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 agentmods add commands/dork-labs/dorkos/browsertestgit clone --depth 1 https://github.com/dork-labs/dorkosWrote 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/commands/dork-labs/dorkos/browsertest)<a href="https://agentmods.dev/commands/dork-labs/dorkos/browsertest"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/browsertest.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.01590 |
| Opus 5 | $0.00005 | $0.00795 |
| Sonnet 5 | $0.00002 | $0.00318 |
| Haiku 4.5 | $0.00001 | $0.00159 |
Grade A, and why
browsertest 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 4d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Test Command
You are managing DorkOS browser tests. Parse $ARGUMENTS and route to the appropriate action.
Routing Logic
Parse the first word of $ARGUMENTS:
run [feature]
Execute browser tests.
# Run all tests
cd apps/e2e && npx playwright test
# Run specific feature
cd apps/e2e && npx playwright test tests/<feature>/
After running, read apps/e2e/manifest.json and display a results summary.
create <feature> <description>
Create a new browser test using a 5-phase explore-first loop. Never guess selectors — discover them by navigating like a real user.
Pre-Flight
- Read
apps/e2e/manifest.json— check if a similar test already exists. If it does, confirm with the user before overwriting. - Read
apps/e2e/GOTCHAS.md— absorb known anti-patterns before writing anything. - Check manifest for
explorationNoteson related tests — build on prior knowledge. - Read
apps/e2e/pages/for existing POMs that may already cover needed interactions.
Phase 1: EXPLORE
Navigate the feature step-by-step as a real user would. At each meaningful state change:
mcp__plugin_playwright_playwright__browser_navigatetohttp://localhost:6241(or the relevant page)mcp__plugin_playwright_playwright__browser_snapshotto capture the accessibility tree- Document: element roles, names, testids, hierarchy, loading indicators, conditional rendering
- Note timing: what loads immediately, what appears after an SSE event or API call, what animates
Continue until you have observed every state the test needs to assert against. Stay within the scope of <description> — don't explore unrelated features.
Phase 2: WRITE
Using only the selectors discovered in Phase 1:
- Create or update POMs in
apps/e2e/pages/with the explored locators. PrefergetByRole()→data-testid→ text. Never use CSS classes. - Register new POMs in
apps/e2e/fixtures/index.ts. - Write the
.spec.tsfile inapps/e2e/tests/<feature>/using custom fixtures from../../fixtures. - Follow the patterns in
.claude/skills/browser-testing/SKILL.md.
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.
- 4d ago First seen · 154 lines · 10 tokens per session scan A 69ead9206ae0
browsertest is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 1,590 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
app-control-room
Open the full control room — five screens (Mission Control, Communications, Board, Team, Founder Inbox) in the browser.
dark-factory-behavioral-e2e
Holdout-pattern E2E validator. Drives agent-browser against the running DynaChat app to verify that the PR's user-facing behavior actually matches what the linked issue asked for.
testarch-framework
Initialize production-ready test framework architecture (Playwright or Cypress) with fixtures, helpers, and configuration.
e2e
Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces.
scrape
Web scraping — download website assets for analysis.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.