Borrowing it
Nothing to install: this file belongs to SystemSculpt/obsidian-systemsculpt-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SystemSculpt/obsidian-systemsculpt-ai/main/.claude/skills/e2e-driving/SKILL.mdgit clone --depth 1 https://github.com/SystemSculpt/obsidian-systemsculpt-aiWrote 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/systemsculpt/obsidian-systemsculpt-ai/e2e-driving)<a href="https://agentmods.dev/skills/systemsculpt/obsidian-systemsculpt-ai/e2e-driving"><img src="https://agentmods.dev/badge/skills/systemsculpt/obsidian-systemsculpt-ai/e2e-driving/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/systemsculpt/obsidian-systemsculpt-ai/e2e-driving"><img src="https://agentmods.dev/badge/skills/systemsculpt/obsidian-systemsculpt-ai/e2e-driving.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 | $0.00096 | $0.01650 |
| Opus 5 | $0.00048 | $0.00825 |
| Sonnet 5 | $0.00019 | $0.00330 |
| Haiku 4.5 | $0.00010 | $0.00165 |
Grade A, and why
e2e-driving 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E driving: CLI control of the live Obsidian GUI
Every action is a synthesized user event (pointer, keyboard, input, file-picker change) on the real DOM — never a service shortcut — so a scripted run exercises exactly what a human's clicks would. Round trips are 1–10ms. Full docs: "CLI E2E driving" in docs/development.md.
Preconditions
- Obsidian must be running a development/staging build. Release builds exclude
the driver (
__SS_TEST_DRIVER__define; artifact-gated both directions). - The dev watcher builds, syncs, and hot-reloads automatically on source
changes; the driver reconnects within ~1s. Verify the loop is alive with
npm run e2e -- status(shows vault, version, build stamp). - If the driver never connects: the loaded bundle predates the driver, or the
watcher process predates a build-config change —
npm run dev:watch:installrestarts it from the canonical checkout, then check~/Library/Logs/SystemSculpt/obsidian-plugin-dev.logfor the sync+reload. - A plugin reload (every watcher sync) resets in-flight UI state — sequence scenarios after the reload settles, and never mid-edit of driver source.
Targets
Canonical addressing is data-testid: dot-namespaced, product-shaped ids
stamped by the UI factories (chat.composer.send, chat.turn.edit-resubmit,
settings.tab.chat, studio.node.run).
npm run e2e -- targets— full generated catalog (174+ ids).npm run e2e -- targets --live— what is in the DOM right now, with per-element visibility. Zero results usually means the surface isn't open.- Escape hatches:
css:<selector>,chat:<selector>(chat view scope),label:<aria-label>,setting:<row name>(any Obsidian settings row by its visible name — resolves to the row's toggle/dropdown/input), andsettings.tab:<label>.
Verbs
npm run e2e -- status
npm run e2e -- open-chat
npm run e2e -- click chat.header.new
npm run e2e -- type "Draft text" [--append] [--submit] [--target <t>]
npm run e2e -- press Enter [--shift|--ctrl|--alt|--meta]
npm run e2e -- attach ./diagram.png [--via picker|drop]
npm run e2e -- select chat.composer.approval-mode full-access
npm run e2e -- select "setting:Default chat font size" large
npm run e2e -- scroll top|bottom|<deltaY>
npm run e2e -- read <target> # element summary incl. value/disabled
npm run e2e -- query "css:.systemsculpt-agent-turn" [--limit N]
npm run e2e -- snapshot chat|settings # structured GUI state
npm run e2e -- wait <target> exists|gone|visible|hidden|enabled|disabled|textContains [--text T] [--timeout MS]
npm run e2e -- wait-run [--timeout MS] [--stall MS] # wait for a chat run to finish
npm run e2e -- command <obsidian-command-id>
npm run e2e -- settings [--tab Chat] / settings-close
npm run e2e -- script <file.mjs|json> [--evidence out.json]
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 · 124 lines · 96 tokens per session scan A fdb126cbbcd9
e2e-driving is a skill published in the GitHub repository SystemSculpt/obsidian-systemsculpt-ai (194 stars, last pushed 25d ago), licensed MIT. It adds 96 tokens to every session and 1,650 once invoked, about $0.0005 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
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…