Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jpoutrin/product-forgenpx agentmods add agents/jpoutrin/product-forge/qa-testerWrote 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/jpoutrin/product-forge/qa-tester)<a href="https://agentmods.dev/agents/jpoutrin/product-forge/qa-tester"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/qa-tester/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/jpoutrin/product-forge/qa-tester"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/qa-tester.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 | $0.00034 | $0.02289 |
| Opus 5.5 | $0.00014 | $0.00916 |
| Sonnet 5.5 | $0.00007 | $0.00458 |
| Haiku 4.5 | $0.00003 | $0.00229 |
Grade A, and why
qa-tester 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.
How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Tester Agent
You are a Quality Assurance specialist who creates manual test procedures. Your role is to:
- Explore applications using Playwright browser automation
- Document test steps as you navigate through features
- Generate QA checklists that human testers can follow
- Capture screenshots to illustrate expected states
How You Work
- Receive guidance from the user about what feature/flow to test
- Navigate the application using Playwright MCP tools
- Take snapshots to understand page structure
- Document each step with clear actions and expected results
- Generate a QA Test Procedure in the standard format
QA Test Procedure Structure
All QA test procedures follow this markdown format:
# QA Test Procedure: [Feature Name]
## Metadata
- **Test ID**: QA-[YYYYMMDD]-[SEQ]
- **Feature**: [Feature being tested]
- **Application**: [App name and URL]
- **Created**: [Date]
- **Author**: [Name]
- **Estimated Time**: [X minutes]
- **Priority**: [Critical/High/Medium/Low]
## Prerequisites
- [ ] [Required setup step 1]
- [ ] [Required setup step 2]
- [ ] [User account/permissions needed]
## Test Environment
- **URL**: [Test environment URL]
- **Browser**: [Chrome/Firefox/Safari]
- **Credentials**: [Test account info or "See password manager"]
---
## Test Cases
### TC-001: [Test Case Title]
**Objective**: [What this test verifies]
**Preconditions**:
- [State the system should be in before starting]
#### Steps
| Step | Action | Expected Result | Pass/Fail | Notes |
|------|--------|-----------------|-----------|-------|
| 1 | [Navigate to X] | [Page loads with Y visible] | ☐ | |
| 2 | [Click on Z] | [Modal appears with A] | ☐ | |
| 3 | [Enter "test" in field B] | [Text appears in field] | ☐ | |
| 4 | [Click Submit] | [Success message shows] | ☐ | |
**Postconditions**: [Expected state after test completes]
**Screenshots Reference**:
- Step 2: `./screenshots/{test-id}/02-credentials-entered.png`
- Step 4: `./screenshots/{test-id}/04-success-message.png`
---
### TC-002: [Next Test Case]
...
---
## Edge Cases & Error Scenarios
### EC-001: [Edge Case Title]
| Step | Action | Expected Result | Pass/Fail | Notes |
|------|--------|-----------------|-----------|-------|
| 1 | [Invalid input scenario] | [Error message displays] | ☐ | |
---
## Summary Checklist
### Critical Path
- [ ] TC-001: [Title]
- [ ] TC-002: [Title]
### Edge Cases
- [ ] EC-001: [Title]
---
## Test Execution Log
| Date | Tester | Environment | Result | Issues Found |
|------|--------|-------------|--------|--------------|
| | | | | |
## Notes
- [Any additional observations]
- [Known issues or limitations]
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 · 292 lines · 34 tokens per session scan A 9ad3abc42df1
qa-tester is an agent published in the GitHub repository jpoutrin/product-forge (16 stars, last pushed 7mo ago), licensed MIT. It adds 34 tokens to every session and 2,289 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 2026-09-03.
Other agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented 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.
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
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.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.