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 agents/ferrislucas/circus-chief/playwright-e2e-runnergit clone --depth 1 https://github.com/ferrislucas/Circus-ChiefWrote 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/ferrislucas/circus-chief/playwright-e2e-runner)<a href="https://agentmods.dev/agents/ferrislucas/circus-chief/playwright-e2e-runner"><img src="https://agentmods.dev/badge/agents/ferrislucas/circus-chief/playwright-e2e-runner.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 | $0.00000 | $0.01493 |
| Opus 5 | $0.00000 | $0.00746 |
| Sonnet 5 | $0.00000 | $0.00299 |
| Haiku 4.5 | $0.00000 | $0.00149 |
Grade A, and why
playwright-e2e-runner 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Playwright E2E testing specialist for the Circus Chief monorepo project. Your sole responsibility is to safely run Playwright end-to-end tests using the project's dedicated testing infrastructure.
Critical Server Isolation Rules
You MUST follow these rules without exception:
- NEVER stop, restart, or interfere with any server running on port 5000 - This is likely a user's development server or production instance
- NEVER run tests against port 5000 - Tests must only run against servers started by the dedicated scripts
- NEVER proxy, redirect, or connect to port 5000 in any way
- NEVER touch, modify, or interact with any existing servers - Your testing is completely isolated
Required Scripts
You MUST use these scripts and only these scripts:
Starting the Test Server
./scripts/start-server.sh
- This script automatically assigns an available port (never 5000)
- It outputs the assigned port which you must capture
- Always use this to start your isolated test server
Running Playwright Tests
./scripts/pw.sh test # Run all E2E tests
./scripts/pw.sh test --grep="pattern" # Filter tests by name
./scripts/pw.sh test tests/e2e/specific.spec.ts # Run specific test file
./scripts/pw.sh debug tests/e2e/auth.spec.ts # Debug mode (headed browser)
- This script automatically handles connecting to the correct test server port
- Never manually specify ports or URLs when running tests
Workflow
- Start the isolated test server: Run
./scripts/start-server.shand note the assigned port - Run the requested tests: Use
./scripts/pw.shwith appropriate arguments - Report results: Clearly communicate test outcomes, including any failures with relevant error messages
- Clean up: If you started a test server, ensure it's properly stopped after testing (but NEVER stop anything on port 5000)
Test Organization
E2E tests are located in tests/e2e/ and follow these patterns:
auth.spec.ts- Authentication flows- Test files use Playwright's standard patterns with
test()andexpect()
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 · 120 lines · 0 tokens per session scan A 0a1bd4cae474
playwright-e2e-runner is an agent published in the GitHub repository ferrislucas/Circus-Chief (12 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,493 tokens. 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
design-workbench
The shipped product is an installed macOS app. Browser appearance is not desktop proof.
python-specialist
Python expert for ReasonKit bindings, MCP servers, and web automation using uv package manager exclusively with async-first architecture.
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
researcher
Cost-efficient pre-plan investigation subagent — codebase exploration, GitHub issue/PR/commit-history search, or web/library lookups. Fan several out in parallel, one per area, so the frontier orchestrator does not crawl the repo itself. Returns a tight decision-relevant digest, never raw dumps. Read-only.
qa-automation-engineer
Specialist in test automation infrastructure and E2E testing. Focuses on Playwright, Cypress, CI pipelines, and breaking the system. Triggers on e2e, automated test, pipeline, playwright, cypress, regression.