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 makifbaysal/tasktrooper --skill performance-smoke-testinggit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/performance-smoke-testing)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/performance-smoke-testing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/performance-smoke-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/makifbaysal/tasktrooper/performance-smoke-testing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/performance-smoke-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 | $0.00049 | $0.00545 |
| Opus 5.5 | $0.00020 | $0.00218 |
| Sonnet 5.5 | $0.00010 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
performance-smoke-testing scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
for i in $(seq 20); do curl -s -o /dev/null -w '%{time_total}\n' "$BASE/api/tasks?limit=50"; done | sort -n | awk '{a[NR]=$1} END{print "p50="a[int(NR*.5)]" p95="a[int(NR*.95)]" max="a[NR]}' What it actually says
Performance Smoke Testing
Not full load testing — a smoke check run locally, never against stage or prod.
API
for i in $(seq 20); do curl -s -o /dev/null -w '%{time_total}\n' "$BASE/api/tasks?limit=50"; done | sort -n | awk '{a[NR]=$1} END{print "p50="a[int(NR*.5)]" p95="a[int(NR*.95)]" max="a[NR]}'
Then run the same with 10x the seeded rows. p95 growing more than 3x for 10x the data is an N+1 suspicion — report it with the two numbers. Fail bar: p95 >1s for a simple read on localhost, or any number a criterion states explicitly. 0.5-1s is a note, not a fail.
Concurrency smoke
Only when the change implies it (a shared resource, a write path under contention):
npx -y autocannon -c 10 -d 10 <url>
Errors must be 0.
Web
Measure a production build, never a dev server — dev builds are unoptimized and that is where false fails come from:
npm run build && (nohup npx vite preview --port 4173 > "$QA/preview.log" 2>&1 &)
CHROME_PATH="$CHROME_BIN" npx -y lighthouse@13 http://localhost:4173/<page> --only-categories=performance --form-factor=mobile --screenEmulation.width=360 --chrome-flags="--headless=new" --output=json --output-path="$QA/lh-perf.json"
Report LCP/CLS/TBT against "good": LCP ≤2.5s, CLS ≤0.1, TBT ≤200ms. Fail only for a criterion's own number or a CLS shift you can see on a changed screen; other misses are notes, not fails.
Never
Load-test stage or prod. Use k6 only when the repo already ships k6 scripts — not as the default tool.
Recording
Record cases as category: other with a title prefix perf: — the category enum has no performance value of its own.
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.
- 8d ago First seen · 46 lines · 49 tokens per session scan A d7e77069f22c
performance-smoke-testing is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 545 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other skills, from other repositories
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
nemo-automodel-model-onboarding
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
amc-run-sample-calibration
Run end-to-end calibration on the shipped sample dataset (sdg082sampledata010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
mcore-testing
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
i4h-catheter-navigation-e2e
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.