web-test

A web-debugging workflow that turns problems found while exploring a live page into Playwright end-to-end tests. Playwright is a tool for testing websites in a browser.

In plain words
What is it for?
Use it to inspect page behaviour, diagnose UI bugs, investigate flaky tests, and create regression tests from those findings.
Why use it?
It connects investigation of a live-page bug with a repeatable test, helping catch the same problem later.

Skill for Claude CodeCodex

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 skills/musingfox/cc-plugins/web-test
Any agent
npx skills add musingfox/cc-plugins --skill web-test
Clone the repo
git clone --depth 1 https://github.com/musingfox/cc-plugins

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,743 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.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.01743
Opus 5 $0.00028 $0.00872
Sonnet 5 $0.00011 $0.00349
Haiku 4.5 $0.00006 $0.00174

Measured yesterday against content hash 9071bcdff697, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-test 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.

agent-browser/skills/web-test/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Test: Debug-to-Test Workflow

Overview

This skill orchestrates a four-phase workflow: explore a web page with agent-browser to identify issues, diagnose problems, map element references to Playwright locators, and generate test scripts that capture findings as regression tests.

Prerequisites: agent-browser CLI installed (npm install -g agent-browser && agent-browser install) and @playwright/test installed in the project (npm install -D @playwright/test && npx playwright install).

The four phases:

Explore (agent-browser) → Diagnose → Map refs to locators → Generate Playwright test

Phase 1: Explore with agent-browser

Navigate to the target page and systematically inspect its state:

agent-browser open <url>
agent-browser snapshot -i

Investigation checklist:

  1. Visual scanscreenshot to observe layout, visual state, and obvious defects.
  2. Interactive inventorysnapshot -i to list all interactive elements with refs.
  3. Section focussnapshot -s ".section" to isolate specific areas of interest.
  4. Interaction test — Click buttons, fill forms, navigate links. Re-snapshot after each action to verify state changes.
  5. Scroll explorationscroll down N then re-snapshot to find below-fold content.
  6. Annotated verificationscreenshot --annotate to visually confirm ref-to-element mapping.

Record every interaction step — these become the basis for test cases in Phase 4.

Exploration is complete when all visible sections have been inspected, all interactive elements have been tested, and all observed defects have been recorded.

Phase 2: Diagnose Issues

Categorize findings from exploration:

Category Detection Method Example
Missing element Expected ref absent from snapshot Button in spec but not in DOM
Wrong text Snapshot shows incorrect label/content "Save" button labeled "Svae"
Broken interaction Action produces no or wrong state change Submit button doesn't navigate
Visual defect Screenshot shows layout/style issues Overlapping elements, clipped text
Accessibility gap Snapshot shows missing roles/labels Input without associated label

Read the full file on GitHub · 169 lines

Files

What ships with it

1 file 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. yesterday First seen · 169 lines · 56 tokens per session scan A 9071bcdff697

Subscribe to this mod's changes

web-test is a skill published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,743 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens