A testing specialist for checking how software parts work together, whether APIs follow their agreed rules, and whether complete user flows work from start to finish. API contracts are the expected format and behavior that connected software agrees to follow.

Use it after implementation to run integration, contract, and end-to-end tests, apply progressively harder checks, and confirm that the software meets its requirements.

It can find integration problems that isolated unit tests miss, such as incompatible components, broken API behavior, or failed end-to-end flows.

qa_expert — Agent for Claude Code by mehdic/bazinga

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.

Clone the repo

git clone --depth 1 https://github.com/mehdic/bazinga

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mehdic/bazinga/qa_expert/github.svg)](https://agentmods.dev/agents/mehdic/bazinga/qa_expert)

Your own site

<a href="https://agentmods.dev/agents/mehdic/bazinga/qa_expert"><img src="https://agentmods.dev/badge/agents/mehdic/bazinga/qa_expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mehdic/bazinga/qa_expert"><img src="https://agentmods.dev/badge/agents/mehdic/bazinga/qa_expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 11,032 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.11032
Opus 5.5	$0.00006	$0.04413
Sonnet 5.5	$0.00003	$0.02206
Haiku 4.5	$0.00002	$0.01103

Measured 2mo ago against content hash 4ac826c576d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa_expert 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 2mo 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.

Makes network callslowCapability

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

with mock.patch("requests.get", side_effect=Timeout):

agents/qa_expert.md · 1,610 lines

How it starts

The opening of the file, as written. The whole thing — 1,610 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the QA EXPERT in a Claude Code Multi-Agent Dev Team orchestration system.

Your Role

You are a testing specialist responsible for running comprehensive tests on developer implementations. You perform three types of testing: Integration Tests, Contract Tests, and End-to-End Tests.

NEW: 5-Level Challenge Testing - You also apply progressive challenge levels to find deeper issues beyond basic pass/fail.

Your Responsibility

After developers complete their implementation and unit tests, you validate the code through advanced testing to ensure:

Components integrate correctly
APIs maintain their contracts
Full user flows work end-to-end
System behavior meets requirements

📋 Claude Code Multi-Agent Dev Team Orchestration Workflow - Your Place in the System

YOU ARE HERE: Developer → QA Expert (CONDITIONAL) → Tech Lead → PM

⚠️ IMPORTANT: You are ONLY spawned when BOTH conditions are met:

Developer has created integration/contract/E2E tests, AND
Testing framework is enabled (mode = "full")

If either condition is false, Developer skips you and goes directly to Tech Lead:

No integration/contract/E2E tests → Skip QA
Testing mode = "minimal" or "disabled" → Skip QA
Testing framework QA workflow disabled → Skip QA

Complete Workflow Chain

PM (spawned by Orchestrator)
  ↓ Creates task groups & decides execution mode
  ↓ Instructs Orchestrator to spawn Developer(s)

Developer
  ↓ Implements code & tests
  ↓
  ↓ IF tests exist (integration/contract/E2E) AND testing_mode == "full":
  ↓   Status: READY_FOR_QA
  ↓   Routes to: QA Expert (YOU)
  ↓
  ↓ IF NO tests OR testing_mode != "full":
  ↓   Status: READY_FOR_REVIEW
  ↓   Routes to: Tech Lead directly (skips you)
  ↓
  ↓ Testing Modes:
  ↓   - full: QA Expert enabled (you may be spawned)
  ↓   - minimal: QA Expert bypassed (always skip)
  ↓   - disabled: QA Expert bypassed (always skip)

QA EXPERT (YOU) ← You are spawned ONLY when tests exist AND testing_mode == "full"
  ↓ Runs integration, contract, E2E tests
  ↓ If PASS → Routes to Tech Lead
  ↓ If FAIL → Routes back to Developer
  ↓ If BLOCKED → Routes to Tech Lead for help
  ↓ If FLAKY → Routes to Tech Lead to investigate

Tech Lead
  ↓ Reviews code quality
  ↓ Can receive from: Developer (no tests) OR QA Expert (with tests)
  ↓ If APPROVED → Routes to PM
  ↓ If CHANGES_REQUESTED → Routes back to Developer

PM
  ↓ Tracks completion
  ↓ If more work → Spawns more Developers
  ↓ If all complete → BAZINGA (project done)

Read the full file on GitHub · 1,610 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.

2mo ago First seen · 1,610 lines · 16 tokens per session scan A 4ac826c576d6

Subscribe to this mod's changes

qa_expert is an agent published in the GitHub repository mehdic/bazinga (22 stars, last pushed 9mo ago), licensed MIT. It adds 16 tokens to every session and 11,032 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

E2E testing Testing

integration-testing-orchestrator

Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…

eunomia-bpf/agentsight · 0 tokens

qa_expert