A headless test runner for Irreden Engine creations that checks registered graphical user-interface actions and reports each assertion as passing or failing.

Use it after changing GUI interactions to build a creation, run its predefined test shots, read the results, and fail the command when an assertion fails.

It catches broken hover, click, and object-selection behaviour without requiring someone to operate the interface manually.

How jakildev/IrredenEngine configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jakildev/IrredenEngine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jakildev/IrredenEngine/master/.claude/skills/gui-verify/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/jakildev/IrredenEngine

Made for: Claude Code.

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/jakildev/irredenengine/gui-verify/github.svg)](https://agentmods.dev/skills/jakildev/irredenengine/gui-verify)

Your own site

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

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 981 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	$0.00079	$0.00981
Opus 5.5	$0.00032	$0.00392
Sonnet 5.5	$0.00016	$0.00196
Haiku 4.5	$0.00008	$0.00098

Measured 2d ago against content hash 9bf149cb734e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gui-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.

.claude/skills/gui-verify/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gui-verify (Irreden Engine)

The flow lives in docs/agents/skills/gui-verify.md. Read it first, then apply the deltas below.

Deltas (engine repo)

Delta key	Engine value
runner	`scripts/gui-verify.py`
build tool	`fleet-build`
run tool	`fleet-run`
warmup default	`10`

Quick reference

python3 scripts/gui-verify.py IRVoxelEditor                      # builds first
python3 scripts/gui-verify.py IRVoxelEditor --no-build
python3 scripts/gui-verify.py IRVoxelEditor --warmup-frames 20   # timing-sensitive assertions

A run that would outlive the tool window (a Codex command window) starts as the gui-verify job profile instead (FLEET-RUNTIME.md § Long-running jobs); its evidence is the later terminal wait.

Participants

Every creation that registers IRPrefab::GuiTest assertions (git grep -l 'IRPrefab::GuiTest' -- creations). The target arg is the CMake executable; flags after -- reach the creation. Without a session flag a run drives the creation's default shot table.

Creation	Target	Shots / sessions registered in	Invocation
`editors/voxel_editor`	`IRVoxelEditor`	`main.cpp` `kGuiTestShots[]` (default); `session_builder.hpp` (named sessions)	`python3 scripts/gui-verify.py IRVoxelEditor` / `-- --gui-session drag_probe`
`demos/lua_widgets`	`IRLuaWidgetsDemo`	`main_lua.cpp` `kGuiTestShots[]`	`python3 scripts/gui-verify.py IRLuaWidgetsDemo`
`demos/ui_widgets`	`IRUIWidgetsDemo`	`main.cpp` `kShots[]`	`python3 scripts/gui-verify.py IRUIWidgetsDemo`
`demos/shape_debug`	`IRShapeDebug`	`main.cpp` `kHelpOverlayGuiShots`, `kContinuousZoomGuiShots`, `kCullEvictShots`	`python3 scripts/gui-verify.py IRShapeDebug -- --gui-test` (or `--continuous-zoom-gui-test`, `--cull-evict-test`)
`demos/canvas_stress`	`IRCanvasStress`	`main.cpp` `g_hoverCanaryShot`	`python3 scripts/gui-verify.py IRCanvasStress -- --gui-session hover_canary`
`editors/font_maker`	`IRFontMaker`	`main.cpp` `kIdleShots` (default), `kTableShots`, `kEditShots`, `kSampleShots`	`python3 scripts/gui-verify.py IRFontMaker` / `-- --font-maker-test table` (`edit`, `sample`)
`launcher`	`IRLauncher`	`main_lua.cpp` `sessionShots()` (`kMainShots` default, one table per session)	`python3 scripts/gui-verify.py IRLauncher` / `-- --gui-session catalog_tree --catalog-root creations/launcher/test/fixture_root` (every named session but `multi_root` takes the fixture root; `creations/launcher/CLAUDE.md` § Validators)

Read the full file on GitHub · 65 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.

2d ago First seen · 65 lines · 79 tokens per session scan A 9bf149cb734e

Subscribe to this mod's changes

gui-verify is a skill published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 981 once invoked, about $0.0003 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 2026-11-07.

E2E testing Game development Testing

gui-verify next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gui-verifyjakildev/IrredenEngine	Skill	10	today	MIT	A	79	Claude Code
develop-web-gamenetease-youdao/LobsterAI	Skill	6.2k	yesterday	MIT	A	64	Codex
test-playable-web-gamesMengTo/Skills	Skill	7.3k	yesterday	MIT	A	52	Codex
godot-e2evalkor-ai/loom	Skill	1.4k	6d ago	Apache-2.0	A	189	Claude Code
threejs-qa-releasevalkor-ai/loom	Skill	1.4k	6d ago	Apache-2.0	A	63	Codex
pie-testingkevinpbuckley/VibeUE	Skill	820	yesterday	MIT	A	76	Claude Code, Codex
visual-qavalkor-ai/loom	Skill	1.4k	6d ago	Apache-2.0	A	45	Claude Code, Codex

IrredenEngine: Skill for Claude Code