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 skills add lipas-liikuntapaikat/lipas --skill lipas-e2egit 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/skills/lipas-liikuntapaikat/lipas/lipas-e2e)<a href="https://agentmods.dev/skills/lipas-liikuntapaikat/lipas/lipas-e2e"><img src="https://agentmods.dev/badge/skills/lipas-liikuntapaikat/lipas/lipas-e2e/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/skills/lipas-liikuntapaikat/lipas/lipas-e2e"><img src="https://agentmods.dev/badge/skills/lipas-liikuntapaikat/lipas/lipas-e2e.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.02493 |
| Opus 5 | $0.00028 | $0.01247 |
| Sonnet 5 | $0.00011 | $0.00499 |
| Haiku 4.5 | $0.00006 | $0.00249 |
Grade A, and why
lipas-e2e 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LIPAS E2E
Driving real flows through a running dev system, verifying coherently across DB, ES, app-db, and DOM. Not blackbox UI testing — glass-box, REPL-augmented.
For the why behind this skill (principles, architecture, what we deliberately don't build), see webapp/docs/agent-tooling.md.
Prerequisites
- nREPL on
localhost:7888(useclj-nrepl-eval -p 7888) - App reachable at
https://localhost(self-signed cert) - System running:
(user/reset)if it isn't,(user/refresh-all)then(user/reset)after code changes - Browser MCP available if a scenario needs UI verification
Choose a scenario
| Want to verify | Open |
|---|---|
| Municipality user creates a sports facility | scenarios/create-site.md |
| Municipality user updates an existing sports facility | scenarios/update-site.md |
If your task isn't listed, compose from the catalog. Add a new scenario file when the task you just did is something you'll do again.
E2E tooling — one layer, all from clj REPL
The agent stays in the clj nREPL session the entire time. lipas.e2e.tools exposes both backend and UI-driver helpers; UI helpers internally call into the running browser via shadow.cljs.devtools.api/cljs-eval, polling cljs state from clj where Thread/sleep actually blocks.
(require '[lipas.e2e.tools :as e2e] :reload)
(require '[lipas.backend.core :as core])
;; Backend / fixture ops
(def liminka (core/get-user (e2e/db) "[email protected]"))
(def lid (e2e/seed-site! {:type-code 3110 :city-code 425
:name "Fixture" :user liminka}))
;; UI-driven ops (browser dispatches under the hood, blocks on clj side)
(e2e/ui-login! "limindemo" "liminka")
(def created (e2e/ui-create-site! {:type-code 3110 :coords [25.42 64.81]
:name "Demo" :owner "city" :admin "city-sports"
:address "Testikatu 1" :postal-code "91900"}))
(e2e/ui-update-site! {:lipas-id created :changes [[[:name] "Updated"]]})
;; Verification helpers
(e2e/ui-current-name created) ; reads app-db latest revision
(e2e/coherent? created) ; cross-layer DB↔ES check
(e2e/revision-count created) ; raw revision count
(e2e/cleanup! created)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 141 lines · 55 tokens per session scan A bfa6ced437a6
lipas-e2e is a skill published in the GitHub repository lipas-liikuntapaikat/lipas (78 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 2,493 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 skills, from other repositories
init-verify
TEMPLATE-ONLY - verify changes against a fully running stack by instantiating the template, checking in the browser, then reverting every init artifact. Use whenever a change needs visual or runtime verification in the real app. Removed by init.sh, do not reference from skills that survive init.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
playwright-skill
Generates production-grade Playwright automation scripts and E2E tests in TypeScript, JavaScript, Python, Java, or C#. Supports local execution and TestMu AI cloud across 3000+ browser/OS combinations and real mobile devices. Use when the user asks to write Playwright tests, automate browsers, run cross-browser tests…
playwright-e2e
E2E browser testing with Playwright MCP. Use when asked to test frontend flows, verify UI behavior, navigate pages, fill forms, check visual state, or debug browser issues. Trigger words: "test E2E", "prueba de frontend", "navegar", "registrarse", "loguearse", "verificar en el navegador", "playwright", "browser test".
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.