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 arcasilesgroup/ai-engineering --skill ai-stress-testgit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/arcasilesgroup/ai-engineering/ai-stress-test)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-stress-test"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-stress-test/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/arcasilesgroup/ai-engineering/ai-stress-test"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-stress-test.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00151 | $0.01824 |
| Opus 5.5 | $0.00060 | $0.00730 |
| Sonnet 5.5 | $0.00030 | $0.00365 |
| Haiku 4.5 | $0.00015 | $0.00182 |
Grade A, and why
ai-stress-test 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 19d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-stress-test — find where it breaks, not just whether it works
What it produces
A named breaking point with the load that caused it, the metric that failed first, and the safe capacity ceiling. Every claim backed by a number from a real run.
Safety
- Never run against production without explicit written approval and a defined abort threshold.
- Never generate unbounded concurrency or duration. Every run has a ceiling.
- Refuse requests that look like denial-of-service: "flood this", "hammer it until it dies", "DDoS it" get a hard no, followed by a controlled alternative.
- Default to
plan-onlymode when the target environment is unclear. Ask before executing. - Stop immediately if error rate exceeds 5% during a run, or if the target system reports health-check failures.
Steps
1. Collect inputs
Gather or ask for:
- target: base URL, host, or service under test.
- environment:
local,staging, orproduction. Ifproduction, require explicit approval and abort thresholds before doing anything. - endpoints: which flows to test. If unknown, ask for the top 5 most critical user journeys (from access logs, SLOs, or product judgment).
- baseline load: normal traffic level (requests/second or concurrent users).
- expected peak: what the system should handle without degradation.
- thresholds: acceptable latency (p95, p99), max error rate, minimum throughput. If not provided, use conservative defaults: p95 < 500ms, error rate < 1%, throughput matching baseline.
- auth: how to authenticate requests (API key, bearer, session, none).
2. Select the tool
Use the installed tool. Do not install anything without asking.
| Tool | When | Command shape |
|---|---|---|
| k6 | Default for HTTP APIs, CI-friendly, threshold-native | k6 run script.js |
| JMeter | Existing .jmx plans, team already uses it |
jmeter -n -t plan.jmx |
| Locust | Python shops, complex user behavior modeling | locust -f locustfile.py --headless |
What ships with it
2 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.
- 19d ago Changed 9be18dec704c
- 22d ago Changed ed00ba43700b
- 29d ago First seen · 200 lines · 151 tokens per session scan A 55d6c2f3aa5c
ai-stress-test is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 151 tokens to every session and 1,824 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-17.
Other skills, from other repositories
702-technologies-wiremock
Use when you need framework-agnostic WireMock guidance — stub design, JSON or programmatic mappings, precise request matching, response bodies and faults, classpath fixtures, isolation and reset between tests, verification of calls, dynamic ports and base URLs, and avoiding flaky stubs — without choosing Spring Boot…
054-design-tdd
Use when Java implementation work should be guided by Test-Driven Development, including maintaining a test list, choosing the next behavior, writing a failing test first, implementing only enough production code to pass, and refactoring while keeping tests green. This should trigger for requests such as Apply TDD…
generate-microcks-openapi-samples
Use when creating OpenAPI mock examples for Microcks, setting up request/response routing with dispatchers, or mapping request fields to mock responses.
131-java-testing-unit-testing
Use when you need to review, improve, or write Java unit tests — including migrating from JUnit 4 to JUnit 5, adopting AssertJ for fluent assertions, structuring tests with Given-When-Then, ensuring test independence, applying parameterized tests, mocking dependencies with Mockito, verifying boundary conditions…
132-java-testing-integration-testing
Use when you need to set up, review, or improve Java integration tests — including generating a BaseIntegrationTest.java with WireMock for HTTP stubs, detecting HTTP client infrastructure from import signals, injecting service coordinates dynamically via System.setProperty(), creating WireMock JSON mapping files with…
321-frameworks-spring-boot-testing-unit-tests
Use when you need to write unit tests for Spring Boot applications — including pure unit tests with @ExtendWith(MockitoExtension.class) for @Service/@Component, slice tests with @WebMvcTest and @MockitoBean for controllers, @JsonTest for JSON serialization, parameterized tests with @CsvSource/@MethodSource, test…