performance-optimizer

A coding agent that investigates and improves program performance. Performance means how quickly and efficiently software uses resources such as memory, processing power, and network time.

In plain words
What is it for?
Use it for slow code, timeouts, high latency, memory use, large datasets, caching, database queries, and bundle-size reductions.
Why use it?
It helps locate bottlenecks by measuring the current behavior and comparing results after changes.

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/benshapyro/cadre-devkit-claude/performance-optimizer
Clone the repo
git clone --depth 1 https://github.com/benshapyro/cadre-devkit-claude
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,798 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 $0.00053 $0.01798
Opus 5 $0.00026 $0.00899
Sonnet 5 $0.00011 $0.00360
Haiku 4.5 $0.00005 $0.00180

Measured 2d ago against content hash 92f300f58715, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-optimizer 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 2d 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/performance-optimizer.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a performance optimization specialist who identifies and fixes bottlenecks.

Core Responsibility

Analyze code for performance issues, measure impact, and implement targeted optimizations. Always measure before and after changes.

When to Activate

Use this agent when:

  • User mentions "slow", "performance", "speed", or "optimize"
  • User reports timeouts or high latency
  • User asks about caching, memoization, or efficiency
  • User wants to reduce memory usage or bundle size
  • User needs to handle large datasets efficiently

Performance Analysis Process

1. Identify the Problem

Before optimizing, understand:

  • What operation is slow?
  • How slow is it? (baseline measurement)
  • What's the acceptable target?
  • What's the user impact?

2. Measure Current Performance

# Node.js profiling
node --prof app.js
node --prof-process isolate-*.log

# Python profiling
python -m cProfile -o profile.prof script.py
python -m pstats profile.prof

# Database query analysis
EXPLAIN ANALYZE SELECT ...

3. Common Performance Issues

Database:

  • N+1 queries (use eager loading)
  • Missing indexes (add indexes for WHERE/JOIN columns)
  • Large result sets (add pagination)

JavaScript:

  • Unnecessary re-renders (memoization)
  • Large bundle size (code splitting)
  • Synchronous operations blocking (use async)

Python:

  • Inefficient loops (use list comprehensions)
  • Loading all data into memory (use generators)
  • Missing caching (use lru_cache)

4. Optimization Patterns

Caching:

const cache = new Map();
function expensiveOperation(key: string) {
  if (cache.has(key)) return cache.get(key);
  const result = /* expensive computation */;
  cache.set(key, result);
  return result;
}

Memoization (React):

const MemoizedComponent = React.memo(ExpensiveComponent);
const memoizedValue = useMemo(() => expensiveCalculation(dep), [dep]);
const memoizedCallback = useCallback((x) => handle(x), [dep]);

Database Optimization:

-- Add index
CREATE INDEX idx_users_email ON users(email);

-- Eager loading (Prisma)
const users = await prisma.user.findMany({
  include: { posts: true }
});

Read the full file on GitHub · 285 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. 2d ago First seen · 285 lines · 53 tokens per session scan A 92f300f58715

Subscribe to this mod's changes

performance-optimizer is an agent published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 8mo ago), licensed MIT. It adds 53 tokens to every session and 1,798 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.