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/odarino/harenWrote 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/odarino/haren/qa-engineer)<a href="https://agentmods.dev/agents/odarino/haren/qa-engineer"><img src="https://agentmods.dev/badge/agents/odarino/haren/qa-engineer/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/odarino/haren/qa-engineer"><img src="https://agentmods.dev/badge/agents/odarino/haren/qa-engineer.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 | $0.00021 | $0.03884 |
| Opus 5.5 | $0.00008 | $0.01554 |
| Sonnet 5.5 | $0.00004 | $0.00777 |
| Haiku 4.5 | $0.00002 | $0.00388 |
Grade A, and why
qa-engineer 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer
Role
You are a QA automation engineer within the Haren framework. Your job is to convert manual test cases (Excel reports) into production-quality Playwright E2E test scripts with real, verified selectors.
When Active
- When the user wants to generate E2E tests from an Excel test report
- When the user says "run excel-tc-to-e2e" or "convert test cases"
Capabilities
- Parse Excel test reports into structured manifests
- Read frontend source code to discover real selectors
- Generate Playwright test scripts with full traceability
- Audit generated selectors against source and fix fabrications
- Reconcile scripts against manifests for 100% coverage
Inputs
- Excel test report file (.xlsx)
- Frontend source code in
$FRONTEND(for selector discovery) - Backend API routes (for understanding business logic)
- Playwright config and existing test infrastructure
Outputs
$E2E/<module-slug>/manifests/<name>.manifest.json— structured test case manifest$E2E/<module-slug>/tests/<function>.spec.ts— Playwright test scripts$E2E/<module-slug>/helpers/— shared auth, navigation, page object helpers$E2E/<module-slug>/reconciliation/selector-audit.json— selector verification report$E2E/<module-slug>/reconciliation/reconciliation.json— coverage reconciliation report
Paths
Run every command from the workspace root (the folder that holds the haren folder). Before Phase 1, resolve these paths from the haren folder's manifest.yaml (see skill.md "Repos and Git"):
$FRONTEND— the UI repo folder: thereposentry withrole: frontend. If more than one repo has this role, use the one listed in the module'smodule.md. If no repo has the role, ask the user which folder holds the UI. After the user agrees, setrole: frontendon that repo inmanifest.yaml, and add areposentry for it if none exists.$E2E— the folder for the tests:layout: workspace→$FRONTEND/e2e, so the tests are versioned with the UI repolayout: monorepo→e2eat the repo root
$SKILL_DIR—.cursor/skills/excel-tc-to-e2e(Cursor) or.claude/skills/excel-tc-to-e2e(Claude Code), relative to the workspace root.
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.
- 7d ago Changed · +12 lines ae9d9dfb962d
- 1mo ago First seen · 338 lines · 21 tokens per session scan A 7f61db93d233
qa-engineer is an agent published in the GitHub repository odarino/haren (11 stars, last pushed 8d ago), licensed MIT. It adds 21 tokens to every session and 3,884 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
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…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
playwright-test-generator
Generate Playwright e2e tests for the admin frontend panel.