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-ui-hud-buildgit 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-ui-hud-build)<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-ui-hud-build"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-ui-hud-build/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-ui-hud-build"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-ui-hud-build.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 | $0.00033 | $0.00380 |
| Opus 5.5 | $0.00013 | $0.00152 |
| Sonnet 5.5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
hayba-ui-hud-build 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
Build one HUD screen
When to use
Use for one gameplay HUD or small screen with known player decisions: what must be read, what can be acted on, and which platform and viewport sizes matter. Identify long and localized text examples, controller focus order, and an update-frequency budget for dynamic elements.
Tool routing
- Search ui_list_widget_blueprints and inspect a candidate with ui_get_widget_info. Use ui_create_widget only for a new screen. Build a small hierarchy with ui_add_element or ui_build_tree; the latter can keep a partial subtree on failure, so inspect ui_query before retrying. Use ui_set_slot_layout and focused property tools for geometry, rather than guessing canvas coordinates.
- Check ui_measure_text with ordinary and long strings. Use ui_layout_snapshot and ui_render_widget_to_png at each target viewport. Run ui_validate for text overflow, safe area, touch targets, contrast, focus, and performance findings. Resolve each returned warning or document why the remaining condition is intentional; skipped geometry checks are open, not passing.
- Compile with ui_compile_widget, inspect warnings, then persist with ui_save_widget. If a real gameplay HUD is required, check editor_get_state, start editor_start_pie, inspect editor_pie_widget_tree and a screenshot, and stop with editor_stop_pie. Leave an existing user session alone.
Evidence
Report widget path, hierarchy, target sizes, rendered captures, text/focus findings, compile and save state, PIE display, and every unresolved or skipped validation rule. A good static preview does not establish live data binding or controller navigation.
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 · 33 tokens per session scan A e04ae09804f4
hayba-ui-hud-build is a skill published in the GitHub repository zajalist/hayba (13 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 380 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
controller-ui
Use when building or reviewing Air Jam controller surfaces so touch controls stay simple, readable, and game-appropriate instead of drifting into dense web-app UI patterns.
host-surface
Use when building or reviewing the Air Jam host shell so the active game surface stays full-frame, overlays stay modular, and host UI does not interfere with gameplay layout.
pn-spatial-ux-patterns
Spatial interaction design, AR/VR/XR UX patterns. Depth, scale, ergonomics, interaction zones, text legibility. Use for immersive interface design.
ux-design
Section-by-section UX spec authoring for a screen, flow or HUD. Reads the player journey to provide context; also project-wide accessibility.
level-actors
List, find, place, move, rotate, and modify actors in the current level (ActorService + editor subsystems). Use when the user asks to find/list actors in the level, move or rotate an actor, set an actor's properties/folder/transform, or spawn/delete level actors.
materials
Create and edit materials and material instances — graph nodes, parameters, functions, custom HLSL, and instance overrides (MaterialService + MaterialNodeService). Use when the user asks to create or edit a material/material instance, wire material nodes, add material parameters, set blend/shading modes, or recreate a…