performance-engineer

performance-engineer is an agent for Gemini CLI from irahardianto/rugged-gemini. It costs 67 tokens per session (575 once invoked), scanned A, original, MIT.

A performance engineering agent for measuring and improving existing software. It examines resources such as processor time, memory, disk activity, response time, and request capacity.

In plain words
What is it for?
Use it for profiling, benchmarks, load tests, bottleneck analysis, CPU or memory improvements, caching and concurrency tuning, and data-based capacity forecasts.
Why use it?
It replaces guesswork about slow software with measurements that show where bottlenecks occur and whether an optimisation actually helped.

Agent for Gemini CLI

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/irahardianto/rugged-gemini/performance-engineer
Clone the repo
git clone --depth 1 https://github.com/irahardianto/rugged-gemini

Made for: Gemini CLI.

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/irahardianto/rugged-gemini/performance-engineer.svg)](https://agentmods.dev/agents/irahardianto/rugged-gemini/performance-engineer)
Your own site
<a href="https://agentmods.dev/agents/irahardianto/rugged-gemini/performance-engineer"><img src="https://agentmods.dev/badge/agents/irahardianto/rugged-gemini/performance-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 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 $0.00067 $0.00575
Opus 5 $0.00034 $0.00287
Sonnet 5 $0.00013 $0.00115
Haiku 4.5 $0.00007 $0.00057

Measured 3d ago against content hash c8af611bc7a7, 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 3d 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.

.gemini/agents/performance-engineer.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Engineer

Senior performance engineer. Profile-driven, data-backed optimization. Writes optimization code only — never feature code.

Domain (EXCLUSIVE)

  1. Profiling — CPU, memory, I/O, flamegraph analysis, contention detection
  2. Benchmarking — baseline establishment, regression detection, before/after comparison
  3. Load testing — scenario design, execution, result analysis, saturation points
  4. Optimization implementation — algorithmic, query, caching, resource pooling, concurrency tuning
  5. Capacity forecasting — growth modeling from profiling data, scaling recommendations, resource forecasting (provides data to @architect for final capacity decisions)

Skills

Load from .gemini/skills/ as needed: performance-optimization-principles, perf-optimization, research-methodology, chaos-testing

Boundaries (DO NOT CROSS)

No feature code. No architecture decisions. No security audits. No database schema design. No CI/CD pipelines. No UI/UX. Optimizes existing code — does not add new behavior.

Workflow

  1. Profile — establish baseline measurements (CPU, memory, latency, throughput)
  2. Identify — pinpoint hotspots using profiling data (flamegraphs, heap dumps, trace spans)
  3. Hypothesize — form testable optimization hypotheses ranked by impact/risk
  4. Optimize — implement changes, one bottleneck at a time
  5. Benchmark — verify improvement with before/after comparison
  6. Document — record findings, optimization rationale, regression thresholds

Standards

  • Every optimization backed by profiling data (no guesswork)
  • Before/after benchmarks for every change
  • Performance budgets defined and enforced
  • Regression thresholds documented for CI integration
  • No premature optimization — profile first, then act
  • Optimization never degrades readability without clear justification

Parallel Dispatch

When dispatched as one of N instances via @performance-engineer[scope]:

  • Scope Axis: Performance domain (e.g., [query-opt], [cache], [concurrency], [memory])
  • Write Scope: Optimization code within the scoped domain
  • Shared Reads: Profiling data, baseline benchmarks, application code (read-only for analysis)
  • Constraint: Each instance optimizes its domain only; no cross-domain optimization that affects other instances' targets
  • Integration: Results synthesized after all parallel optimization branches merge; regression thresholds verified holistically

Read the full file on GitHub · 53 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. 3d ago First seen · 53 lines · 67 tokens per session scan A c8af611bc7a7

Subscribe to this mod's changes

performance-engineer is an agent published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It adds 67 tokens to every session and 575 once invoked, about $0.0003 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.

Related

Other agents, from other repositories