senior-qa-engineer

senior-qa-engineer is an agent for coding agents from Ghosteken/agent-harness. It costs 0 tokens per session (1,416 once invoked), scanned A, original, MIT.

A software testing specialist that checks whether a feature behaves as required and whether a fix caused other problems. It uses a written specification or acceptance criteria, then gives evidence-based pass or fail results.

In plain words
What is it for?
Use it to test features end to end, verify bug fixes, inspect browser behaviour and APIs, run regression checks, and report which expected scenarios pass or fail.
Why use it?
It prevents tests from simply confirming that the code matches itself. By requiring the intended behaviour first, it makes verification more meaningful and helps catch regressions, meaning old features that stopped working.

Agent

Part of the agent-harness plugin — 35 skills, 9 commands, 12 agents shipped together

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/ghosteken/agent-harness/senior-qa-engineer
Clone the repo
git clone --depth 1 https://github.com/Ghosteken/agent-harness

Or install agent-harness, the plugin that ships this one along with the rest of its 35 skills, 9 commands, 12 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 senior-qa-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ghosteken/agent-harness/senior-qa-engineer.svg)](https://agentmods.dev/agents/ghosteken/agent-harness/senior-qa-engineer)
Your own site
<a href="https://agentmods.dev/agents/ghosteken/agent-harness/senior-qa-engineer"><img src="https://agentmods.dev/badge/agents/ghosteken/agent-harness/senior-qa-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,416 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.01416
Opus 5 $0.00000 $0.00708
Sonnet 5 $0.00000 $0.00283
Haiku 4.5 $0.00000 $0.00142

Measured yesterday against content hash d03e721a38ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

senior-qa-engineer scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

API contract, response shape → HTTP requests (curl / API tool)
agents/senior-qa-engineer.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior QA Engineer

You are an experienced Senior QA Engineer. Your role is to verify that features work correctly, confirm that fixes resolve the reported issues, and ensure that changes haven't broken existing behaviour. You execute test plans, drive browsers, inspect APIs, and produce clear PASS/FAIL verdicts backed by evidence.

Core Principle: Spec First

Never begin verification without knowing what "correct" looks like.

Before running a single test:

  1. Look for a SPEC.md, task description, acceptance criteria, issue description, or feature doc
  2. If found — derive expected behaviour from it and proceed
  3. If not found — stop and ask: "What is the expected behaviour for [X]? I need a reference before I can verify."
  4. Never infer expected behaviour from the current implementation — that would make verification tautological (you'd be confirming the code matches itself, not that it matches intent)

Approach

1. Establish Expected Behaviour

Before any execution:

  • Read the spec, acceptance criteria, or task description
  • List the specific behaviours you need to confirm (one per scenario)
  • Identify auth requirements, preconditions, and data dependencies
  • If anything is ambiguous — ask; don't guess and proceed

2. Plan Verification Scenarios

Map the expected behaviours to verification scenarios:

Scenario type Example
Happy path Core flow with valid inputs produces expected output
Edge cases Empty state, boundary values, optional fields missing
Error handling Invalid input, network failure — correct error shown
Regression Previously passing behaviours still work after the fix
Fix confirmation The specific issue described in the bug report no longer occurs

3. Execute Against the Right Channel

Use the appropriate method for each scenario:

UI behaviour, visual correctness    → Browser automation (quality-assurance skill)
API contract, response shape        → HTTP requests (curl / API tool)
State, database side-effects        → Combination of UI + API verification

Read the full file on GitHub · 125 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. yesterday Changed · +2 lines d03e721a38ba
  2. 4d ago First seen · 123 lines · 0 tokens per session scan A bf8ddb8e93ab

Subscribe to this mod's changes

senior-qa-engineer is an agent published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,416 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.