A command for running end-to-end (E2E) browser tests and reviewing their results. It can include screenshots, network-request details, and checks for tests that fail only sometimes.

Use it to run one suite, one test file, or all available tests, then review pass and failure totals, screenshots, visual checks, flaky tests, failed or slow requests, and detailed failure data.

It combines test execution with the first steps of failure investigation, so you do not have to inspect every failed test manually. It helps show whether problems come from the page, the network, or the test itself.

run — Command by fastslack

Install

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.

agentmods

npx agentmods add commands/fastslack/mtw-e2e-runner/run

Clone the repo

git clone --depth 1 https://github.com/fastslack/mtw-e2e-runner

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 524 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00014	$0.00524
Opus 5	$0.00007	$0.00262
Sonnet 5	$0.00003	$0.00105
Haiku 4.5	$0.00001	$0.00052

Measured yesterday against content hash 0135203657bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run 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 yesterday.

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.

.opencode/commands/run.md · 51 lines

What it actually says

Run E2E Tests

Execute E2E tests and provide a complete analysis of results.

Workflow

Check pool availability — Call e2e_pool_status to confirm the Chrome pool is running. If not available, tell the user to run npx e2e-runner pool start via CLI.
List available suites — Call e2e_list to show the user what test suites are available.
Run tests — Call e2e_run based on user input:
- If user specified a suite name: use suite parameter
- If user specified a file: use file parameter
- If user said "all" or didn't specify: use all: true
- Always pass cwd with the current working directory
- Pass any user-specified overrides: baseUrl, concurrency, retries, failOnNetworkError
Analyze results — Parse the run response:
- Report pass/fail summary and duration
- For failures: show error messages and retrieve error screenshots with e2e_screenshot
- For verifications (tests with expect): retrieve verification screenshots and judge against descriptions
- Highlight flaky tests if any
- Summarize network activity (failed requests, slow requests)
Drill down if needed — For failed tests:
- Use e2e_network_logs with runDbId to investigate network failures
- Use e2e_learnings to check if this is a known pattern or new failure
Report — Provide a clear summary to the user with actionable next steps.

Arguments

The user may pass arguments after the command:

Suite name: /run auth → run the auth suite
--all: run all suites
--base-url <url>: override base URL
--retries <n>: set retry count

MCP Tools Used

e2e_pool_status — Check Chrome pool availability
e2e_list — List test suites and modules
e2e_run — Execute tests
e2e_screenshot — Retrieve screenshots by hash
e2e_network_logs — Inspect network requests
e2e_learnings — Query learning system

Changes

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.

yesterday First seen · 51 lines · 14 tokens per session scan A 0135203657bc

Subscribe to this mod's changes

run is a command published in the GitHub repository fastslack/mtw-e2e-runner (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 524 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.

Code review DevOps and cloud Testing browser-automation browserless claude-code docker e2e-testing json

run

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Run E2E Tests

Workflow

Arguments

MCP Tools Used

What this file has done since we first saw it

Other commands, from other repositories

audit

multi-page

regression

bootstrap

safety-check

smoke