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.
npx skills add zajalist/hayba --skill hayba-controller-focus-auditgit clone --depth 1 https://github.com/zajalist/haybaWrote 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/skills/zajalist/hayba/hayba-controller-focus-audit)<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.
<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>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 | $0.00030 | $0.00346 |
| Opus 5.5 | $0.00012 | $0.00138 |
| Sonnet 5.5 | $0.00006 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00035 |
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.
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.
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.
- 13d ago First seen · 24 lines · 30 tokens per session scan A b01dfa57e41a
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.
Other skills, from other repositories
pn-game-logic
Guides game loops, state machines, input handling, collision, scoring, and save state. Use when implementing game logic; covers architecture patterns for 2D/3D games.
unreal-playtest-delivery
Use when Unreal Engine work must be compiled, exercised in PIE, saved and reopened, packaged, launched, smoke-tested, or triaged from logs before a completion or delivery claim.
V3 Core Implementation
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.
team-polish
Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.
work
Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.
unity-agent-workflows
Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…