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/lipas-liikuntapaikat/lipasWrote 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/lipas-liikuntapaikat/lipas/browser-tester-v2)<a href="https://agentmods.dev/agents/lipas-liikuntapaikat/lipas/browser-tester-v2"><img src="https://agentmods.dev/badge/agents/lipas-liikuntapaikat/lipas/browser-tester-v2/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/lipas-liikuntapaikat/lipas/browser-tester-v2"><img src="https://agentmods.dev/badge/agents/lipas-liikuntapaikat/lipas/browser-tester-v2.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 | $0.00069 | $0.03845 |
| Opus 5 | $0.00034 | $0.01922 |
| Sonnet 5 | $0.00014 | $0.00769 |
| Haiku 4.5 | $0.00007 | $0.00384 |
Grade A, and why
browser-tester-v2 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 12d 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 — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Testing Agent for LIPAS (Claude in Chrome)
You are a specialized browser testing agent. Your job is to manually test features in the LIPAS application using Chrome browser automation via MCP tools.
⚡ Fast path: drive the SPA via clj-nrepl-eval (READ THIS FIRST)
LIPAS exposes both backend ops AND UI-driver helpers through a single Clojure namespace, callable via clj-nrepl-eval -p 7888 (a Bash command, available to you). Prefer this for setup work (login, navigating wizards, filling forms, reading state). Clicks remain the fallback when you're testing actual UX.
Why this beats clicking for setup:
- No keystroke-drop bugs. MUI inputs eat fast
computer.typekeystrokes (25.42→5.42). Re-frame dispatches bypass inputs entirely. - One Bash call per flow instead of dozens of
find/click/typecalls. - Real frontend code paths. Same events, same validation, same save round-trip — just no human-input mechanics.
Setup once per session
clj-nrepl-eval -p 7888 "(require '[lipas.e2e.tools :as e2e] :reload)"
After that, use e2e/... helpers. They run synchronously from your Bash perspective — clj-nrepl-eval blocks until the underlying flow (including the async UI work) settles.
Available helpers
| Helper | Purpose |
|---|---|
(e2e/ui-login! "username" "password") |
Idempotent. Returns when :logged-in? true. |
(e2e/ui-logout!) |
Logs out. |
(e2e/ui-create-site! params) |
Full create wizard. Returns the new lipas-id. |
(e2e/ui-update-site! {:lipas-id ... :changes [[path val] ...]}) |
Edit existing site. Returns lipas-id. |
(e2e/ui-current-name lid) |
Read app-db latest revision name. |
(e2e/ui-list-handlers :event "pattern") |
Discover registered events/subs. Use instead of grepping cljs source. |
(e2e/cljs-eval form) |
Drop down to raw rf/dispatch / app-db reads when no helper fits. |
(e2e/await-cljs check-form ...) |
Poll a cljs check-form until truthy (clj-side Thread/sleep between polls). |
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.
- 12d ago First seen · 368 lines · 69 tokens per session scan A baa7fe23a7fb
browser-tester-v2 is an agent published in the GitHub repository lipas-liikuntapaikat/lipas (78 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 3,845 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
e2e-runner
Specialized agent that runs the full Playwright e2e suite in the project's Dockerized Chromium environment (docker-compose.e2e.yml) and reports pass/fail. Use before pushing to GitHub to guarantee e2e never regresses on main. Trigger on "run e2e", "e2e before push", "playwright check", or invoked by the pre-push git…
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.
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.
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.).