playwright-agentic

playwright-agentic is a skill for Codex from Mallikarjun-Roddannavar/playwright-agentic-automation. It costs 31 tokens per session (625 once invoked), scanned A, original, MIT.

A set of instructions for working safely in a Playwright UI and API automation codebase. Playwright is a tool for testing web pages and web APIs.

In plain words
What is it for?
Use it to investigate feature impact, work on page objects or API tests, maintain test tooling, and check whether project knowledge is current.
Why use it?
It directs an agent to the right repository guidance and checks before changing tests, framework code, or related knowledge.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit Use it to investigate feature impact, work on page objects or API tests, maintain test tooling, and check whether project knowledge is current.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mallikarjun-roddannavar/playwright-agentic-automation/playwright-agentic
Install

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.

Any agent
npx skills add Mallikarjun-Roddannavar/playwright-agentic-automation --skill playwright-agentic
Clone the repo
git clone --depth 1 https://github.com/Mallikarjun-Roddannavar/playwright-agentic-automation

Made for: Codex.

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 playwright-agentic

README.md
[![agentmods](https://agentmods.dev/badge/skills/mallikarjun-roddannavar/playwright-agentic-automation/playwright-agentic/github.svg)](https://agentmods.dev/skills/mallikarjun-roddannavar/playwright-agentic-automation/playwright-agentic)
Your own site
<a href="https://agentmods.dev/skills/mallikarjun-roddannavar/playwright-agentic-automation/playwright-agentic"><img src="https://agentmods.dev/badge/skills/mallikarjun-roddannavar/playwright-agentic-automation/playwright-agentic/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 playwright-agentic

Your own site · 80×15
<a href="https://agentmods.dev/skills/mallikarjun-roddannavar/playwright-agentic-automation/playwright-agentic"><img src="https://agentmods.dev/badge/skills/mallikarjun-roddannavar/playwright-agentic-automation/playwright-agentic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 625 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 $0.00031 $0.00625
Opus 5 $0.00015 $0.00313
Sonnet 5 $0.00006 $0.00125
Haiku 4.5 $0.00003 $0.00063

Measured 3d ago against content hash 3f9becf97222, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

playwright-agentic 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 3d 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.

skills/playwright-agentic/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Playwright Agentic

Use this entry skill inside a checkout of playwright-agentic-automation when a task spans framework conventions, product behavior, UI/API automation, or impact analysis. It is a routing guide for an external coding agent; it does not invoke an LLM or make changes automatically.

Start safely

  1. Read AGENTS.md for repository-wide ownership and validation rules.
  2. Run npm run agent:doctor before runtime work when the environment may be new or stale.
  3. For a feature question or impact analysis, read knowledge/index.md, run npm run knowledge:check, and query the narrowest relevant term with npm run knowledge:query -- <term> or npm run knowledge:impact -- <term>.

Route by work type

  • UI Page Objects, UI specs, selectors, or navigation: read .agents/skills/pw-ui-pom/SKILL.md.
  • API services/specs, fixtures, or authentication: read .agents/skills/pw-api-pom/SKILL.md.
  • Scripts, Playwright configuration, linting, reporting, or README tooling claims: read .agents/skills/pw-framework-tooling/SKILL.md.
  • Knowledge freshness, source relationships, traceability, or impact: read .agents/skills/codebase-second-brain/SKILL.md.
  • A cross-layer failure involving UI, API, data, or Playwright evidence: read .agents/skills/full-stack-incident-analyst/SKILL.md.
  • A failed Playwright test, diagnosis-only request, or guarded test repair: read .agents/skills/qa-safe-healing/SKILL.md, then treat qa/failure-taxonomy.json and qa/evidence-schema.json as the policy source of truth.

Use the narrowest relevant skill. When a task spans layers, use the knowledge skill first and then the owning implementation skill.

Evidence boundary

Treat source code, configuration, and executed tests as authoritative. The generated knowledge graph is static evidence, not proof that a path ran. Keep selectors in Page Objects, assertions in tests, and business-meaning changes under human review before they enter active product knowledge.

For a failure, diagnose before modifying. Preserve evidence, classify it, and obey the resulting modification decision. Never weaken assertions, skip/fixme/delete tests, swallow failures, or force actions merely to obtain green output. Run npm run qa:guardrails before accepting a repair.

Read the full file on GitHub · 38 lines

Files

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.

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. 3d ago First seen · 38 lines · 31 tokens per session scan A 3f9becf97222

Subscribe to this mod's changes

playwright-agentic is a skill published in the GitHub repository Mallikarjun-Roddannavar/playwright-agentic-automation (11 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 625 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 2026-09-08.