qa-test

qa-test is a skill for Claude Code from piti6/SpikeTrap. It costs 44 tokens per session (5,855 once invoked), scanned A, original, MIT.

A comprehensive quality-assurance test suite for SpikeTrap, a C# tool that measures performance problems in a game or application. It tests its programming interface, data collection, filtering, reload behavior, edge cases, and user interface.

In plain words
What is it for?
Use it after code changes or before release to run the full test suite, API-only checks, or an individual test group.
Why use it?
It checks the feature against known performance events and expected thresholds, helping find regressions before release.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Install

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.

agentmods
npx agentmods add skills/piti6/spiketrap/qa-test
Any agent
npx skills add piti6/SpikeTrap --skill qa-test
Clone the repo
git clone --depth 1 https://github.com/piti6/SpikeTrap

Made for: Claude Code.

Wrote 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.

agentmods badge for qa-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/piti6/spiketrap/qa-test.svg)](https://agentmods.dev/skills/piti6/spiketrap/qa-test)
Your own site
<a href="https://agentmods.dev/skills/piti6/spiketrap/qa-test"><img src="https://agentmods.dev/badge/skills/piti6/spiketrap/qa-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.05855
Opus 5 $0.00022 $0.02927
Sonnet 5 $0.00009 $0.01171
Haiku 4.5 $0.00004 $0.00585

Measured 6d ago against content hash 1bcfb34eabf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa-test 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.

Packages/com.piti6.spike-trap/.claude/skills/qa-test/SKILL.md · 711 lines

How it starts

The opening of the file, as written. The whole thing — 711 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpikeTrap QA Test Suite

Comprehensive, reproducible QA test covering all SpikeTrap specifications. $ARGUMENTS

All C# code runs via mcp__uLoopMCP__execute-dynamic-code. Report each test as PASS/FAIL with details.

Test Environment

  • Stress test scene: ProfilerStressTest.cs generates known markers at these rates:
    • HeavyComputation — 5% chance per frame, ~500K sqrt iterations (~15-50ms spike)
    • GarbageBlast — 8% chance per frame, 64KB allocation
    • NetworkSync — 10% chance per frame, ~50K sin iterations
    • SaveCheckpoint — 6% chance per frame, 32KB write
  • Target frame rate: 30fps (set by stress test)
  • Standard test thresholds: spike=5ms, GC=32KB, duration=5s

Modes

Choose based on user request:

  • full (default): Run all test suites including play mode tests. Requires Profiler window open with SpikeTrap module.
  • api-only: Run only API contract and analysis tests on cached/loaded data. No play mode needed.
  • suite N: Run only suite N (e.g., "suite 3" runs only Collect Lifecycle).

If user says "test" or "QA" without specifying, run full.

Execution Rules

  1. Run each test in order — some suites depend on prior suite state.
  2. Report results as they complete, do NOT batch.
  3. On FAIL, log details but continue to next test (do not abort suite).
  4. At the end, print a summary table: suite name, pass count, fail count.
  5. If a test needs play mode and game is not running, enter play mode first.
  6. Always clean up: stop collecting, stop play mode when done.

Suite 1: Prerequisites

T1.1 — Compile Check

Use mcp__uLoopMCP__compile to verify 0 errors.

PASS: 0 compile errors. FAIL: any error.

T1.2 — View Active (auto-setup if needed)

First, unconditionally open the Profiler window via mcp__uLoopMCP__execute-menu-item with MenuItemPath="Window/Analysis/Profiler". This is idempotent — if the window is already open it just focuses it. Wait ~2 seconds for it to initialize.

Then check:

Read the full file on GitHub · 711 lines

Changes

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.

  1. 6d ago First seen · 711 lines · 44 tokens per session scan A 1bcfb34eabf4

Subscribe to this mod's changes

qa-test is a skill published in the GitHub repository piti6/SpikeTrap (22 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 5,855 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 2026-08-30.

Related

Other skills, from other repositories

profiling

Diagnose frame-rate bottlenecks (CPU vs GPU bound FIRST), control Unreal Insights traces, sample live frame times, and annotate performance captures. Use when FPS is low/bad, the game is slow, or you need to find what is limiting the frame rate.

kevinpbuckley/VibeUE · 57 tokens

performance-analysis

Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.

ruvnet/ruflo · 20 tokens

performance

Use when a page or interaction is slow for one user and the fix starts from a measurement — a failing Core Web Vital (LCP, INP, CLS), a heavy JS bundle, wasted re-renders, an over-broad client boundary: profile, attribute the cost to one phase, fix it, re-measure. NOT surviving concurrent load (that is scaling), NOT…

ericrisco/rsc-harness · 91 tokens

tune-performance

Use when the user reports the game is slow, drops framerate, stutters, takes forever to start, or runs poorly on specific hardware. Profiles the running game via summergetdiagnostics, identifies hotspots (rendering / physics / scripting), and proposes specific fixes with before/after metric expectations. Trigger on…

SummerEngine/summer-engine-agent · 94 tokens

performance-expert

Expert-level performance optimization, profiling, benchmarking, and tuning. Use when the user mentions optimization, profiling, benchmarking, or scalability, or when the task involves Performance Fundamentals, Optimization Areas, Profiling Tools, or General.

personamanagmentlayer/pcl · 48 tokens

performance-optimization

Use when performance requirements exist, profiling reveals bottlenecks, or Core Web Vitals need improvement. Do NOT use without evidence — premature optimization adds complexity.

juanmhidalgo/claude-plugins · 35 tokens