hayba-controller-focus-audit

hayba-controller-focus-audit is a skill for Claude Code, Codex from zajalist/hayba. It costs 30 tokens per session (346 once invoked), scanned A, original, MIT.

A guided audit of one Unreal Engine menu path using a keyboard or gamepad. It checks which control is selected, how activation and back navigation work, and whether the interface remains readable and usable.

In plain words
What is it for?
It helps test initial focus, next and previous controls, activation, back navigation, widget layout, and each focus transition in a playable editor session.
Why use it?
A menu may work with a mouse while failing when focus moves with buttons or keys. This audit exposes broken focus order, unclear selection, overlap, contrast problems, and targets that are too small.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps test initial focus, next and previous controls, activation, back navigation, widget layout, and each focus transition in a playable editor session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zajalist/hayba/hayba-controller-focus-audit
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.

Any agent
npx skills add zajalist/hayba --skill hayba-controller-focus-audit
Clone the repo
git clone --depth 1 https://github.com/zajalist/hayba

Made for: Claude Code, Codex.

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.

agentmods badge for hayba-controller-focus-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/zajalist/hayba/hayba-controller-focus-audit/github.svg)](https://agentmods.dev/skills/zajalist/hayba/hayba-controller-focus-audit)
Your own site
<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-controller-focus-audit"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-controller-focus-audit/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.

agentmods 80×15 button for hayba-controller-focus-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-controller-focus-audit"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-controller-focus-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 346 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00346
Opus 5.5 $0.00012 $0.00138
Sonnet 5.5 $0.00006 $0.00069
Haiku 4.5 $0.00003 $0.00035

Measured 13d ago against content hash b01dfa57e41a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hayba-controller-focus-audit 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 13d 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.

mcp-tools/hayba-mcp/addons/workflows/hayba-controller-focus-audit/SKILL.md · 24 lines

What it actually says

Audit one controller menu path

When to use

Use for a defined menu route: initial focus, next/previous controls, activate, and back. State target platform, input device, expected focus order, and minimum readable or touch target size where applicable.

Tool routing

  • Read ui_get_widget_info and ui_layout_snapshot, then run ui_validate. Resolve focus, contrast, overlap, and small-target findings at their named widgets. A skipped geometry rule remains open. Use ui_set_widget_properties or ui_set_slot_layout only after inspecting the exact affected widget, then compile and revalidate.
  • Check editor_get_state, start editor_start_pie, inspect editor_pie_widget_tree, and send each gamepad or keyboard step through editor_pie_press_key. Its press-and-release mode returns before the release tick; observe the next frame instead of assuming a completed action. Capture editor_pie_screenshot at each focus transition and activation. Stop with editor_stop_pie after this workflow's session.
  • If live focus identity is not exposed in the widget tree or screenshot, verify it in Unreal's widget reflector or by a human using a controller. Do not infer focus from an OnClicked binding or a mouse click.

Evidence

Report expected and observed focus sequence, activation/back result, captures, compile and validation findings, and input-device gaps. Passing static focus rules does not prove navigation works in the running game, especially after dynamic elements appear.

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. 13d ago First seen · 24 lines · 30 tokens per session scan A b01dfa57e41a

Subscribe to this mod's changes

hayba-controller-focus-audit is a skill published in the GitHub repository zajalist/hayba (13 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 346 once invoked, about $0.0001 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 2026-10-04.

Related

Other skills, from other repositories