product-verification

product-verification is a skill for Claude Code, Codex from rbah31/claude-code-workflow. It costs 112 tokens per session (914 once invoked), scanned A, original, Apache-2.0.

A workflow for checking a running product by using it like a real user. It tests complete journeys such as loading pages, submitting forms, calling APIs, or completing onboarding.

In plain words
What is it for?
Use it before release or after deployment to test critical web, API, bot, billing, or onboarding journeys end to end.
Why use it?
It catches problems that code-level tests may miss, including broken navigation, incorrect responses, and failed user flows.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/rbah31/claude-code-workflow/product-verification
Any agent
npx skills add rbah31/claude-code-workflow --skill product-verification
Clone the repo
git clone --depth 1 https://github.com/rbah31/claude-code-workflow

Made for: Claude Code, 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 product-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/product-verification.svg)](https://agentmods.dev/skills/rbah31/claude-code-workflow/product-verification)
Your own site
<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/product-verification"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/product-verification.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 914 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00112 $0.00914
Opus 5 $0.00056 $0.00457
Sonnet 5 $0.00022 $0.00183
Haiku 4.5 $0.00011 $0.00091

Measured 5d ago against content hash 3a1226767d00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

product-verification scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl` or `requests` for API endpoints
.claude/skills/product-verification/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Verification

You verify that the product works by driving it like a real user. Unit tests check code. You check the product.

Read config.json in this skill directory for project-specific verification config (endpoints, credentials, flows to test). If it doesn't exist or says NOT_CONFIGURED, ask the user to set it up first (see Setup section below).

What you verify

Identify the critical user journeys for this project and drive each one. Common patterns — adapt to what the project actually does:

Web app / Landing page: Load the page, verify key elements render, check all navigation links, verify forms submit, check responsive breakpoints.

API: Hit each public endpoint with valid and invalid inputs. Verify status codes, response shapes, and error messages.

Discord/Slack bot: Send real commands to a test server. Verify responses, embeds, and error handling.

Billing flow: Drive signup → plan selection → checkout → verify access changes. Use test credentials.

Onboarding: Complete the first-run experience. Verify each step is reachable and functional.

For each journey, capture: what you tested, what happened, and whether it matches expectations.

How to verify

Use the tools that match the project's technology. The skill doesn't prescribe specific tools — choose based on what's available and appropriate:

  • curl or requests for API endpoints
  • Playwright or Puppeteer for browser-based flows
  • Discord/Slack API for bot commands
  • Shell scripts for CLI tools
  • Direct database queries to verify state changes

If verification scripts exist in scripts/, use them. If you find yourself writing the same verification code twice, save it as a script for next time.

Output

Save results to the location the caller expects (e.g., monitoring/deploy-validation-*.md if called from a scheduled task, or sprint directory if called during a sprint).

# Product Verification — [date or sprint]

## Environment
[staging/production URL, version deployed]

## Flows tested

### [Flow name] — ✅ Pass / ❌ Fail
- **Steps**: [what was done]
- **Expected**: [what should happen]
- **Actual**: [what happened]
- **Evidence**: [response code, screenshot path, output snippet]

## Summary
X/Y flows passing
[Any critical failures that need immediate attention]

Read the full file on GitHub · 116 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. 5d ago First seen · 116 lines · 112 tokens per session scan A 3a1226767d00

Subscribe to this mod's changes

product-verification is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 112 tokens to every session and 914 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

smoke-test

End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…

bytedance/deer-flow · 0 tokens

agent-production-validator

Agent skill for production-validator - invoke with $agent-production-validator.

ruvnet/ruflo · 16 tokens

agent-tester

Agent skill for tester - invoke with $agent-tester.

ruvnet/ruflo · 15 tokens

agui-dotnet-integration-tests

Write integration tests for the AG-UI .NET SDK. USE FOR: adding a new AG-UI event type and covering it end-to-end, testing SSE or protobuf streaming through the hosting pipeline, verifying AGUIChatClient maps events to ChatResponseUpdate, multi-turn conversation tests, parameterizing a test over Json/Protobuf…

ag-ui-protocol/ag-ui · 176 tokens

agui-dotnet-cross-language-tests

Author cross-language interop tests that verify the AG-UI .NET SDK is wire-compatible with the TypeScript SDK — a Vitest TS client driving a C# CrossLanguage.TestServer over HTTP, both directions, including protobuf byte-parity against @ag-ui/proto. USE FOR: adding or modifying cross-language interop coverage…

ag-ui-protocol/ag-ui · 146 tokens

agui-playwright-validate

Manually validate a running web app or docs site with the Playwright MCP server — navigate pages, assert headings/text/status, check for console errors, hover/click to exercise interactions, take screenshots for human review, and verify visual details such as an icon's color in light vs dark mode by reading computed…

ag-ui-protocol/ag-ui · 199 tokens