agentmods.dev

release-qa

release-qa is a skill for Claude Code from AishwaryShrivastav/vibe-testing. It costs 52 tokens per session (514 once invoked), scanned A, original, MIT.

A release-quality testing procedure for web apps built with AI. It uses browser flows and regression checks to assess whether an app is ready to launch.

In plain words
What is it for?
Use it to test, verify, inspect, or approve an AI-built web app before shipping.
Why use it?
It helps find broken user flows and regressions before a web app is released.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vibe-testing plugin — 1 skill, 1 MCP server shipped together

not rated 11repo +5 yesterday A scan 52 tokens original MIT

Good fit Use it to test, verify, inspect, or approve an AI-built web app before shipping.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aishwaryshrivastav/vibe-testing/release-qa
View source ↗ AishwaryShrivastav/vibe-testing testing.tfgstudio.com
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 AishwaryShrivastav/vibe-testing --skill release-qa
Clone the repo
git clone --depth 1 https://github.com/AishwaryShrivastav/vibe-testing

Made for: Claude Code.

Or install vibe-testing, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 release-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/aishwaryshrivastav/vibe-testing/release-qa/github.svg)](https://agentmods.dev/skills/aishwaryshrivastav/vibe-testing/release-qa)
Your own site
<a href="https://agentmods.dev/skills/aishwaryshrivastav/vibe-testing/release-qa"><img src="https://agentmods.dev/badge/skills/aishwaryshrivastav/vibe-testing/release-qa/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 release-qa

Your own site · 80×15
<a href="https://agentmods.dev/skills/aishwaryshrivastav/vibe-testing/release-qa"><img src="https://agentmods.dev/badge/skills/aishwaryshrivastav/vibe-testing/release-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 514 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 $0.00052 $0.00514
Opus 5.5 $0.00021 $0.00206
Sonnet 5.5 $0.00010 $0.00103
Haiku 4.5 $0.00005 $0.00051

Measured 28d ago against content hash 0d1c9c99c4f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-qa 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 28d 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/release-qa/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release QA

Use the vibe-testing MCP tools to turn a broad request such as "test my app" into a release decision backed by browser evidence.

Workflow

  1. Ask for the app URL only when it cannot be inferred from the project. Read VIBE.md for credentials and testing constraints.
  2. Call scan_codebase before browsing. Use its real routes, forms, and generated scenarios instead of inventing coverage.
  3. Call get_context for the feature under test. Build steps from actual field names, selectors, validation, and expected outcomes.
  4. Use login when authentication is required. Never request production credentials in chat; direct the user to place test credentials in VIBE.md.
  5. Use explore_page for broad discovery and execute_scenario for critical paths. Prioritize signup, login, onboarding, the product's main value action, payment, destructive actions, and recovery from errors.
  6. After fixing code, rerun the affected scenario. Use snapshot_diff and route_changes to identify fixes, regressions, and newly exposed routes.
  7. Call generate_report before declaring the app ready.

Release verdict

Report findings in this order:

  • Blockers: failures that prevent the main user outcome, payment, access, or data safety.
  • Regressions: behavior that passed in the previous run and fails now.
  • Major issues: broken paths with a workaround.
  • Minor issues: polish problems that can wait.
  • Evidence: route, action, observed result, expected result, and screenshot reference.
  • Coverage gaps: important paths that could not be tested and why.

Give one verdict: READY, READY WITH KNOWN ISSUES, or BLOCKED. Do not call a release ready when a core path was skipped.

Operating rules

  • Reproduce a failure before changing code.
  • Prefer a small deterministic scenario over a long exploratory script.
  • Verify user-visible outcomes, network failures, console errors, and persisted state.
  • Never claim visual correctness from DOM state alone; inspect the screenshot.
  • Keep tests in the user's existing app and test environment. Do not send real messages, place real orders, or mutate production data without authorization.

Read the full file on GitHub · 40 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. 28d ago First seen · 40 lines · 52 tokens per session scan A 0d1c9c99c4f8

Subscribe to this mod's changes

release-qa is a skill published in the GitHub repository AishwaryShrivastav/vibe-testing (11 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 514 once invoked, about $0.0002 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 2026-09-18.

Browser automationClaude CodeE2E testingTestingai-testingbrowser-testingcursormcp
Related

Other skills, from other repositories

Console Error Hunter

Systematically detect, capture, and categorize browser console errors, warnings, and unhandled exceptions during automated test execution.

PramodDutta/qaskills · 26 tokens

Karma Testing

Comprehensive Karma test runner skill for browser-based JavaScript unit testing with Jasmine, Mocha, or QUnit frameworks, real browser execution, coverage reporting, and CI/CD pipeline integration.

PramodDutta/qaskills · 41 tokens

playwright-e2e

Comprehensive end-to-end testing skill using Playwright for web applications, covering page objects, selectors, assertions, waits, fixtures, and test organization.

PramodDutta/qaskills · 36 tokens

Capybara Testing

Expert-level Capybara acceptance testing skill for Ruby and Rails applications. Covers RSpec integration, DSL methods, scoping, Page Objects with SitePrism, JavaScript interactions, and database cleaning strategies.

PramodDutta/qaskills · 46 tokens

Laravel Dusk Testing

Expert-level Laravel Dusk browser testing skill for PHP/Laravel applications. Covers Chrome-based E2E testing, browser assertions, Page Objects, component testing, authentication helpers, and database integration.

PramodDutta/qaskills · 44 tokens

e2e-testing-claude-code

Make Claude Code write and maintain end-to-end tests like a senior SDET — Playwright and Cypress flows with stable locators, the Page Object Model, fixtures, reused auth state, network mocking, and flake-free CI. Claude Code E2E testing, done right.

PramodDutta/qaskills · 65 tokens