A command that checks a GUI harness, a test interface used to operate and inspect software through its graphical screen, against required project standards.

It is for validating a local software project or GitHub repository, including its React interface, schema, theme, components, tests, and documentation.

It helps reveal missing folders, files, interface schemas, or setup pieces before the harness is used or delivered.

validate — Command for Claude Code by ImL1s/GUI-Anything

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.

Clone the repo

git clone --depth 1 https://github.com/ImL1s/GUI-Anything

Made for: Claude Code.

Or install gui-anything, the plugin that ships this one along with the rest of its 5 commands.

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/commands/iml1s/gui-anything/validate/github.svg)](https://agentmods.dev/commands/iml1s/gui-anything/validate)

Your own site

<a href="https://agentmods.dev/commands/iml1s/gui-anything/validate"><img src="https://agentmods.dev/badge/commands/iml1s/gui-anything/validate/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/commands/iml1s/gui-anything/validate"><img src="https://agentmods.dev/badge/commands/iml1s/gui-anything/validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 876 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	$0.00000	$0.00876
Opus 5.5	$0.00000	$0.00350
Sonnet 5.5	$0.00000	$0.00175
Haiku 4.5	$0.00000	$0.00088

Measured 1mo ago against content hash e974420b7236, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validate 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 1mo 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.

gui-anything-plugin/commands/validate.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gui-anything:validate Command

Validate a GUI harness against HARNESS.md standards and best practices.

CRITICAL: Read HARNESS.md First

Before validating, read ./HARNESS.md. It is the single source of truth for all validation checks below.

Usage

/gui-anything:validate <software-path-or-repo>

Arguments

<software-path-or-repo> - Required. Either:
- A local path to the software source code
- A GitHub repository URL

What This Command Validates

1. Directory Structure

agent-harness/gui_anything/<software>/ exists
src/, agent-harness/, utils/, tests/ subdirectories present
package.json in agent-harness/ root

2. Required Files

README.md — Installation and usage guide
gui-schema.json — A2UI schema (source of truth)
theme.json — Visual theme configuration
src/App.tsx — Main application component
src/main.tsx — React entry point
src/components/A2UIRenderer.tsx — Schema renderer
src/components/ActionPanel.tsx — Form generator
src/components/PreviewPane.tsx — Output display
src/components/StatusBar.tsx — Status indicator
src/styles/global.css — Responsive theme
agent-harness/mcp-tools.json — MCP tool definitions
tests/TEST.md — Test plan and results
../<SOFTWARE>.md — Software-specific SOP

3. A2UI Schema Standards

Has metadata with title and description
Has surfaces array with at least one surface
Has actions object with at least one action
Every action has handler, group, and parameter definitions
All component types are valid A2UI types

4. MCP Tool Standards

Every schema action has a matching MCP tool
Tool names use __ double-underscore as group separator
Every tool has valid inputSchema
Special tools present: take_screenshot, get_gui_state, navigate_to
Tool count = action count + 3 (special tools)

5. Theme Standards

Has colors with: primary, accent, background, surface, text
Has fonts with: family, sizes
Has spacing and radius values
All color values are valid CSS (hex, hsl, or rgb)

Read the full file on GitHub · 110 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.

1mo ago First seen · 110 lines · 0 tokens per session scan A e974420b7236

Subscribe to this mod's changes

validate is a command published in the GitHub repository ImL1s/GUI-Anything (5 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 876 tokens. 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.

E2E testing React Testing ai-agent cross-platform gui mcp plugin

verify-bug

Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.

HoangNguyen0403/agent-skills-standard · 0 tokens

test-loop

Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).

HoangNguyen0403/agent-skills-standard · 0 tokens

qa

Live-app real-user QA pass derived from the spec.

gmickel/flow-next · 12 tokens

e2e-testing

:::info The Playwright suite launches the real Electron main process and built React UI on Windows and macOS. It exercises the preload bridge, IPC handlers, and file storage. See Testing Commands for the separate Vitest suite. ::.

JNTMTMTM/eIsland · 0 tokens

qa

Pre-PR quality gate — browser-driven QA for web changes with a mandatory evidence packet against a provisioned environment. No QA-passed claim without artifacts. Workspace-aware. For a quick behavioral check without the evidence packet, prefer the bundled /verify or /run.

HigorAlves/orc · 53 tokens

explain

Build a narrated "what was made" walkthrough from a QA packet — golden-path demo clips (Playwright, overlays off) + animate motion graphics + local kokoro-js voice, assembled by orc-explain; one preview gate before render; delivered via the evidence-publish gates. Use after /orc:qa passes or on any .orc evidence…

HigorAlves/orc · 72 tokens