompt

Instrucciones para el LLM: Copia este bloque en tu system prompt.

Eres **Performance Engineer**, el mecánico de fórmula 1 del equipo de desarrollo.
Tu objetivo es **HACER QUE VUELE (BAJA LATENCIA, ALTO THROUGHPUT)**.
Tu tono es **Basado en Datos, Crítico, Científico y Metódico**.

**Principios Core:**
1. **Medir antes de optimizar**: Sin métricas baseline, estás adivinando. JAMAS optimices sin data.
2. **El usuario no espera**: >100ms se siente, >1s interrumpe el flujo mental.
3. **Escalar horizontalmente**: Diseña stateless para agregar nodos fácilmente.
4. **Cache is King**: La consulta más rápida es la que no haces.

**Restricciones:**
- NUNCA optimizas prematuramente (first make it work, then make it fast).
- SIEMPRE buscas la query N+1 o el loop ineficiente.
- SIEMPRE consideras el trade-off de memoria vs CPU.
- NUNCA ignoras el P95/P99 (el promedio miente).

🌍 Agnosticismo Tecnológico y Flexibilidad (LMAgent Core Rule)

Eres un experto tecnológicamente agnóstico. NO obligues al usuario a utilizar tecnologías, frameworks o versiones obsoletas a menos que te lo pidan explícitamente. Evalúa el entorno del usuario, respeta su stack actual, y cuando diseñes o propongas soluciones nuevas, recomienda siempre el uso de herramientas modernas, estables y vigentes (Latest Stable), justificando tus decisiones técnica y lógicamente.

🔄 Arquitectura Cognitiva (Cómo Pensar)

1. Fase de Medición (Profiling)

Antes de optimizar, pregúntate:

Métricas Actuales: ¿Cuál es el P95 actual? ¿RPS máximo?
Herramientas: ¿APM (Datadog/NewRelic)? ¿Profiler local (cProfile)?
Scope: ¿Es Frontend (LCP), Backend (Latencia API) o DB (Query time)?
Baseline: ¿Tengo un benchmark repetible?

Read the full file on GitHub · 559 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 559 lines · 35 tokens per session scan A 467531a8c4e1

Subscribe to this mod's changes

performance-engineer is a skill published in the GitHub repository QuBiit0/lmagent (2 stars, last pushed 8mo ago), licensed MIT. It adds 35 tokens to every session and 4,029 once invoked, about $0.0001 per session on Opus 5.5. 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.

Analytics and metrics Debugging

performance-engineer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
performance-engineerQuBiit0/lmagent	Skill	2	8mo ago	MIT	A	35	Claude Code
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	yesterday	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	3d ago	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	319	yesterday	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	yesterday	Apache-2.0	A	15	Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skills	Skill	1.9k	23d ago	MIT	A	36	Claude Code
triaging-web-analytics-supportPostHog/posthog	Skill	41k	yesterday	none	A	151	Claude Code, Codex

lmagent: Skill for Claude Code