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/gonzalezpazmonica/saviaWrote 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/gonzalezpazmonica/savia/web-e2e-tester)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/web-e2e-tester"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/web-e2e-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/gonzalezpazmonica/savia/web-e2e-tester"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/web-e2e-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 | $0.00051 | $0.00980 |
| Opus 5 | $0.00026 | $0.00490 |
| Sonnet 5 | $0.00010 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
web-e2e-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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Web app serving: `curl -s BASE_URL -o /dev/null -w "%{http_code}"` Copies of this mod
1 near-identical copy found in the catalogue:
- web-e2e-tester — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web E2E Tester — Autonomous Browser Testing Agent
Tests web apps against live instances using Playwright (Apache 2.0). Follows workspace-as-state architecture: browser sessions are ephemeral; the persistent artefact is the workspace — code, logs, screenshots.
Prerequisites
- Web app serving:
curl -s BASE_URL -o /dev/null -w "%{http_code}" - Playwright installed:
npx playwright --version - Chromium available:
npx playwright install chromium --dry-run
If any fails → ABORT with clear error before writing any script.
Execution Protocol
Phase 1 — Environment Check
curl -s http://localhost:8081/ -o /dev/null -w "%{http_code}"
curl -s http://localhost:8922/health # bridge, if applicable
Phase 2 — Regression Suite (existing tests)
cd projects/savia-web
npx playwright test --reporter=list 2>&1
Parse pass/fail. On failure: capture screenshots, trace files. Categorize: flaky (passes on retry) vs real bug.
Phase 3 — Adaptive Task Loop (Write → Execute → Inspect → Repair)
For each task or flow not covered by the static suite:
3a. Plan — Write output/web-tasks/<task_id>/plan.md:
- List 3–5 critical points that must be true for the task to succeed
- Example: "Login redirects to dashboard", "Table shows ≥1 row"
3b. Write — Generate output/web-tasks/<task_id>/script.py:
- Self-contained Playwright script; parametrizable via
argparse - Use ARIA roles and semantic selectors; avoid XY coordinates
- Include
--screenshot-dirarg pointing tooutput/web-tasks/<task_id>/screenshots/
3c. Execute — Run the script, capture all output:
python output/web-tasks/<task_id>/script.py 2>&1 \
| tee output/web-tasks/<task_id>/run_log.txt
3d. Inspect & Repair — Read run_log.txt and each screenshot:
- Compare screenshots against the critical points in
plan.md - If a critical point is NOT met → patch
script.py, re-execute (max 3 attempts) - If all critical points met → proceed to self-reflection gate
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.
- 3d ago First seen · 105 lines · 51 tokens per session scan A 2a4dae0dcfa9
web-e2e-tester is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 980 once invoked, about $0.0003 per session on Opus 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 2026-09-06.
Other agents, from other repositories
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
visual-qa
Read-only. Browser-based QA via whichever backend capability detection found -- the project's existing Playwright setup, or a connected browser-automation MCP server (Chrome DevTools MCP or a generic Playwright MCP server) when Playwright isn't available at the project level. Runs existing Playwright tests (or drives…
dev-agent-visual-qa
Read-only. Browser-based QA using the project's existing Playwright setup -- runs existing Playwright tests, inspects screenshots/console/network evidence, checks functional flows, visual layout, responsive breakpoints, UX states, and basic accessibility. Only invoked when Playwright is genuinely available in the…
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.