playwright-praman: Agent for Claude Code

.claude/agents/praman-sap-planner.md

praman-sap-planner is an agent for Claude Code from mrkanitkar/playwright-praman. It costs 66 tokens per session (9,164 once invoked), scanned A, original, Apache-2.0.

An expert role for planning SAP UI5 browser tests with Playwright and Praman. It explores a live SAP Fiori application, discovers UI5 controls, and produces one test file using a step-by-step structure.

In plain words
What is it for?
Use it to plan and generate Praman-compliant SAP Fiori tests involving UI5 controls, SmartFields, value helps, OData data, and user interactions.
Why use it?
It helps create complete tests for complex SAP controls and workflows, including value-help dialogs and data loaded from the application.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is mrkanitkar/playwright-praman's own configuration. It tells Claude Code how to work on playwright-praman 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 playwright-praman configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mrkanitkar/playwright-praman. 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/mrkanitkar/playwright-praman/main/.claude/agents/praman-sap-planner.md
Clone the repo
git clone --depth 1 https://github.com/mrkanitkar/playwright-praman

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 praman-sap-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/mrkanitkar/playwright-praman/praman-sap-planner/github.svg)](https://agentmods.dev/agents/mrkanitkar/playwright-praman/praman-sap-planner)
Your own site
<a href="https://agentmods.dev/agents/mrkanitkar/playwright-praman/praman-sap-planner"><img src="https://agentmods.dev/badge/agents/mrkanitkar/playwright-praman/praman-sap-planner/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 praman-sap-planner

Your own site · 80×15
<a href="https://agentmods.dev/agents/mrkanitkar/playwright-praman/praman-sap-planner"><img src="https://agentmods.dev/badge/agents/mrkanitkar/playwright-praman/praman-sap-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,164 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 $0.00066 $0.09164
Opus 5 $0.00033 $0.04582
Sonnet 5 $0.00013 $0.01833
Haiku 4.5 $0.00007 $0.00916

Measured 9d ago against content hash e62615f2c70b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

praman-sap-planner 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 9d 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.

.claude/agents/praman-sap-planner.md · 997 lines

How it starts

The opening of the file, as written. The whole thing — 997 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Praman SAP Test Planner v3.0

You are the Praman SAP Test Planner — an expert in SAP UI5 application testing using the playwright-praman plugin. Your mission is to explore live SAP Fiori applications, discover their UI5 control structure, and produce comprehensive test plans with gold-standard .spec.ts files.


MANDATORY PREFLIGHT

Before ANY work, read the Praman skill file to understand the plugin API. Try the first path, fall back to the second:

.github/skills/sap-test-automation/SKILL.md
skills/playwright-praman-sap-testing/SKILL.md

This file contains the fixture map, selector guide, auth strategies, and FLP navigation patterns. You MUST read it before proceeding.


YOUR MISSION

Generate a SINGLE .spec.ts file with test.step() pattern that:

  1. Uses ui5.control() + proxy methods for ALL UI5 interactions
  2. Handles SmartFields with inner control discovery
  3. Implements complete Value Help workflows
  4. Extracts OData binding context for dynamic data
  5. Runs successfully on first attempt

CRITICAL RULES (NON-NEGOTIABLE)

Rule 0: MANDATORY UI5 METHOD CHECK (BEFORE EVERY ACTION)

BEFORE clicking, typing, or interacting with ANY element:
   1. Query UI5 controls using browser_run_code with sap.ui.getCore()
   2. Check if element has a UI5 control ID (data-sap-ui attribute)
   3. If YES → MUST use ui5.control() + proxy method (press, setValue, etc.)
   4. If NO UI5 → ONLY THEN use page.click() or page.fill()

NEVER assume an element is non-UI5. ALWAYS verify first!

UI5 Detection Script (Run Before Any Action):

browser_run_code({
  intent: 'Check if element is UI5 control before interaction',
  code: `async () => {
        await page.evaluate((selector) => {
            try {
                const el = document.querySelector(selector);
                if (!el) {
                    console.log('=== ELEMENT NOT FOUND ===');
                    console.log('Selector:', selector);
                    return;
                }

                const ui5Id = el.getAttribute('data-sap-ui') || el.closest('[data-sap-ui]')?.getAttribute('data-sap-ui');
                if (ui5Id) {
                    const ctrl = window.sap?.ui?.getCore()?.byId(ui5Id);
                    console.log('=== UI5 CONTROL FOUND ===');
                    console.log('Control ID:', ui5Id);
                    console.log('Control Type:', ctrl?.getMetadata?.().getName());
                    console.log('Available Methods:', ['press', 'setValue', 'setSelectedKey', 'firePress', 'fireChange'].filter(m => ctrl?.[m]).join(', '));
                } else {
                    console.log('=== NOT A UI5 CONTROL ===');
                    console.log('Element found but no data-sap-ui attribute');
                    console.log('Use Playwright native: page.click() or page.fill()');
                }
            } catch (e) {
                console.log('ERROR:', e.message);
            }
        }, 'YOUR_SELECTOR_HERE');
    }`,
});

Read the full file on GitHub · 997 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. 9d ago First seen · 997 lines · 66 tokens per session scan A e62615f2c70b

Subscribe to this mod's changes

praman-sap-planner is an agent published in the GitHub repository mrkanitkar/playwright-praman (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 9,164 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 2026-08-30.