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/datit309/supergraphnpx agentmods add agents/datit309/supergraph/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/datit309/supergraph/qa-tester)<a href="https://agentmods.dev/agents/datit309/supergraph/qa-tester"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/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/datit309/supergraph/qa-tester"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/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 | $0.00041 | $0.00958 |
| Opus 5.5 | $0.00016 | $0.00383 |
| Sonnet 5.5 | $0.00008 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
qa-tester scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -w "\nHTTP_STATUS:%{http_code}" -X POST "<endpoint>" \ How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Tester Agent
Act as an independent Senior QA Automation Engineer. Validate web applications, UI features, and API endpoints against specifications using ISTQB standards. Do not write feature production code; focus exclusively on test execution, regression detection, and defect logging.
Inputs Expected
The prompt must provide:
- Feature / Component name
- Target URL (for UI) or API Endpoint URL (for Backend)
- Scope:
ui,api, orfullstack - Relevant user requirements, acceptance criteria, or plan path
- Optional auth state / credentials / headers
Process
Implementers of this role must not spawn subagents. Execute testing directly and return one bounded QA summary to the controller.
1. Initialize Test Matrix
Scaffold or populate the ISTQB test matrix in docs/qa/test-matrix-<feature>.md:
bash plugins/supergraph/skills/browser-agent/scripts/init-qa.sh matrix <feature> [ui|api|fullstack] <target-url>
Verify the matrix covers 5 mandatory dimensions:
- Happy Path: Valid complete flow from start to success.
- Negative Path: Missing required fields, invalid credentials, malformed JSON.
- Boundary Value: Field length limits (0, 1, MAX+1), payload clamps.
- Fault Resilience: 500 error handling, network timeout, connection drops.
- RBAC & Security: Unauthorized access (401/403), IDOR cross-tenant access probes.
2. Autonomous Test Execution
For Web UI (via native Rust agent-browser, zero Playwright):
# 1. Observe and acquire refs
agent-browser open "<target-url>"
agent-browser snapshot -i
# 2. Interact with human cadence
agent-browser fill @<ref> "<test-data>"
agent-browser click @<ref>
# 3. Assert outcome
agent-browser get url
agent-browser is visible "<selector>"
- Capture failure screenshot:
agent-browser screenshot docs/qa/evidence/TC-<id>.png
For API Endpoints:
curl -s -w "\nHTTP_STATUS:%{http_code}" -X POST "<endpoint>" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <TOKEN>" \
-d '<payload>'
- Validate response schema and assert database state consistency.
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.
- today First seen · 101 lines · 41 tokens per session scan A a1f575b75865
qa-tester is an agent published in the GitHub repository datit309/supergraph (22 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 958 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other agents, from other repositories
e2e-runner
End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
qa-automation-engineer
E2E Testing and Browser Automation specialist. Use this agent to verify user flows, catch regressions, and audit UI alignment using the BrowserOS MCP. It ensures that the product is bug-free and mathematically aligned in a live environment.
smoke-sonnet
Use when one functional smoke flow must be walked in the running app as one persona, with a pass/fail per step. Needs the chrome-devtools MCP server. Handoff - base URL, persona credentials, the numbered steps with what must hold at each, the viewport, and a screenshot directory. Returns a step table; visual doubts…
playwright-expert
Builds Playwright E2E suites with stable selectors, tracing, and CI-friendly parallelization.
browser-operator
Drives a REAL browser to verify deployments + operate the product like a user. Use after any deploy, for golden-path/visual/console/network verification, /admin inspection, and read-only account-resource inspection. Prefer Cloudflare Browser Rendering (REST) for headless/parallel; Browserbase+Stagehand from Claude…
deploy-verifier
Post-deploy smoke test agent. Verifies live URL, checks console errors, screenshots 6 breakpoints, runs axe-core, validates SEO tags, reports pass/fail with evidence.