agentmods.dev

webapp-testing

webapp-testing is a skill for Claude Code, Codex from bh-rat/steer. It costs 54 tokens per session (1,259 once invoked), scanned A, original, MIT.

A toolkit for testing local web applications with Playwright, a browser-automation tool. It can check behavior, investigate interface problems, capture screenshots, and collect browser logs.

In plain words
What is it for?
Use it to test local sites, automate browser actions, debug frontend behavior, take screenshots, and inspect console logs.
Why use it?
It verifies what a web app actually does in a browser and provides evidence when the interface or behavior is wrong.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 7repo 3mo ago A scan 54 tokens original MIT

Good fit Use it to test local sites, automate browser actions, debug frontend behavior, take screenshots, and inspect console logs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bh-rat/steer/webapp-testing
View source ↗ bh-rat/steer steer-docs.vercel.app
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.

Any agent
npx skills add bh-rat/steer --skill webapp-testing
Clone the repo
git clone --depth 1 https://github.com/bh-rat/steer

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for webapp-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/bh-rat/steer/webapp-testing/github.svg)](https://agentmods.dev/skills/bh-rat/steer/webapp-testing)
Your own site
<a href="https://agentmods.dev/skills/bh-rat/steer/webapp-testing"><img src="https://agentmods.dev/badge/skills/bh-rat/steer/webapp-testing/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.

agentmods 80×15 button for webapp-testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/bh-rat/steer/webapp-testing"><img src="https://agentmods.dev/badge/skills/bh-rat/steer/webapp-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,259 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.01259
Opus 5.5 $0.00022 $0.00504
Sonnet 5.5 $0.00011 $0.00252
Haiku 4.5 $0.00005 $0.00126

Measured 1mo ago against content hash 2f9c6d9ae2ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

webapp-testing 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (references/console_logging.py, references/element_discovery.py, references/static_html_automation.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

examples/rebuilds/webapp-testing/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

webapp-testing

Test and debug local web applications by writing native Python Playwright scripts. The user gets verified frontend behavior, screenshots, console logs, or automation results; every server started for the job is managed, its output captured, and stopped cleanly afterwards.

This skill bundles its own steer runtime at scripts/steer.py; the commands below invoke it with python3 and need nothing installed. Paths are relative to this skill's directory: when your working directory is elsewhere (it usually is), use the skill's full path (python3 <path-to-this-skill>/scripts/steer.py ...).

Before you start

  1. Ground yourself. Run python3 scripts/steer.py context --tools node,npm,playwright and read the snapshot; it tells you the platform, project type, and whether node and playwright exist here before you write any script.
  2. Apply past lessons. Run python3 scripts/steer.py learn show and follow what it says; those lessons came from real previous runs.

Decision tree

User task -> Is it static HTML?
    - Yes -> Read the HTML file directly to identify selectors
             - Works -> Write a Playwright script using those selectors
             - Fails or incomplete -> Treat as dynamic (below)
    - No (dynamic webapp) -> Is the server already running?
             - No  -> Start it managed (see Servers below), then script
             - Yes -> Reconnaissance then action (below)

Servers

Start every server through steer so nothing leaks or zombies, stdout and stderr are captured to a log, and readiness is checked before your automation runs:

python3 scripts/steer.py proc start app --ready-port 5173 -- npm run dev
python3 scripts/steer.py proc status app     # running? port open?
python3 scripts/steer.py proc logs app       # captured output, e.g. startup errors
python3 scripts/steer.py proc stop app       # TERM then KILL, the whole process group

Multiple servers (e.g. backend + frontend):

python3 scripts/steer.py proc start backend --ready-port 3000 --cwd backend -- python3 server.py
python3 scripts/steer.py proc start frontend --ready-port 5173 --cwd frontend -- npm run dev

Read the full file on GitHub · 129 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 1mo ago First seen · 129 lines · 54 tokens per session scan A 2f9c6d9ae2ab

Subscribe to this mod's changes

webapp-testing is a skill published in the GitHub repository bh-rat/steer (7 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 1,259 once invoked, about $0.0002 per session on Opus 5.5. 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.

Browser automationE2E testingTestingagent-skillsaiskills
Related

Other skills, from other repositories

browser-testing-with-devtools

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…

addyosmani/agent-skills · 68 tokens

actionbook-web-test

Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…

actionbook/actionbook · 71 tokens

web-test

A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.

Nikolay-Shirokov/cc-1c-skills · 44 tokens

playwright-visual-testing

Add, repair, or review Playwright visual regression tests for browser-facing .NET apps, including screenshot baselines, Pixelmatch thresholds, deterministic rendering, and GitHub Actions artifacts. USE FOR: toHaveScreenshot, page.screenshot visual checks, Pixelmatch/pngjs comparison scripts, visual baseline updates…

managedcode/dotnet-skills · 101 tokens

appbuilder-e2e-testing

Use this skill whenever the user wants browser-based end-to-end tests for an Adobe App Builder application. Covers Playwright E2E testing for ExC Shell SPAs, AEM extension UIs, and full-stack flows. Use when the user mentions: "E2E test", "end-to-end test", "Playwright", "browser test", "test my SPA in the browser"…

adobe/skills · 144 tokens

dogfood

This skill guides you through systematic exploratory QA testing of web applications using the browser toolset. You will navigate the application, interact with elements, capture evidence of issues, and produce a structured bug report.

AtlasOmnia/donna-starter · 20 tokens