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 sailingnaturali/claude-skills --skill signalk-server-e2egit clone --depth 1 https://github.com/sailingnaturali/claude-skillsWrote 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/sailingnaturali/claude-skills/signalk-server-e2e)<a href="https://agentmods.dev/skills/sailingnaturali/claude-skills/signalk-server-e2e"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/signalk-server-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/sailingnaturali/claude-skills/signalk-server-e2e"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/signalk-server-e2e.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 | $0.00120 | $0.01774 |
| Opus 5 | $0.00060 | $0.00887 |
| Sonnet 5 | $0.00024 | $0.00355 |
| Haiku 4.5 | $0.00012 | $0.00177 |
Grade C, and why
signalk-server-e2e scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
kill "$SK_PID" 2>/dev/null; rm -rf /tmp/sk-e2e Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
(In an `e2e.mjs`, spawn the server with `child_process` and kill it in a `finally`.) How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-to-end test a SignalK server or plugin change in a real browser
When a change touches server behavior a unit test can't reach — Admin UI, a plugin's config
panel, data reaching Freeboard-SK, the delta/stream path — verify it in a real browser against a
running server before you open the PR. This is the browser-level complement to the server's own
npm test; it catches the "serves fine but the UI never shows it" class of bug that mocked
tests miss.
This skill is the SignalK-specific layer. The shared browser mechanics live in the companion
webapp-e2e skill (always installed alongside this one): using the repo's bundled
@playwright/test chromium instead of a system/MCP browser, role/label locators + auto-waiting
expect, mounting a Module-Federation component, the headless-Chrome blank-canvas gotcha, and
the PR-evidence gating. Read webapp-e2e for those; below is only what's specific to a SignalK
server.
1. Spin up the server under test
Start a real server on a throwaway config dir so you never touch a live install:
# from the signalk-server checkout; -c points at a scratch data dir
mkdir -p /tmp/sk-e2e
PORT=4000 npm start -- -c /tmp/sk-e2e &
SK_PID=$!
-
Readiness gate: poll an HTTP endpoint until it answers (
GET /signalkreturns 200) before launching the browser — "process started" ≠ "server answering". Make thisfetch-poll the primary gate; a SignalK UI holds its delta WebSocket open, sopage.goto(..., { waitUntil: "networkidle" })may never fire and is only a fallback for the page load itself.for (let i = 0; i < 60; i++) { try { if ((await fetch("http://localhost:4000/signalk")).ok) break; } catch {} await new Promise((r) => setTimeout(r, 500)); } -
Plugin under test: symlink your plugin into the server's
node_modules(ornpm iit as afile:dep) so anpm run buildin the plugin dir is picked up on the next server restart — nonpm linkdance. Rebuild the plugin, restart the server, then run the browser check. -
Security: with security disabled (fresh scratch config) the
/signalk/v1/streamWebSocket accepts unauthenticated deltas and the resource/data APIs are anonymously readable — which is what makes headless e2e cheap. If you must test an admin-gated path, log in through the UI in the Playwright script and reuse the storage state. -
Teardown: always kill the server and remove the scratch dir when done, even on failure, so a wedged
:4000or a stale config doesn't poison the next run:
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 · 115 lines · 120 tokens per session scan C b090606524aa
signalk-server-e2e is a skill published in the GitHub repository sailingnaturali/claude-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 120 tokens to every session and 1,774 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
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.
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.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…