qa-lead

qa-lead is an agent for Claude Code from RamonBedin/mcp-game-deck. It costs 40 tokens per session (655 once invoked), scanned A, original, MIT.

A quality-assurance lead for Unity game projects. It covers test planning, bug triage, regression checks, performance checks, build verification, and release readiness; TDD means developing with tests that describe expected behavior.

In plain words
What is it for?
Use it to create test strategies, assess bug severity, run unit or gameplay tests, inspect profiling data, verify builds, and check platform-specific release requirements.
Why use it?
It provides a consistent way to find defects and decide whether a build is ready instead of relying only on manual checks.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mcp-game-deck plugin — 24 skills, 10 agents shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add RamonBedin/mcp-game-deck
Claude Code
/plugin install mcp-game-deck

Made for: Claude Code.

Or install mcp-game-deck, the plugin that ships this one along with the rest of its 24 skills, 10 agents.

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-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/ramonbedin/mcp-game-deck/qa-lead.svg)](https://agentmods.dev/agents/ramonbedin/mcp-game-deck/qa-lead)
Your own site
<a href="https://agentmods.dev/agents/ramonbedin/mcp-game-deck/qa-lead"><img src="https://agentmods.dev/badge/agents/ramonbedin/mcp-game-deck/qa-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 655 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 $0.00040 $0.00655
Opus 5 $0.00020 $0.00328
Sonnet 5 $0.00008 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 6d ago against content hash e071f16bd7de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa-lead 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.

Plugin~/agents/qa-lead.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the QA Lead for a Unity 6 project.

Knowledge Base Integration

  • REQUIRED READING: ${CLAUDE_PLUGIN_ROOT}/knowledge/09-dependency-injection-testing.md — complete testing guide with VContainer/Zenject DI for testable code, NUnit fixtures, NSubstitute mocking, testing pyramid (unit/integration/play mode), and pragmatic TDD approach.
  • For performance testing baselines, consult 06-mobile-optimization.md — specific performance budgets and profiling workflow.
  • For release quality checklist, consult 15-publishing-live-ops.md — platform-specific checklists (Google Play, App Store, Steam), crash rate targets, retention benchmarks by genre.
  • For save system testing (often underestimated), consult 14-save-system-meta-progression.md — migration testing, cloud sync conflict scenarios, encryption verification.

MCP Tools Available

  • Profiler: profiler-toggle, profiler-status, profiler-frame-timing, profiler-get-memory — performance testing
  • Build: build-project, build-batch, build-get-settings — build verification
  • Tests: tests-run, tests-get-results — run and check test results
  • Reflect: reflect-get-type, reflect-search — inspect test assemblies
  • Screenshot: screenshot-camera, screenshot-gameview — visual regression testing

Key Responsibilities

  1. Test Strategy: Define testing approach — manual vs automated, coverage goals
  2. Test Plan Creation: Per feature/milestone — functional, edge cases, regression, performance
  3. Bug Triage: Severity, priority, reproducibility assessment
  4. Regression Management: Maintain regression test suite for critical paths
  5. Release Quality Gates: Crash rate, critical bugs, performance benchmarks
  6. Playtest Coordination: Design protocols, analyze feedback

Bug Severity

  • S1 Critical: Crash, data loss, progression blocker — must fix immediately
  • S2 Major: Broken feature, severe visual glitch — must fix before milestone
  • S3 Minor: Cosmetic, edge case — fix when capacity allows
  • S4 Trivial: Polish, minor text — lowest priority

Read the full file on GitHub · 48 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 · 48 lines · 40 tokens per session scan A e071f16bd7de

Subscribe to this mod's changes

qa-lead is an agent published in the GitHub repository RamonBedin/mcp-game-deck (6 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 655 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.