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 joao-aires/agent-skills-public --skill performance-testinggit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/performance-testing)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/performance-testing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/performance-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/skills/joao-aires/agent-skills-public/performance-testing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/performance-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 | $0.00059 | $0.01480 |
| Opus 5.5 | $0.00024 | $0.00592 |
| Sonnet 5.5 | $0.00012 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
performance-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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test application performance
Use local k6 execution by default; no Grafana Cloud account, MCP or distributed operator is required. Keep scripts and useful workload fixtures within the target application's tests, following its layout. Add actual CI workflows there when delivery work is in scope, rather than introducing a plugin-owned pipeline framework. Preserve a suitable existing performance suite unless replacement is requested.
Define the claim and workload
Read critical journeys, architecture, accepted targets and operating constraints.
- Use installed journey and actual-platform verification expertise for workload/evidence methods when useful; retain an explicit demand, outcome and execution boundary without it.
- Use reliability expertise, capacity and demand-modeling expertise and observability expertise when available for outcome contracts, demand and trustworthy signals.
- Choose representative authenticated reads/writes, data volumes, cache conditions and traffic mix; avoid measuring only an unauthenticated health endpoint.
- For async work, distinguish admission from completion and track accepted jobs that miss their deadline.
- HTTP duration alone does not establish user-journey latency or browser rendering performance; retain Playwright for browser correctness and use browser-performance evidence when that is the claim.
Record intended arrival rate or concurrency, duration, warmup, thresholds, target and resources. Derive acceptance from user needs or an accepted comparable baseline. Label provisional values and seek unresolved product decisions; do not invent production commitments. Keep a short low-load smoke profile for script correctness, a bounded regression/load profile and longer stress/spike/soak profiles only when justified. A short smoke pass is not a capacity result.
Implement meaningful k6 scenarios
| Workload model | Executor choice and interpretation |
|---|---|
| Fixed concurrent population | Virtual-user executors. In a closed model, slower responses can reduce offered traffic; account for that when interpreting overload. |
| Independent incoming demand | Arrival-rate executors. |
What ships with it
1 file 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.
- yesterday Changed · +28 lines 52c3b88e262d
- 2d ago Changed cdbfa2bc48a7
- 7d ago First seen · 58 lines · 59 tokens per session scan A aa441d14b789
performance-testing is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,480 once invoked, about $0.0002 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 2026-10-15.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.