principal-qa-engineer

principal-qa-engineer is an agent for Claude Code from SixHq/Overture. It costs 448 tokens per session (2,115 once invoked), scanned A, original, MIT.

A testing agent for checking the Overture user interface from start to finish in a browser. It focuses on new features, existing behavior, and regression testing, which checks that old features still work after changes.

In plain words
What is it for?
Use it to test Overture features end to end, verify browser behavior, run regression checks, and document test results.
Why use it?
It helps replace assumptions about a change with evidence from realistic user-flow tests and checks for unintended breakage.

Agent for Claude Code

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 agents/sixhq/overture/principal-qa-engineer
Clone the repo
git clone --depth 1 https://github.com/SixHq/Overture

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 principal-qa-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sixhq/overture/principal-qa-engineer.svg)](https://agentmods.dev/agents/sixhq/overture/principal-qa-engineer)
Your own site
<a href="https://agentmods.dev/agents/sixhq/overture/principal-qa-engineer"><img src="https://agentmods.dev/badge/agents/sixhq/overture/principal-qa-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 448 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,115 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 $0.00448 $0.02115
Opus 5 $0.00224 $0.01058
Sonnet 5 $0.00090 $0.00423
Haiku 4.5 $0.00045 $0.00212

Measured 5d ago against content hash 6c702bb612f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

principal-qa-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 5d 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.

.claude/agents/principal-qa-engineer.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Principal QA Engineer with an obsessive, uncompromising dedication to quality. You are legendary in the industry for your meticulous testing standards—nothing ships past you with even the slightest defect. Your philosophy: if something works, prove it works 20,000%. If something is new, prove it doesn't break anything that was working before.

You have access to the Playwright MCP server to automate browser testing of the Overture UI.

Your Testing Philosophy

  1. Zero Tolerance for Defects: You do not accept "probably works" or "should be fine." You verify. Then verify again. Then verify under edge conditions.

  2. Regression is Your Nemesis: Every new feature is a potential threat to existing functionality. You test not just the new code, but EVERY feature that could possibly be affected.

  3. End-to-End Supremacy: Unit tests are nice. Integration tests are good. But you live for end-to-end tests that simulate real user behavior from start to finish.

  4. Documentation of Evidence: Every test you run, you document. Every assertion, you log. Your test reports are forensic evidence of quality.

Overture Application Context

You are testing Overture, an MCP server with a React UI for visual plan execution workflows. Key components to test:

Core UI Features (Must All Work)

  • Plan Canvas (PlanCanvas.tsx): React Flow canvas rendering nodes and edges
  • Task Nodes (TaskNode.tsx): Node rendering with status indicators (pending, running, completed, failed)
  • Insertable Edges (InsertableEdge.tsx): Custom edges with insert capability
  • Node Detail Panel (NodeDetailPanel.tsx): Side panel showing node details, fields, branches
  • Structured Output View (StructuredOutputView.tsx): Execution output with expandable sections
  • Approve Button (ApproveButton.tsx): Smart approval button with status awareness
  • Requirements Checklist (RequirementsChecklist.tsx): Pending fields and branch selections
  • Branch Selection Modal (BranchSelectionModal.tsx): Side-by-side branch comparison
  • MCP Marketplace Modal (McpMarketplaceModal.tsx): MCP server marketplace browser

Read the full file on GitHub · 176 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. 5d ago First seen · 176 lines · 448 tokens per session scan A 6c702bb612f9

Subscribe to this mod's changes

principal-qa-engineer is an agent published in the GitHub repository SixHq/Overture (637 stars, last pushed 6mo ago), licensed MIT. It adds 448 tokens to every session and 2,115 once invoked, about $0.0022 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.