evaluator-write-qa-parallel-agent

evaluator-write-qa-parallel-agent is an agent for coding agents from redker56/auto-harness. It costs 36 tokens per session (257 once invoked), scanned A, original, MIT.

A specialized QA worker for parallel Auto-Harness sprints. It exercises the running app like a user, inspects named project artifacts, and writes the current sprint's QA report.

In plain words
What is it for?
Use it to test the current parallel sprint, inspect its artifacts, and record a pass-or-fail report without changing application source code.
Why use it?
It provides an evidence-based check of parallel work and separates testing from implementation.

Agent

Part of the auto-harness plugin — 20 skills, 8 commands, 26 agents, 5 hooks, 1 MCP server 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/redker56/auto-harness/evaluator-write-qa-parallel-agent
Clone the repo
git clone --depth 1 https://github.com/redker56/auto-harness

Or install auto-harness, the plugin that ships this one along with the rest of its 20 skills, 8 commands, 26 agents, 5 hooks, 1 MCP server.

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 evaluator-write-qa-parallel-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/redker56/auto-harness/evaluator-write-qa-parallel-agent.svg)](https://agentmods.dev/agents/redker56/auto-harness/evaluator-write-qa-parallel-agent)
Your own site
<a href="https://agentmods.dev/agents/redker56/auto-harness/evaluator-write-qa-parallel-agent"><img src="https://agentmods.dev/badge/agents/redker56/auto-harness/evaluator-write-qa-parallel-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 257 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 $0.00036 $0.00257
Opus 5 $0.00018 $0.00129
Sonnet 5 $0.00007 $0.00051
Haiku 4.5 $0.00004 $0.00026

Measured 4d ago against content hash 8aa4be932f25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluator-write-qa-parallel-agent 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 4d 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.

agents/evaluator-write-qa-parallel-agent.md · 23 lines

What it actually says

You are the action-specific Parallel Evaluator Write QA subagent for Auto-Harness.

You run in a fresh, isolated subagent context. Your single source of behavioral truth is the preloaded evaluator-write-qa-parallel skill.

Runtime Contract

  • Read the current .harness-parallel/ state from the project through the preloaded skill.
  • Exercise the running app like a real user, inspect named artifacts, and write only the current sprint QA report.
  • If the target is a web application, use Playwright MCP to drive the real UI before issuing PASS or FAIL.
  • Do not modify application source code.
  • Do not spawn other subagents.
  • Treat the project .harness-parallel/ files as the durable state source of truth.
  • Score against evidence plus the rubric files bundled with the preloaded skill, not Generator intent.
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. 4d ago First seen · 23 lines · 36 tokens per session scan A 8aa4be932f25

Subscribe to this mod's changes

evaluator-write-qa-parallel-agent is an agent published in the GitHub repository redker56/auto-harness (14 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 257 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 2026-08-30.