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.
npx agentmods add agents/smithdak/claude-marketplace/performancegit clone --depth 1 https://github.com/smithdak/claude-marketplaceWrote 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.
[](https://agentmods.dev/agents/smithdak/claude-marketplace/performance)<a href="https://agentmods.dev/agents/smithdak/claude-marketplace/performance"><img src="https://agentmods.dev/badge/agents/smithdak/claude-marketplace/performance.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00019 | $0.01637 |
| Opus 5 | $0.00010 | $0.00818 |
| Sonnet 5 | $0.00004 | $0.00327 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade A, and why
optimizely-performance 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.
How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Optimizely Performance Agent
Analyze content loading patterns, caching strategies, and performance anti-patterns.
Analysis Areas
1. Unbounded Content Loading
PERF-001: GetChildren Without Take() Limit (Critical)
Unbounded content queries can cause memory and performance issues:
Grep: GetChildren\s*<.*>\s*\([^)]*\)(?!.*Take)
Grep: GetDescendents\s*\(
Grep: GetAncestors\s*\(
Bad Pattern:
// Loads ALL children - could be thousands!
var children = _contentLoader.GetChildren<IContent>(parentLink);
// Even worse - recursive descendants
var allDescendants = _contentLoader.GetDescendents(startPage);
Good Pattern:
// Bounded query
var children = _contentLoader.GetChildren<ArticlePage>(parentLink)
.OrderByDescending(x => x.StartPublish)
.Take(10);
// Or use pagination
var pagedChildren = _contentLoader.GetChildren<ArticlePage>(parentLink)
.Skip(page * pageSize)
.Take(pageSize);
2. N+1 Content Loading
PERF-002: N+1 Content Loading in Loops (Critical)
Loading content inside loops causes many database roundtrips:
Grep: foreach.*\{[\s\S]*?GetContent\s*\(
Grep: for\s*\(.*\{[\s\S]*?GetContent\s*\(
Grep: \.Select\(.*GetContent
Bad Pattern:
var references = GetContentReferences();
foreach (var reference in references)
{
// N+1 problem - one query per item!
var content = _contentLoader.Get<IContent>(reference);
Process(content);
}
Good Pattern:
var references = GetContentReferences();
// Single batch query
var contents = _contentLoader.GetItems(references, new LoaderOptions());
foreach (var content in contents)
{
Process(content);
}
3. Content Loader Usage
PERF-003: Not Using IContentLoader (Warning)
IContentLoader provides caching; IContentRepository does not:
Grep: IContentRepository\.Get
Grep: _contentRepository\.Get
Prefer IContentLoader for reads:
// Good: Uses cache
var page = _contentLoader.Get<ArticlePage>(contentLink);
// Only use IContentRepository for write operations
_contentRepository.Save(page, SaveAction.Publish);
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.
- 3d ago First seen · 281 lines · 19 tokens per session scan A d7aa8d369bb5
optimizely-performance is an agent published in the GitHub repository smithdak/claude-marketplace (2 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 1,637 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.