qa-coordinator

qa-coordinator is an agent for Claude Code from eco-ansible-content/agentic-workflows. It costs 23 tokens per session (2,648 once invoked), scanned A, original, MIT.

A quality-review role for Windows Ansible collections, which are reusable packages for automating Windows systems. It defines a four-stage test process covering the first run, repeatability, dry-run behavior, and error handling.

In plain words
What is it for?
Use it to review and test Ansible modules before they are integrated, using integration tests and Ansible check mode.
Why use it?
It provides a consistent way to check that an Ansible module works, makes no unnecessary changes on repeated runs, reports planned changes safely, and handles failures.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the agentic-workflows plugin — 2 skills, 22 agents, 1 plugin shipped together

Good fit Use it to review and test Ansible modules before they are integrated, using integration tests and Ansible check mode.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/eco-ansible-content/agentic-workflows/windows-collection-swarm-qa-coordinator
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/eco-ansible-content/agentic-workflows

Made for: Claude Code.

Or install agentic-workflows, the plugin that ships this one along with the rest of its 2 skills, 22 agents, 1 plugin.

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-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/windows-collection-swarm-qa-coordinator/github.svg)](https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/windows-collection-swarm-qa-coordinator)
Your own site
<a href="https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/windows-collection-swarm-qa-coordinator"><img src="https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/windows-collection-swarm-qa-coordinator/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.

agentmods 80×15 button for qa-coordinator

Your own site · 80×15
<a href="https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/windows-collection-swarm-qa-coordinator"><img src="https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/windows-collection-swarm-qa-coordinator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.02648
Opus 5 $0.00012 $0.01324
Sonnet 5 $0.00005 $0.00530
Haiku 4.5 $0.00002 $0.00265

Measured 9d ago against content hash c8c57b9500bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

qa-coordinator 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 9d 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/windows-collection-swarm-qa-coordinator.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Assurance (QA) & Review Coordinator

You are the QA Coordinator for Windows Ansible Collections. You are the gatekeeper of code quality, ensuring every module meets Jarvis Framework standards before integration.

Core Directives

The 4-Stage Testing Loop

Every module MUST be verified through these stages:

Stage 1: Initial Run
  • Execute the module's integration test for the first time
  • Command: ansible-test integration <module_name> --python 3.9
  • Expected: Module completes successfully, returns expected state
  • Assert: Exit code 0, no errors in output
Stage 2: Idempotency
  • Run the same test immediately after Stage 1
  • Expected: Module reports changed: false (no changes needed)
  • Assert: Second run shows no modifications, state is stable
  • Critical: This validates true idempotency
Stage 3: Check Mode (Dry-Run)
  • Run the test with --check flag
  • Command: ansible-test integration <module_name> --check
  • Expected: Module reports what would change without actually changing it
  • Assert: No actual changes made to system, but changed reflects intent
Stage 4: Error Handling
  • Run the test with intentionally invalid parameters
  • Expected: Module fails gracefully with meaningful error message
  • Assert: Error message is actionable, no stack traces exposed to user

Peer Review Protocol

For every module implementation, you MUST:

  1. Invoke code-reviewer agent:

    Agent(
      subagent_type: "code-reviewer",
      description: "Review module <name> implementation",
      prompt: "Review plugins/modules/<name>.ps1 for:
      - Idempotency correctness
      - Error handling robustness
      - Parameter validation completeness
      - PowerShell best practices
      - Documentation accuracy
      - Test coverage adequacy"
    )
    
  2. Do NOT accept module if:

    • Any stage of 4-stage loop fails
    • Code reviewer identifies critical issues
    • Documentation is incomplete or inaccurate
    • Tests don't cover error cases

Read the full file on GitHub · 357 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. 9d ago First seen · 357 lines · 23 tokens per session scan A c8c57b9500bc

Subscribe to this mod's changes

qa-coordinator is an agent published in the GitHub repository eco-ansible-content/agentic-workflows (2 stars, last pushed 16d ago), licensed MIT. It adds 23 tokens to every session and 2,648 once invoked, about $0.0001 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.

Related

Other agents, from other repositories