Run Load Test

Run Load Test is a Quality skill for Claude Code, published by omnigent-ai in omnigent.

8.9K stars1.3K forkson omnigent-ai/omnigentAdded 2026/08/15+1% in starsRepository updated 2026/08/15

agent-frameworkagent-governanceagent-orchestrationagentsaiai-agentai-agentsclaude-codecodexcoding-agentsdeveloper-toolsllmmlmulti-agentpythonsandbox

Install in seconds

Install Run Load Test

Copy Run Load Test into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/omnigent-ai/omnigent/tree/main/.claude/skills/run-load-test ~/.claude/skills/run-load-test

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/omnigent-ai/omnigent.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/run-load-test/SKILL.md in omnigent-ai/omnigent
Installs to: ~/.claude/skills/run-load-test
Collection: One of 24 skills cataloged from this repository
Category: Quality — 1354 skills

What Run Load Test does

Run Load Test drives Omnigent's load-test stack to benchmark concurrency with real host-bound sessions and a mocked LLM. Use it when load-testing, stress-testing, or benchmarking Omnigent under concurrency.

Run Load Test is cataloged under Quality on DirSkills. Run Load Test comes from a repository tagged agent-framework, agent-governance, agent-orchestration, agents and ai.

Documentation

README

Excerpt

Run the Omnigent load test

Drives dev/loadtest/ end to end: collect inputs → run → read summary.md → explain the latencies. Each Locust user is a real omnigent host that registers over the host tunnel, creates host-bound sessions, and drives real multi-turn conversations — every turn is a genuine post→idle loop through the host's runner, with the LLM mocked (zero latency) so the numbers are Omnigent's own overhead. -u N scales the number of hosts.

It boots its own local stack (server + mock LLM), so there is no server to point at, and it runs from a repo checkout only. For single-request latency micro-benchmarks (not concurrency), that is a different tool: dev/benchmarks/.

1. Ensure deps (repo checkout)

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Run Load Test

What else does omnigent-ai publish alongside Run Load Test?
Run Load Test is one of 24 skills that DirSkills catalogs from omnigent-ai/omnigent, the repository it ships in. Its siblings there include API Docs, Antigravity Native E2E Testing and Antigravity SDK E2E Dev. Each one is a separate skill with its own page in this directory, installs the same way Run Load Test does, and is maintained by omnigent-ai in that same repository. The rest of the collection is listed on the omnigent-ai/omnigent page.
How does Run Load Test compare to other Quality skills?
Run Load Test ranks #210 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Run Load Test against them. Open each page to compare what they document and how they install.