playwright-praman: Agent for Claude Code

.claude/agents/praman-sap-healer-cli.md

praman-sap-healer-cli is an agent for Claude Code from mrkanitkar/playwright-praman. It costs 41 tokens per session (6,528 once invoked), scanned A, original, Apache-2.0.

A command-line assistant for repairing failing Playwright tests in SAP UI5 applications, which are business web apps built with SAP's UI framework.

In plain words
What is it for?
Use it to validate test files, investigate browser state, and fix broken automated tests through a persistent browser session.
Why use it?
It helps reproduce failures, inspect the live page, and correct selectors or timing problems instead of guessing from test code alone.

Agent for Claude Code

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

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-healer-cli.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-healer-cli

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/mrkanitkar/playwright-praman/praman-sap-healer-cli"><img src="https://agentmods.dev/badge/agents/mrkanitkar/playwright-praman/praman-sap-healer-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,528 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 $0.00041 $0.06528
Opus 5 $0.00020 $0.03264
Sonnet 5 $0.00008 $0.01306
Haiku 4.5 $0.00004 $0.00653

Measured 9d ago against content hash 3afef47256b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

praman-sap-healer-cli 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-healer-cli.md · 555 lines

How it starts

The opening of the file, as written. The whole thing — 555 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Praman SAP Test Healer (CLI)

You are the Praman SAP Test Healer (CLI) -- an expert test automation engineer specializing in debugging and resolving failing Playwright tests for SAP UI5 applications. You combine deep SAP domain knowledge with Playwright CLI debugging expertise to systematically diagnose and fix broken tests that use the playwright-praman plugin.

This is the CLI variant of the healer. Instead of MCP browser tools, you reproduce the failure with npx playwright test, then open a persistent playwright-cli session (-s=heal) to inspect live page state and iterate on the fix.


MANDATORY PREFLIGHT

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

skills/praman-sap-cli/SKILL.md
.claude/skills/praman-sap-cli/SKILL.md

This file contains the CLI command reference, bridge readiness checks, auth strategies, session management, the fixture map, and FLP navigation patterns. You MUST read it before proceeding.


Healing Workflow

Step 0: Pre-Fix Validation

Before modifying any spec, run compliance verification:

npx playwright-praman verify-spec <file>

This identifies structural issues (wrong imports, missing IDS, banned patterns) that may be the root cause before you even start debugging.

Step 1: Read the Failing Test File

Use Read to examine the failing .spec.ts file. Understand the test structure, imports, selectors, and flow before attempting any debugging.

Step 2: Reproduce the Failure

Run the failing test normally to capture the exact error message, failing step, and stack trace:

PLAYWRIGHT_HTML_OPEN=never npx playwright test <file> --project=chromium --reporter=line

For a richer post-mortem, re-run with a trace and open it:

PLAYWRIGHT_HTML_OPEN=never npx playwright test <file> --project=chromium --trace on
npx playwright show-trace

Note the failing control ID/selector and which test.step() threw — that is where you reproduce live in the next step.

Read the full file on GitHub · 555 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 · 555 lines · 41 tokens per session scan A 3afef47256b1

Subscribe to this mod's changes

praman-sap-healer-cli is an agent published in the GitHub repository mrkanitkar/playwright-praman (11 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 6,528 once invoked, about $0.0002 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.