claude-testing-kit: Skill for Claude Code

.claude/skills/skills-locator-healer-agent/SKILL.md

skills-locator-healer-agent is a skill for Claude Code from anhtester/claude-testing-kit. It costs 29 tokens per session (833 once invoked), scanned A, a copy of Locator Healer Agent, MIT.

A testing skill that repairs selectors—code used to find page elements—when browser automation tests can no longer locate the intended element.

In plain words
What is it for?
Comparing old selectors with the current page, inspecting the page structure, and proposing replacements for reactive or proactive checks.
Why use it?
It helps diagnose failures caused by changes to a website’s HTML structure and can also find fragile or incorrect selectors before they fail.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is anhtester/claude-testing-kit's own configuration. It tells Claude Code how to work on claude-testing-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-testing-kit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to anhtester/claude-testing-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/anhtester/claude-testing-kit/main/.claude/skills/skills-locator-healer-agent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/anhtester/claude-testing-kit

Made for: Claude Code.

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 skills-locator-healer-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/anhtester/claude-testing-kit/skills-locator-healer-agent/github.svg)](https://agentmods.dev/skills/anhtester/claude-testing-kit/skills-locator-healer-agent)
Your own site
<a href="https://agentmods.dev/skills/anhtester/claude-testing-kit/skills-locator-healer-agent"><img src="https://agentmods.dev/badge/skills/anhtester/claude-testing-kit/skills-locator-healer-agent/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 skills-locator-healer-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/anhtester/claude-testing-kit/skills-locator-healer-agent"><img src="https://agentmods.dev/badge/skills/anhtester/claude-testing-kit/skills-locator-healer-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 833 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 86% copy Near-identical to another mod 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 $0.00029 $0.00833
Opus 5 $0.00015 $0.00417
Sonnet 5 $0.00006 $0.00167
Haiku 4.5 $0.00003 $0.00083

Measured 10d ago against content hash f91d9f81f448, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skills-locator-healer-agent 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 10d 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.

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.

Origin

This is a copy

86% identical to Locator Healer Agent — 17 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/skills-locator-healer-agent/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Locator Healer Agent

Purpose: Automatically repair broken locators when automation tests fail.


When to Use

Use this skill when:

  • A test fails with "element not found" or "element detached" errors
  • UI has changed and existing locators no longer work
  • After a frontend deployment that modifies DOM structure

Hai Kiểu Kích Hoạt

Kiểu Trigger Input Đường vào
Reactive — chữa theo lỗi Test fail với ElementNotFound / strict mode violation Error log + stack trace /analyze_flaky_tests
Proactive — rà cả loạt UI vừa đổi, chưa chạy test cũng rà được Page Object + URL Yêu cầu trực tiếp từ user

Kiểu proactive không có error log để lần theo — phải trích toàn bộ locator từ Page Object, mở browser đưa về đúng trạng thái chứa element, rồi đối chiếu từng cái. Bắt được cả locator mong manh (còn chạy nhưng bám thuộc tính dễ đổi) lẫn locator sai element (match 1 element nhưng không phải element cần — test vẫn xanh mà thao tác nhầm chỗ).


Responsibilities

When a locator fails:

  1. Inspect current DOM or UI hierarchy
  2. Compare old locator with current page structure
  3. Identify updated attributes
  4. Generate a replacement locator
  5. Re-run test to verify the fix

Detection Strategy

Locator is considered broken when:

  • Element not found (NoSuchElementException / TimeoutError)
  • Element detached from DOM
  • Selector matches zero elements
  • Selector matches wrong element (different text/position)

Healing Workflow

Step 1: Analyze the Error

  • Read error log to identify which locator failed
  • Identify the Page Object file and line number

Step 2: Inspect Current DOM

  • Open the page using MCP tools
  • Navigate to the same state as the failing test
  • Inspect the target area in DOM

Step 3: Find Alternative Locator

Try the following in priority order:

  1. Accessibility attributes (aria-label, role)
  2. data-testid / data-test
  3. id (if stable, not auto-generated)
  4. Semantic locator (Playwright getByRole, getByLabel)
  5. css selector (stable attributes)
  6. xpath (relative, not positional)

Read the full file on GitHub · 110 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. 10d ago First seen · 110 lines · 29 tokens per session scan A f91d9f81f448

Subscribe to this mod's changes

skills-locator-healer-agent is a skill published in the GitHub repository anhtester/claude-testing-kit (53 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 833 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to Locator Healer Agent, differing in 17 lines, and is treated as a copy.