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.
git clone --depth 1 https://github.com/christopherlouet/claude-baseWrote 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/commands/christopherlouet/claude-base/ops-load-testing)<a href="https://agentmods.dev/commands/christopherlouet/claude-base/ops-load-testing"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/ops-load-testing/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/commands/christopherlouet/claude-base/ops-load-testing"><img src="https://agentmods.dev/badge/commands/christopherlouet/claude-base/ops-load-testing.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 | $0.00000 | $0.00476 |
| Opus 5.5 | $0.00000 | $0.00190 |
| Sonnet 5.5 | $0.00000 | $0.00095 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
ops-load-testing 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 11d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OPS-LOAD-TESTING Agent
Set up and run load and stress tests.
Request context
$ARGUMENTS
Objective
Validate the application's performance and resilience under load, identify limits and bottlenecks.
Workflow
- Identify the type of test (load, stress, spike, soak, breakpoint)
- Choose the right tool (k6 recommended, Locust, Artillery, JMeter)
- Write test scripts with realistic scenarios
- Define acceptable performance thresholds (p95, p99, error rate)
- Run the tests on an isolated environment with active monitoring
- Analyze the results and identify bottlenecks
- Integrate into CI/CD if relevant
Expected output
- Test scripts: load-test.js, stress-test.js, scenario-test.js
- Report: p95/p99 latency, error rate, throughput, bottlenecks
- Prioritized optimization recommendations
- CI/CD integration if applicable
Related agents
| Agent | Usage |
|---|---|
/qa:qa-perf |
Performance optimization |
/ops:ops-monitoring |
Monitoring in production |
/ops:ops-cost |
Optimize cloud costs (FinOps) |
IMPORTANT: Always test on an isolated environment, never in production.
YOU MUST define acceptable performance thresholds before the tests.
NEVER run load tests without active monitoring.
Think hard about realistic scenarios before creating the tests.
See also
For k6, Grafana's own skills — grafana/skills skills/grafana-k6/* (Apache-2.0, pin 1ccacf29, already the ops-monitoring vendor) — go far deeper: script authoring, maintenance, trend analysis, cloud runs. The k6 skill validates every script it writes by running it — a full k6 run for named executors, otherwise one VU and one iteration — against the target in the script, and nothing in it gates on authorisation (k6-perf-test-website asks whether you own the backend but does not stop when you do not). The rule above still applies: an isolated environment, never production, only systems you own or are authorised to test.
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.
- 11d ago Changed · +4 lines 0763782676a2
- 1mo ago First seen · 47 lines · 0 tokens per session scan A a7f8b85f1c30
ops-load-testing is a command published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 476 tokens. 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 2026-09-03.
Other commands, from other repositories
test-plan
Generate a test strategy document — test matrix, coverage goals, and test pyramid allocation for the current project.
deps-update
Audit and update dependencies safely.
test-suite
Run comprehensive test suite with coverage analysis.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
auto-claude
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
health-check
Perform a comprehensive, read-only end-to-end review of any portfolio app across three layers — Frontend (E2E), Database integrity, and Audit Log & User Activity — and produce a structured, observations-only report. Optionally, on explicit opt-in, generate (never apply) the infrastructure provisions needed so future…