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.
git clone --depth 1 https://github.com/redker56/auto-harnessWrote 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.
[](https://agentmods.dev/agents/redker56/auto-harness/evaluator-write-retest-agent)<a href="https://agentmods.dev/agents/redker56/auto-harness/evaluator-write-retest-agent"><img src="https://agentmods.dev/badge/agents/redker56/auto-harness/evaluator-write-retest-agent/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.
<a href="https://agentmods.dev/agents/redker56/auto-harness/evaluator-write-retest-agent"><img src="https://agentmods.dev/badge/agents/redker56/auto-harness/evaluator-write-retest-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00033 | $0.00256 |
| Opus 5.5 | $0.00013 | $0.00102 |
| Sonnet 5.5 | $0.00007 | $0.00051 |
| Haiku 4.5 | $0.00003 | $0.00026 |
Grade A, and why
evaluator-write-retest-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 1mo 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.
What it actually says
You are the action-specific Evaluator Write Retest subagent for Auto-Harness.
You run in a fresh, isolated subagent context. Your single source of behavioral truth is the preloaded evaluator-write-retest skill.
Runtime Contract
- Read the current
.harness/state from the project through the preloaded skill. - Retest the named fixes against the running app like a real user and write only the current sprint retest report.
- If the target is a web application, use Playwright MCP to drive the real UI while verifying each named fix.
- Do not modify application source code.
- Do not spawn other subagents.
- Treat the project
.harness/files as the durable state source of truth. - Read and follow the rubric files bundled with the preloaded skill while judging retest outcomes.
- Carry forward unresolved bugs honestly based on evidence.
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.
- 1mo ago First seen · 24 lines · 33 tokens per session scan A d1abb5c92b03
evaluator-write-retest-agent is an agent published in the GitHub repository redker56/auto-harness (15 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 256 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
coverage-analyst
Test coverage analysis expert. Comprehensively evaluates Unit / Integration / E2E three-layer test coverage, identifies gaps, and provides remediation suggestions.
qa-executor
Run an approved QA test plan against a built harness, assert every observation point, produce a report with per-scenario evidence, and emit bug candidates. Never edits test or product code to make a run pass.
verify-app
Verification expert. Proactively runs tests after code changes, analyzes failures, and suggests fixes.
qa-engineer
Automated testing, E2E validation, and bug reproduction.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
playwright-explorer
Use when exploring websites, proving hypotheses about web application behavior, automating browser interactions, or generating E2E tests - investigates page structure through accessibility snapshots, tests assumptions systematically, and coordinates Playwright MCP tools with tenacity to complete complex multi-step…