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.
git clone --depth 1 https://github.com/ImL1s/GUI-AnythingWrote 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.
[](https://agentmods.dev/commands/iml1s/gui-anything/test)<a href="https://agentmods.dev/commands/iml1s/gui-anything/test"><img src="https://agentmods.dev/badge/commands/iml1s/gui-anything/test/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.
<a href="https://agentmods.dev/commands/iml1s/gui-anything/test"><img src="https://agentmods.dev/badge/commands/iml1s/gui-anything/test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00512 |
| Opus 5.5 | $0.00000 | $0.00205 |
| Sonnet 5.5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
test 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gui-anything:test Command
Run tests for a GUI harness and update TEST.md with results.
CRITICAL: Read HARNESS.md First
Before running tests, read ./HARNESS.md. It defines the test standards,
expected structure, and what constitutes a passing test suite.
Usage
/gui-anything:test <software-path-or-repo>
Arguments
-
<software-path-or-repo>- Required. Either:- A local path to the software source code
- A GitHub repository URL
The software name is derived from the directory name. The agent locates the GUI harness at
<software-name>/agent-harness/.
What This Command Does
- Locates the GUI harness — Finds the harness based on the software path
- Validates schema — Checks
gui-schema.jsonfor required fields and valid types - Validates structure — Checks all required files exist per HARNESS.md spec
- Validates theme — Checks
theme.jsonfor valid CSS values - Validates MCP tools — Checks
mcp-tools.jsonfor completeness - Runs test suite — Executes any test files in the tests/ directory
- Updates TEST.md — Appends results to the Test Results section
- Reports status — Shows pass/fail summary
Test Output Format
The command appends to TEST.md:
## Test Results
Last run: 2025-01-15 14:30:00
Schema validation: PASS (15 checks) Structure validation: PASS (12 files) Theme validation: PASS (8 properties) MCP tools validation: PASS (18 tools)
**Summary**: All 4 validation layers passed
Example
# Run all tests for calculator GUI
/gui-anything:test ./calculator
# Run tests for image editor
/gui-anything:test https://github.com/user/image-editor
Success Criteria
- All validation layers pass
- TEST.md is updated with full results
- No validation errors
- Schema actions count matches MCP tools count
Failure Handling
If tests fail:
- Shows which validations failed with details
- Does NOT update TEST.md (keeps previous passing results)
- Suggests fixes based on error messages
- Offers to re-run after fixes
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 · 79 lines · 0 tokens per session scan A 6bb1b1f1f08c
test 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 512 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.
Other commands, from other repositories
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.
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, revision-bound evidence, and PR-ready output.
verify-work
Verify feature, bug, UI, API, mobile, security, or deployment work against acceptance criteria.
cyber-purple-validation
Controlled purple validation using paired action-observation evidence and explicit defensive outcomes.
plugin-commands
:::info This document covers all build, test, and smoke commands for eIsland native plugins. Windows plugins live under plugins/windows/; macOS helpers live under plugins/macos/. Each plugin has its own package.json with independent scripts. ::.
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. ::.