A browser-based checking workflow that compares a running application with the screens and acceptance rules written in its PRD, or product requirements document.

Use it to test the application's specified screens and user scenarios in a browser, provided the required readiness report and Playwright setup are available.

It catches visual differences and functional failures that may not be obvious from reading the code alone.

verify — Skill for Claude Code by VoxTechnologies/transmute-framework

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/VoxTechnologies/transmute-framework

agentmods

npx agentmods add skills/voxtechnologies/transmute-framework/verify

Made for: Claude Code.

Or install transmuter, the plugin that ships this one along with the rest of its 23 skills, 1 command, 7 agents, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/voxtechnologies/transmute-framework/verify/github.svg)](https://agentmods.dev/skills/voxtechnologies/transmute-framework/verify)

Your own site

<a href="https://agentmods.dev/skills/voxtechnologies/transmute-framework/verify"><img src="https://agentmods.dev/badge/skills/voxtechnologies/transmute-framework/verify/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/voxtechnologies/transmute-framework/verify"><img src="https://agentmods.dev/badge/skills/voxtechnologies/transmute-framework/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,256 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.

Model	Per session	Once invoked
Fable 5.1	$0.00100	$0.03256
Opus 5.5	$0.00040	$0.01302
Sonnet 5.5	$0.00020	$0.00651
Haiku 4.5	$0.00010	$0.00326

Measured 20d ago against content hash 004834b78c5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify 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 20d 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/verify/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage 6V: Visual & Functional Verification

Verify the RUNNING application against every screen specification and acceptance criterion in the PRD by navigating the app in a browser. Lead a multi-agent verification project (teammates are Agent-tool subagents; see the pipeline agent's Execution Model).

Read the detailed guide at ${CLAUDE_SKILL_DIR}/references/verification-detailed-guide.md for full teammate prompts, failure patterns, and report templates.

Read the scenario generation guide at ${CLAUDE_SKILL_DIR}/references/feature-scenario-generation.md for the algorithm to build the Feature Scenario Matrix.

Prerequisites

Verify ./plancasting/_launch/readiness-report.md exists and shows READY. If NOT READY or file missing, STOP -- run Stage 6H first. Exception — Stage 5V (early runtime check): when invoked with MODE: critical directly after 5B (alias /transmuter:cast early-verify), require ./plancasting/_audits/implementation-completeness/report.md (PASS or CONDITIONAL PASS) instead of the 6H report, run only the critical scope, and title the report "Stage 5V — Early Runtime Check (6V critical scope)". The full 6V run after 6H overwrites it.

Create output directories:

mkdir -p ./plancasting/_audits/visual-verification
mkdir -p ./screenshots/automated
mkdir -p ./screenshots/criteria
mkdir -p ./screenshots/vision
mkdir -p ./screenshots/visual-verification/baseline
mkdir -p ./e2e/verification

Verify Playwright browsers are installed:

bunx playwright install --with-deps chromium

Scope Modes

full (default) -- All screens in plancasting/prd/08-screen-specifications.md. ~30-60 min.
critical -- P0/P1 features only. ~15-30 min.
diff -- Only screens related to files changed since last verification. ~10-20 min. Note: last-verified-commit.txt is created at the END of a 6V run, so diff mode only works on the second or subsequent run. If the file does not exist, automatically falls back to full. Warning: diff mode requires a previous 6V report to diff against — do not use for the first 6V run.

Read the full file on GitHub · 201 lines

Files

What ships with it

2 files 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.

20d ago Changed · +2 lines 004834b78c5d
1mo ago First seen · 199 lines · 100 tokens per session scan A ef090acff029

Subscribe to this mod's changes

verify is a skill published in the GitHub repository VoxTechnologies/transmute-framework (5 stars, last pushed 9d ago), licensed MIT. It adds 100 tokens to every session and 3,256 once invoked, about $0.0004 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 2026-08-31.

Browser automation Claude Code Code Generation E2E testing Testing ai-agent automation claude-code-plugin plan-casting

e2e-testing-standards

End-to-end testing with Playwright - browser automation, visual regression, test data management.

LiorCohen/sdd · 26 tokens

test-site

Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.

microsoft/power-platform-skills · 46 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

verify