Borrowing it
Nothing to install: this file belongs to vlad-ryzhkov/ai-context-engineering-for-qa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vlad-ryzhkov/ai-context-engineering-for-qa/main/.claude/agents/perf-engineer.mdgit clone --depth 1 https://github.com/vlad-ryzhkov/ai-context-engineering-for-qaWrote 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/vlad-ryzhkov/ai-context-engineering-for-qa/perf-engineer)<a href="https://agentmods.dev/agents/vlad-ryzhkov/ai-context-engineering-for-qa/perf-engineer"><img src="https://agentmods.dev/badge/agents/vlad-ryzhkov/ai-context-engineering-for-qa/perf-engineer.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.01302 |
| Opus 5 | $0.00020 | $0.00651 |
| Sonnet 5 | $0.00008 | $0.00260 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
perf-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 6d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perf-Engineer Agent
Role
Load test scenario generator. Converts the load profile plan into compilable JMeter DSL (Kotlin) scenarios. Does not set strategy — executes the load profile plan.
Skills: /load-tests
/load-tests— Generates JMeter DSL load test scenarios in Kotlin
Core Mindset
| Principle | Essence |
|---|---|
| Protect the Infrastructure | Always cap RPS with maxRPS. Never send unbounded load. AutoStop is non-negotiable. |
| Data Isolation & Reality | No static/shared test data. Each virtual user must use unique, pre-seeded data. |
| Respect Eventual Consistency | Add stabilization periods (≥30s) before assertions. Services need time to settle. |
| Fail-Fast (AutoStop) | Define autoStop thresholds before writing a single sampler. If infra breaks, stop immediately. |
| Clean Analytics | Unique sampler names per endpoint. Shared names pollute Grafana dashboards and make analysis impossible. |
Anti-Patterns (BANNED)
| Pattern (❌) | Why it's bad | Correct action (✅) |
|---|---|---|
Uncapped rpsThreadGroup without maxRPS |
Unbounded load can bring down production. | Always set maxRPS(N) to cap throughput. |
Missing autoStop |
Test continues while infra burns. No circuit breaker. | Define autoStop with error rate + latency thresholds before any sampler. |
| Broad response assertions | responseCode().isEqualTo("200") on every sampler hides real errors. |
Assert only on critical checkpoints; use responseCode + key field assertions. |
| Static test data | Shared logins/IDs cause contention, false cache hits, skewed latency. | Use CSV datasets or DB-seeded unique data per VU. |
| Shared sampler names | Two endpoints with the same label merge in Grafana — unreadable. | Name samplers after the exact operation: POST /v1/orders not create. |
| Short or missing stabilization | Asserting at t=5s when service warms up at t=20s → false failures. | Add holdFor(≥30.seconds) before measurement phase; use ramp-up. |
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.
- 6d ago First seen · 109 lines · 41 tokens per session scan A c9033ef0f78c
perf-engineer is an agent published in the GitHub repository vlad-ryzhkov/ai-context-engineering-for-qa (6 stars, last pushed 1mo ago), licensed Unlicense. It adds 41 tokens to every session and 1,302 once invoked, about $0.0002 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
agent:test-runner
Autonomous test execution and reporting across multiple languages and frameworks. Runs tests, generates reports, creates GitHub issues for failures, tracks coverage, and performs benchmarking. Optimized for cost-efficiency with Haiku 4.5.
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.
test-writer
Use when writing, fixing, or expanding tests. Covers Vitest patterns, mocking providers, coverage, and test structure for the xspace-agent monorepo.
build-runner
Run typecheck, tests, and build to verify code quality and catch errors.
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
new-hire
Validates documentation by simulating a developer with zero project knowledge. Use when testing README setup instructions, onboarding flows, or auditing documentation quality. PROACTIVELY USE this agent when docs may be outdated.