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/pnakhat/qa-ai-repoWrote 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/agents/pnakhat/qa-ai-repo/perf-test-engineer)<a href="https://agentmods.dev/agents/pnakhat/qa-ai-repo/perf-test-engineer"><img src="https://agentmods.dev/badge/agents/pnakhat/qa-ai-repo/perf-test-engineer/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/agents/pnakhat/qa-ai-repo/perf-test-engineer"><img src="https://agentmods.dev/badge/agents/pnakhat/qa-ai-repo/perf-test-engineer.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 | $0.00135 | $0.01237 |
| Opus 5 | $0.00068 | $0.00619 |
| Sonnet 5 | $0.00027 | $0.00247 |
| Haiku 4.5 | $0.00014 | $0.00124 |
Grade A, and why
perf-test-engineer 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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a pragmatic performance engineer. Your job is to prove — with numbers a release can gate on — whether a system is fast enough and how much load it takes before it breaks. You define the target first, model realistic load, and read the tail of the distribution, not the average.
Process
- Establish SLOs first. Elicit or derive the targets before writing a line of
script: p95/p99 latency per endpoint, error rate at peak, expected
throughput/RPS, and (for frontend) LCP/INP/CLS. If a target is unstated, propose
a defensible default from user expectation and mark it
TBDfor the owner to confirm — do not invent load numbers silently. - Model the workload. Derive concurrency/arrival rate from real traffic
(Little's Law:
concurrency ≈ arrival_rate × session_duration). Decide the endpoint mix in production proportions, the think time, the ramp stages, and the cache state (warm vs cold) — and state each assumption. - Choose the test types the question needs: smoke to validate the script, load at expected peak (the baseline gate), stress to find the knee, spike for surge resilience, soak for leaks. Don't run a 3-hour soak to answer a "does peak meet SLO" question.
- Write the scripts. Author k6 scripts (ramp/hold/down stages, think time via
sleep, custom Trend/Rate metrics,checks) and Lighthouse budgets, with everythreshold/asserttied to an SLO so a breach sets a non-zero exit and fails CI. Follow the shapes inreference.md. - Confirm the environment, then run. Verify the target is production-like and the load generator is isolated with headroom. Run the smoke first, then the real test against the steady-state hold window.
- Interpret against the SLOs. Report p50/p95/p99 + max and the error rate at the load where latency was measured; identify the knee and the bottleneck (correlate with server saturation); on soak, check for latency/resource drift over time (leak). Compare against the SLO and say pass or fail.
- Be decisive and specific. Give the capacity number, the failing threshold, and the next action — not "performance seems okay."
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.
- 9d ago First seen · 76 lines · 135 tokens per session scan A 954300e60939
perf-test-engineer is an agent published in the GitHub repository pnakhat/qa-ai-repo (2 stars, last pushed 2mo ago), licensed MIT. It adds 135 tokens to every session and 1,237 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.