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.
npx skills add agentmantis/test-skills --skill create-pomgit clone --depth 1 https://github.com/agentmantis/test-skillsWrote 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.
[](https://agentmods.dev/skills/agentmantis/test-skills/create-pom)<a href="https://agentmods.dev/skills/agentmantis/test-skills/create-pom"><img src="https://agentmods.dev/badge/skills/agentmantis/test-skills/create-pom/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.
<a href="https://agentmods.dev/skills/agentmantis/test-skills/create-pom"><img src="https://agentmods.dev/badge/skills/agentmantis/test-skills/create-pom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01695 |
| Opus 5.5 | $0.00029 | $0.00678 |
| Sonnet 5.5 | $0.00014 | $0.00339 |
| Haiku 4.5 | $0.00007 | $0.00169 |
Grade A, and why
create-pom 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.
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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Page Object Model
Generate a POM class for the specified page following all E2E test conventions.
Workflow
- Determine the page name from the user's request (e.g., "Settings" →
settings.page.ts) - Check if a POM already exists for this page in
e2e/poms/. If so, add methods to the existing POM — do NOT create a second POM for the same page - Identify the base page class in
e2e/poms/base.page.tsand extend it - Read the target page in the application to understand its elements and interactions
- Generate the POM file following the template below
- Verify the file compiles with no TypeScript errors
Rules
- One page = one POM — every distinct page/view gets exactly one POM file
- All POMs extend the base page class — check
e2e/poms/base.page.tsfor the abstract class - Implement
setUp()andtearDown()— inherited from the base class - Reusable helpers belong in
BasePage— if a helper method is useful across multiple POMs (e.g.,waitForToast,dismissModal), it must live inBasePage, not in a derived POM. Derived POMs should contain only page-specific behavior. If you find yourself writing the same helper in a second POM, promote it toBasePageimmediately - NEVER reference another POM from within a POM — if a test needs multiple pages, the spec file orchestrates between POMs
- Detailed JSDoc on every public method — describe what it does step by step, with
@paramtags - Use the selector priority order:
getByRole()>getByLabel()>getByText()>getByPlaceholder()>locator()
POM Structure
Organise every POM with these clearly separated sections using comment banners:
import { Page, Locator, expect } from '@playwright/test';
// TODO: Import your project's base page class
import { BasePage } from './base.page';
export class FeaturePage extends BasePage {
constructor(page: Page) {
super(page);
}
// ==========================================
// LIFECYCLE (from BasePage)
// ==========================================
/**
* Navigates to the feature page and cleans up any stale data
* left by previous failed test runs.
*
* Steps:
* 1. Navigates to /feature via direct URL.
* 2. Waits for the page heading to be visible.
* 3. Deletes any items matching the test data pattern.
*/
async setUp(): Promise<void> {
// TODO: Implement navigation and cleanup
}
/**
* Cleans up any data created during the test suite.
*
* Steps:
* 1. Navigates to /feature.
* 2. Deletes all items created by this test run.
*/
async tearDown(): Promise<void> {
// TODO: Implement cleanup
}
// ==========================================
// LOCATORS
// ==========================================
/** The main heading of the feature page. */
get heading(): Locator {
return this.page.getByRole('heading', { name: 'Feature Name' });
}
/** The "Create" button that opens the creation modal. */
get createButton(): Locator {
return this.page.getByRole('button', { name: /create/i });
}
// TODO: Add locators for all interactive elements on this page
// ==========================================
// NAVIGATION
// ==========================================
/**
* Navigates directly to the feature page via URL.
*
* Steps:
* 1. Calls page.goto('/feature').
* 2. Asserts the page heading is visible.
* 3. Asserts the URL contains '/feature'.
*/
async navigateToPage(): Promise<void> {
await this.page.goto('/feature');
await expect(this.heading).toBeVisible();
await expect(this.page).toHaveURL(/\/feature/);
}
// ==========================================
// VERIFICATION
// ==========================================
/**
* Verifies an item appears in the list with the expected name.
*
* Steps:
* 1. Locates the item row by name text.
* 2. Asserts the row is visible.
*
* @param name - The expected item name
*/
async verifyItemExists(name: string): Promise<void> {
await expect(
this.page.getByRole('row', { name: new RegExp(name, 'i') })
).toBeVisible();
}
// ==========================================
// CREATE
// ==========================================
/**
* Creates a new item via the creation modal.
*
* Steps:
* 1. Clicks the "Create" button to open the modal.
* 2. Fills in the name field.
* 3. Clicks "Submit" and waits for the modal to close.
*
* @param name - Display name for the new item
*/
async createItem(name: string): Promise<void> {
await this.createButton.click();
const modal = this.page.getByRole('dialog');
await modal.getByLabel('Name').fill(name);
await modal.getByRole('button', { name: 'Submit' }).click();
await expect(modal).toBeHidden();
}
// ==========================================
// EDIT
// ==========================================
// TODO: Add edit methods
// ==========================================
// DELETE
// ==========================================
// TODO: Add delete methods
}
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.
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.
- 1mo ago First seen · 210 lines · 72 tokens per session scan A 5a487393e2f2
create-pom is a skill published in the GitHub repository agentmantis/test-skills (12 stars, last pushed 6mo ago), licensed MIT. It adds 72 tokens to every session and 1,695 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.