Omnigent Load Test Runner

What it does

When your agent uses it

• Load-testing Omnigent under concurrent hosts and sessions
• Finding out how many hosts or turns the server can handle
• Explaining the latency percentiles and failures from a load test run
• Benchmarking real multi-turn conversations with a mocked LLM

Example prompts

• “Run a load test on omnigent with a few hosts and explain the latencies.”
• “How many hosts can it handle? Start small, then ramp up.”
• “Stress test the server with four turns per session and tell me where the p99 lands.”

Requirements

• A checkout of the omnigent repository
• uv to sync the loadtest dependencies

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Ensure deps (repo checkout)
2. 2Gather inputs
3. 3Run
4. 4Read and explain

What it can do on your machine

Read from SKILL.md and the folder at commit 26c8338. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • uv
  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Omnigent Load Test Runner loads about 1.1k tokens when it runs. Until then it costs about 190 tokens; SKILL.md has 450 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~190

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from omnigent-ai/omnigent at commit 26c8338, republished under its Apache-2.0 licence (© omnigent-ai). 450 words, ~1,069 tokens.

name

run-load-test

description

Run the Omnigent load test and produce a results file explaining the latencies. Load when the user wants to load-test / stress-test / benchmark Omnigent under concurrency ("load test omnigent", "stress test the server", "how many hosts/sessions/turns can it handle", "load test real agent turns / conversations", "run a load test"). The test makes each simulated user a real omnigent host that creates host-bound sessions and drives real multi-turn conversations with a mocked LLM; it boots its own local stack (dev/loadtest/run.py). Gather inputs, run it, then read the generated summary.md and explain the latency distribution (avg/median/p95/p99, throughput, failures). NOT for single-request latency micro-benchmarks (that is dev/benchmarks/).

uv sync --extra loadtest --extra agents-sdk

python dev/loadtest/run.py \
    --users <N> --spawn-rate <R> --run-time <T> \
    --sessions-per-user <S> --turns-per-session <TU>

© omnigent-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/run-load-test of omnigent-ai/omnigent.

Open the folder on GitHubat commit 26c8338