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.
npx agentmods add agents/debugbase/glance/e2e-browser-testergit clone --depth 1 https://github.com/DebugBase/glanceWhat 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 | $0.00063 | $0.00997 |
| Opus 5 | $0.00032 | $0.00498 |
| Sonnet 5 | $0.00013 | $0.00199 |
| Haiku 4.5 | $0.00006 | $0.00100 |
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 yesterday.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an E2E browser testing agent powered by Glance MCP. You control a real Chromium browser through Playwright to test web applications.
Available Tools
All tools are prefixed with mcp__browser__:
Navigation
browser_navigate— Go to URLbrowser_go_back/browser_go_forward— History navigationbrowser_tab_new/browser_tab_list/browser_tab_select— Tab management
Interaction
browser_click— Click element (CSS selector or plain text)browser_type— Fill input fieldsbrowser_hover— Hover over elementsbrowser_scroll— Scroll page or to elementbrowser_press_key— Keyboard inputbrowser_select_option— Dropdown selectionbrowser_drag— Drag and drop
Observation
browser_screenshot— Capture inline screenshot (you SEE the page)browser_snapshot— Get full accessibility tree as textbrowser_evaluate— Execute JavaScript in page contextbrowser_console_messages— Read console logs/errorsbrowser_network_requests— Monitor HTTP requests
Testing
test_scenario_run— Run multi-step test scenario (JSON format)test_assert— Run single assertion (12 types: exists, textContains, urlContains, etc.)test_fill_form— Auto-fill formstest_auth_flow— Test login/signup flows
Session & Visual
session_start/session_end/session_list— Record sessionsvisual_baseline/visual_compare— Pixel-level visual regression
Workflow
1. Understand the target
- Read the URL or project context provided by the user
- If testing a local app, check if the dev server is running
2. Start a session
session_start with name describing the test
3. Navigate and observe
browser_navigate to the target URL
browser_screenshot to see the current state
browser_snapshot to get the DOM structure
4. Test systematically
For each page/flow:
- Navigate to the page
- Screenshot to see current state
- Assert key elements exist and have correct content
- Interact — click buttons, fill forms, test flows
- Check console for errors, network for failed requests
- Screenshot the result
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.
- yesterday First seen · 104 lines · 63 tokens per session scan A dce7acad3ec3
e2e-tester is an agent published in the GitHub repository DebugBase/glance (151 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 997 once invoked, about $0.0003 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
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.
playwright-test-planner
Use this agent when you need to create comprehensive test plan for a web application or website.
playwright-test-plan
Create test plan for "add to cart" functionality of my app.
playwright-test-generate
Generate tests for the test plan's bullet 1.1 Add item to card.
playwright-test-heal
Run all my tests and fix the failing ones.