Run Tests

What it does

When your agent uses it

• Tasks that involve End-to-end testing
• Tasks that involve Test generation

Example prompts

• “Use the run-tests skill to discover and runs Browser4 test suites (unit, integration, E2E, CLI, PowerShell, real-world scenarios, production…”
• “/run-tests”

Requirements

• Pre-approved tools (allowed-tools): Bash(pwsh:*), Bash(./bin/test.ps1:*)

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

1. 1Creates an isolated working directory (default: system temp + random suffix)
2. 2Cleans any pre-existing global browser4-cli installation
3. 3Installs the latest CLI via the remote bootstrap script (unmodified)
4. 4Verifies the CLI is on PATH after install (fails if the install script is broken)
5. 5Smoke-tests: --help, --version, config --help, agent-run --help, invalid command
6. 6Cold-starts the browser server (open), verifies health endpoint responds
7. 7Measures warm-start latency vs cold-start (cycle 2)
8. 8Shuts down the server (close-all, kill-all), verifies it's unreachable
9. 9Uninstalls and verifies runtime data is removed
10. 10Repeats the install cycle to verify idempotency
11. 11(With -Stress) Runs multi-scenarios.ps1 against the global CLI

What it can do on your machine

Read from SKILL.md and the folder at commit 0fdba82. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash(pwsh:*)
  • Bash(./bin/test.ps1:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • cargo

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Run Tests loads about 1.9k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 649 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~46

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from platonai/Browser4 at commit 0fdba82, republished under its Apache-2.0 licence (© platonai). 649 words, ~1,924 tokens.

name

run-tests

description

Discovers and runs Browser4 test suites (unit, integration, E2E, CLI, PowerShell, real-world scenarios, production acceptance). Use when asked to run, check, or verify tests.

allowed-tools

Bash(pwsh:*), Bash(./bin/test.ps1:*)

title

Run Tests — Execute Browser4 test suites via bin/test.ps1

./bin/test.ps1 [OPTIONS] [TEST-TYPES...] [EXTRA-ARGS...]

# Run fast unit tests
./bin/test.ps1 fast

# Show the Maven command without executing
./bin/test.ps1 -DryRun fast

# Run integration tests with extra Maven args
./bin/test.ps1 it -pl browser4-core

# Run end-to-end tests
./bin/test.ps1 e2e

# Run CLI tests (Rust cargo test)
./bin/test.ps1 cli

# Pass extra cargo test args to CLI tests
./bin/test.ps1 cli -- --help

# Run all PowerShell test files (+ the skills/ document conformance check)
./bin/test.ps1 ps

# Run all PS tests quietly
./bin/test.ps1 ps -Quiet

# Run all main tests together
./bin/test.ps1 main

# Run fast tests and PS tests together
./bin/test.ps1 fast ps

# Run fast tests without persisting session
./bin/test.ps1 -NoSession fast

# Write session to a custom path
./bin/test.ps1 -SessionPath out/session.json ps

# Preview what tests would be run
./bin/test.ps1 -Show main

# Resume from the last failed Maven module
./bin/test.ps1 resume

# Launch the mock server
./bin/test.ps1 mock-site -Dmock.site.port=18080

# Run all real-world scenarios
./bin/test.ps1 rws --scenarios

# Run a specific scenario
./bin/test.ps1 rws --scenarios amazon

# Run scenarios against installed production CLI
./bin/test.ps1 rws --scenarios --production

# List discovered scenarios
./bin/test.ps1 rws --scenarios --list

# Run a single task file directly
./bin/test.ps1 rws --task tasks/real-world/generic/amazon.md

# Run scenarios with 30-minute per-task timeout
./bin/test.ps1 rws --scenarios --timeout 30

ls -t .test-sessions/*/test-session.json | head -1 | xargs cat

./bin/test-production.ps1

# Show help (no arguments = safe default)
./bin/test-production.ps1

# Run the full acceptance test
./bin/test-production.ps1 -Stress

# Production CI: stress test with multiple iterations, clean up afterward
./bin/test-production.ps1 -Stress -MultiScenariosIterations 3 -RemoveWorkingDir

# Use a specific working directory
./bin/test-production.ps1 -WorkingDir /tmp/my-acceptance-test

© platonai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in coworker/skills/run-tests of platonai/Browser4.

Open the folder on GitHubat commit 0fdba82