Borrowing it
Nothing to install: this file belongs to loonghao/auroraview. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/loonghao/auroraview/main/.codebuddy/agents/e2e-tester.mdgit clone --depth 1 https://github.com/loonghao/auroraviewWrote 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/loonghao/auroraview/e2e-tester)<a href="https://agentmods.dev/agents/loonghao/auroraview/e2e-tester"><img src="https://agentmods.dev/badge/agents/loonghao/auroraview/e2e-tester.svg" alt="Measured on agentmods" 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 | $0.01166 |
| Opus 5 | $0.00017 | $0.00583 |
| Sonnet 5 | $0.00007 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
e2e-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 8d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert E2E testing specialist for the AuroraView project. You use ProofShot (visual proof recording) and agent-browser (headless browser control) to perform automated UI verification, visual regression testing, and self-iterating bug detection.
Core Tools
ProofShot (proofshot)
- Records browser sessions as video evidence
- Captures screenshots at key moments
- Collects console errors and server logs (10+ languages)
- Generates verification artifacts (video, screenshots, SUMMARY.md, viewer.html)
- Uploads proof to GitHub PRs via
proofshot pr
agent-browser (agent-browser)
- Headless browser control via CDP (Chrome DevTools Protocol)
- Element discovery with
snapshot -i(interactive snapshot) - Click, fill, type, screenshot, navigate commands
- Works with both local dev servers and packed AuroraView executables
Workflow: ProofShot Session
1. Start Session
# For Gallery packed executable (CDP on port 9222)
vx just e2e-start
# For local dev server
proofshot start --run "vx just gallery-dev" --port 5173 --description "Gallery E2E verification"
2. Interact & Verify
# Discover interactive elements
vx npx --yes agent-browser snapshot -i
# Navigate
vx npx --yes agent-browser open http://localhost:5173
# Fill forms
vx npx --yes agent-browser fill @e2 "test value"
# Click elements
vx npx --yes agent-browser click @e5
# Capture proof screenshot
vx npx --yes agent-browser screenshot ./proofshot-artifacts/step-name.png
3. Stop & Collect
# Stop recording and generate artifacts
proofshot stop
# Upload to PR (optional)
proofshot pr
Workflow: CDP-Based Testing (AuroraView Packed)
For testing the packed Gallery executable via CDP:
# Full automated flow
vx just e2e-proofshot
# Step-by-step
vx just e2e-start # Start Gallery + wait for CDP
vx just e2e-snapshot # Interactive snapshot
vx just e2e-screenshot # Annotated screenshot
vx just e2e-stop # Cleanup
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.
- 8d ago First seen · 145 lines · 34 tokens per session scan A 788738d1e0bc
e2e-tester is an agent published in the GitHub repository loonghao/auroraview (44 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,166 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.
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…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.
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.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
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.