verify

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

In plain words
What is it for?
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.
Why use it?
It catches visual differences and functional failures that may not be obvious from reading the code alone.

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/voxtechnologies/transmute-framework/verify
Any agent
npx skills add VoxTechnologies/transmute-framework --skill verify
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/transmute-framework

Made for: Claude Code, Codex.

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,123 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00100 $0.03123
Opus 5 $0.00050 $0.01562
Sonnet 5 $0.00020 $0.00625
Haiku 4.5 $0.00010 $0.00312

Measured 2d ago against content hash ef090acff029, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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 · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 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 using Claude Code Agent Teams.

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

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

Prerequisites

  1. Verify ./plancasting/_launch/readiness-report.md exists and shows READY. If NOT READY or file missing, STOP -- run Stage 6H first.
  2. 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
    
  3. 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.

How to specify scope: Append MODE: full, MODE: critical, or MODE: diff on a new line after pasting the prompt, or as a separate follow-up message. Default is full.

Important: This stage uses the FULL generation mode (all priorities) of the Feature Scenario Matrix. Do not use critical or diff scope unless explicitly requested by the user.

Read the full file on GitHub · 199 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.

  1. 2d 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 (4 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 3,123 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

codegen-html

Scaffold and iterate on standalone Preact + HTM applications with zero build dependencies.

initializ/forge · 20 tokens

wasm-bindings

wasm-bindgen conventions for compiling a Rust core to WebAssembly for JavaScript: wasm-pack packaging, JsValue mapping, async futures, bundle-size tuning, web-sys/js-sys, and TypeScript defs. Load when generating or reviewing WebAssembly/JS bindings for a Rust library.

Goldziher/ai-rulez · 64 tokens

uiux

Establishes a design philosophy based on kickoff outputs, and generates a design system/wireframes/HTML prototype. Recommended flow — /prd → /kickoff → /uiux.

pillip/claude-dev-kit · 39 tokens

vgpu-shaders

Decide whether a Next.js 16 project should reach for WebGPU at all, then wire vgpu in: the .wgsl loader (Turbopack/webpack), a "use client" canvas that survives SSR, a prefers-reduced-motion path the library omits, a headless render snapshot in CI. Non-visual uses too — compute shaders (compute/dispatch, storage…

lukedj78/dev-flow · 260 tokens

write-tests

Write Vitest unit/integration tests OR Playwright e2e tests for an existing source file (server action, page, component, query). Reads the project's wired test framework from .workflow/meta.json#stack.test, follows the mocking patterns already present in vitest.setup.ts and any sibling test files. Use when the user…

lukedj78/dev-flow · 165 tokens

add-wshcmd

Guide for adding new wsh commands to Wave Terminal. Use when implementing new CLI commands, adding command-line functionality, or extending the wsh command interface.

mits-pl/wove · 36 tokens