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 skills add Bbeierle12/Skill-MCP-Claude --skill performance-at-scalegit clone --depth 1 https://github.com/Bbeierle12/Skill-MCP-ClaudeWrote 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/skills/bbeierle12/skill-mcp-claude/performance-at-scale)<a href="https://agentmods.dev/skills/bbeierle12/skill-mcp-claude/performance-at-scale"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/performance-at-scale/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.
<a href="https://agentmods.dev/skills/bbeierle12/skill-mcp-claude/performance-at-scale"><img src="https://agentmods.dev/badge/skills/bbeierle12/skill-mcp-claude/performance-at-scale.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00369 |
| Opus 5 | $0.00026 | $0.00185 |
| Sonnet 5 | $0.00010 | $0.00074 |
| Haiku 4.5 | $0.00005 | $0.00037 |
Grade A, and why
performance-at-scale 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 9d 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.
What it actually says
Performance at Scale
Spatial indexing and world streaming for large-scale building systems.
Quick Start
import { SpatialHashGrid } from './scripts/spatial-hash-grid.js';
import { Octree } from './scripts/octree.js';
// Uniform distribution - use hash grid
const grid = new SpatialHashGrid(10);
grid.insert(piece, piece.position);
const nearby = grid.queryRadius(position, 15);
// Clustered bases - use octree
const octree = new Octree(bounds, { maxDepth: 8 });
octree.insert(piece);
const inBox = octree.queryBox(min, max);
Reference
See references/performance-at-scale.md for detailed guidance on:
- Spatial partitioning selection (when to use grid vs octree)
- Chunk loading strategies
- Instancing and LOD
- Memory management
Scripts
scripts/spatial-hash-grid.js- O(1) queries for uniform distributionscripts/octree.js- Adaptive queries for clustered objectsscripts/chunk-manager.js- World streaming for large mapsscripts/performance-profiler.js- Benchmarking utilities
Selection Guide
| Pieces | Distribution | Use |
|---|---|---|
| <1,000 | Any | Array |
| 1-5k | Uniform | SpatialHashGrid |
| 1-5k | Clustered | Octree |
| 5k+ | Any | ChunkManager + Octree per chunk |
What ships with it
6 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.
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.
- 9d ago First seen · 50 lines · 51 tokens per session scan A d53cd07b968d
performance-at-scale is a skill published in the GitHub repository Bbeierle12/Skill-MCP-Claude (8 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 369 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.
Other skills, from other repositories
flask-werkzeug-attack
Exploit Flask/Werkzeug debugger exposure for traceback and SECRET leaks.
flask-expert
Expert-level Flask web development, REST APIs, extensions, and production deployment. Use when the user mentions Python, web framework, REST APIs, or Jinja2, or when the task involves Flask Fundamentals or Flask Extensions.
fast-dash
Build a Fast Dash web app from a Python function. Use when the user wants to turn a function into an interactive app, add a UI to an existing function, or build a dashboard / form / wizard. Fast Dash infers UI components from type hints, so a well-typed function becomes an app with one decorator.
flask
Flask - Lightweight Python web framework for microservices, REST APIs, and flexible web applications with extensive extension ecosystem.
flask
Operational skill for Flask: app factories, blueprints, request context, Jinja/JSON APIs, extensions, and pytest testing patterns.
flask
Flask - Lightweight Python web framework for microservices, REST APIs, and flexible web applications with extensive extension ecosystem.