dx-bug-verify

dx-bug-verify is a skill for Claude Code from easingthemes/dx-aem-flow. It costs 98 tokens per session (6,748 once invoked), scanned A, original, MIT.

A browser-based bug verification workflow that opens a reproduction URL, follows the reported steps, takes screenshots, and checks whether the problem can be reproduced. Playwright is a tool for controlling a web browser in automated tests.

In plain words
What is it for?
Use it before a fix, after a bug fix, or after a pull request is merged to verify the expected and actual browser behavior.
Why use it?
It provides evidence about whether a reported bug actually occurs and whether a later change fixed it.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is SPEC_DIR=$(bash .ai/lib/dx-common.sh find-spec-dir $ARGUMENTS).

Part of the dx-core plugin — 49 skills, 7 agents shipped together

Good fit Use it before a fix, after a bug fix, or after a…

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/easingthemes/dx-aem-flow
agentmods
npx agentmods add skills/easingthemes/dx-aem-flow/dx-bug-verify

Made for: Claude Code.

Or install dx-core, the plugin that ships this one along with the rest of its 49 skills, 7 agents.

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 dx-bug-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/dx-bug-verify.svg)](https://agentmods.dev/skills/easingthemes/dx-aem-flow/dx-bug-verify)
Your own site
<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/dx-bug-verify"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/dx-bug-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,748 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00098 $0.06748
Opus 5 $0.00049 $0.03374
Sonnet 5 $0.00020 $0.01350
Haiku 4.5 $0.00010 $0.00675

Measured 6d ago against content hash 9d3d3f307e89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

dx-bug-verify scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const resp = await fetch(window.location.href, {
plugins/dx-core/skills/dx-bug-verify/SKILL.md · 741 lines

How it starts

The opening of the file, as written. The whole thing — 741 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Defaults

Read shared/provider-config.md for provider detection and tool mapping.

Read .ai/config.yaml:

  • tracker.provider (or scm.provider for backward compat) — ado (default) or jira

If provider = ado:

  • Organization: scm.org
  • Project: scm.project

If provider = jira:

  • Jira URL: jira.url
  • Project Key: jira.project-key

You reproduce a bug using Playwright MCP — navigate to the repro URL, execute the repro steps, take screenshots at each step, and confirm whether the bug is reproducible.

Flow

digraph bug_verify {
    "Parse mode" [shape=box];
    "Locate spec directory" [shape=box];
    "Spec exists?" [shape=diamond];
    "Parse repro inputs" [shape=box];
    "Repro URL found?" [shape=diamond];
    "Check existing output" [shape=box];
    "Output current?" [shape=diamond];
    "Ensure Playwright MCP" [shape=box];
    "Tools available?" [shape=diamond];
    "Navigate + authenticate" [shape=box];
    "Page loaded?" [shape=diamond];
    "Take initial screenshot" [shape=box];
    "Execute repro steps" [shape=box];
    "Verify expected vs actual" [shape=box];
    "Determine result" [shape=box];
    "Collect diagnostics" [shape=box];
    "Save output file" [shape=box];
    "Post comment" [shape=box];
    "Present summary" [shape=doublecircle];
    "Report Blocked (no spec)" [shape=doublecircle];
    "Report Blocked (no URL)" [shape=doublecircle];
    "Skip (up to date)" [shape=doublecircle];
    "Report Blocked (no tools)" [shape=doublecircle];
    "Report Blocked (unreachable)" [shape=doublecircle];

    "Parse mode" -> "Locate spec directory";
    "Locate spec directory" -> "Spec exists?";
    "Spec exists?" -> "Parse repro inputs" [label="yes"];
    "Spec exists?" -> "Report Blocked (no spec)" [label="no"];
    "Parse repro inputs" -> "Repro URL found?";
    "Repro URL found?" -> "Check existing output" [label="yes"];
    "Repro URL found?" -> "Report Blocked (no URL)" [label="no"];
    "Check existing output" -> "Output current?";
    "Output current?" -> "Skip (up to date)" [label="yes"];
    "Output current?" -> "Ensure Playwright MCP" [label="no"];
    "Ensure Playwright MCP" -> "Tools available?";
    "Tools available?" -> "Navigate + authenticate" [label="yes"];
    "Tools available?" -> "Report Blocked (no tools)" [label="no"];
    "Navigate + authenticate" -> "Page loaded?";
    "Page loaded?" -> "Take initial screenshot" [label="yes"];
    "Page loaded?" -> "Report Blocked (unreachable)" [label="no"];
    "Take initial screenshot" -> "Execute repro steps";
    "Execute repro steps" -> "Verify expected vs actual";
    "Verify expected vs actual" -> "Determine result";
    "Determine result" -> "Collect diagnostics";
    "Collect diagnostics" -> "Save output file";
    "Save output file" -> "Post comment";
    "Post comment" -> "Present summary";
}

Read the full file on GitHub · 741 lines

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. 6d ago First seen · 741 lines · 98 tokens per session scan A 9d3d3f307e89

Subscribe to this mod's changes

dx-bug-verify is a skill published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 5d ago), licensed MIT. It adds 98 tokens to every session and 6,748 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

verify-bug

Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.

HoangNguyen0403/agent-skills-standard · 39 tokens

reality-verification

This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…

tzachbon/smart-ralph · 81 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog · 112 tokens

testing-blocks

Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.

adobe/skills · 61 tokens

flutter-skill

Automate and test Flutter applications — launch apps, inspect widgets, tap elements, enter text, scroll, swipe, take screenshots, validate state, and debug via Dart VM Service Protocol. Use when the user wants to run Flutter app tests, automate Flutter UI interactions, inspect widget trees, debug a running Flutter…

ai-dashboad/flutter-skill · 73 tokens

qa

Read-only automated QA sweep of a deployed stardust site on AEM Edge Delivery Services — validates routing, content fidelity vs the source capture, template conformance, rendered integrity (geometry, JS errors, broken images), visual regression vs baselines, metadata/SEO/JSON-LD, link integrity, accessibility (axe)…

adobe/skills · 138 tokens