hayba-physics-interaction

hayba-physics-interaction is a skill for Claude Code, Codex from zajalist/hayba. It costs 29 tokens per session (431 once invoked), scanned A, original, MIT.

A workflow for checking one physical interaction in Unreal, such as pushing a crate, blocking movement, or entering a trigger. It examines collision settings and physics simulation, then tests the expected action in PIE, Unreal's Play In Editor mode.

In plain words
What is it for?
Use it to find the intended object, set or verify its collision and simulation settings, validate the scene, and observe the interaction during a PIE test.
Why use it?
It catches incorrect collision profiles, components that cannot simulate, overlaps, and penetration before they become confusing gameplay bugs. An editor-only impulse is not treated as proof that the player interaction works.

Skill for Claude CodeCodex

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

Good fit Use it to find the intended object, set or verify its collision and simulation settings, validate the scene, and observe the interaction during a PIE test.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zajalist/hayba/hayba-physics-interaction
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-physics-interaction
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-physics-interaction

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-physics-interaction"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-physics-interaction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 431 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 $0.00029 $0.00431
Opus 5.5 $0.00012 $0.00172
Sonnet 5.5 $0.00006 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured 13d ago against content hash c20a99f4f027, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hayba-physics-interaction 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-physics-interaction/SKILL.md · 25 lines

What it actually says

Verify one physical interaction

When to use

Use for one identified primitive component and one expected player action, such as pushing a crate or passing a trigger. Record the required collision response, mass or movement expectation, and the platform's object-count or physics budget if supplied.

Tool routing

  • Find the actor with actor_find and inspect its components through actor_get_components. Run scene_validate_physics to locate overlaps or penetration before changing the setup. Confirm the project collision profile name before physics_set_collision_profile; the tool reads the assigned profile back and rejects a mismatch.
  • Use physics_set_simulate only on the intended primitive. Inspect its returned simulation flag: an accepted setter call can still read back false when the component cannot simulate. physics_add_impulse is an editor-world probe and refuses a non-simulating component; it cannot prove the player interaction in PIE.
  • Re-run scene_validate_physics. For runtime behavior, check editor_get_state, start editor_start_pie, perform the intended input with editor_pie_press_key or editor_pie_click_actor as appropriate, inspect the PIE actor through editor_pie_actor_inspect, and stop with editor_stop_pie. Leave an existing user PIE session alone.
  • For an accepted edit to a placed component, re-read its collision and simulation settings, save the exact active map with level_save, and inspect saved, dirty, and verified status. Re-read the component after saving; if persistence is uncertain, mark the setup unsaved and route it to hayba-world-save-integrity. An editor-world impulse is only a probe and is not a persistent edit.

Evidence

Report actor and component identity, requested and read-back profile, simulation state, collision findings, PIE input and observed response, plus unresolved warnings. Editor-world velocity or a nonpenetrating placement does not prove the runtime control, networking, or player feel.

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 · 25 lines · 29 tokens per session scan A c20a99f4f027

Subscribe to this mod's changes

hayba-physics-interaction is a skill published in the GitHub repository zajalist/hayba (13 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 431 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

unreal-mcp

Automate Unreal Engine editor scenes, actors, and renders.

NousResearch/hermes-agent · 17 tokens

asset-management

Import files from disk (images, meshes, any format the editor imports), export textures, query the Content Browser selection, and check if an asset is open (AssetDiscoveryService). Search, load, save, move, rename, duplicate, and delete assets are handled by Unreal's native AssetTools toolset or EditorAssetLibrary.…

kevinpbuckley/VibeUE · 130 tokens

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.

kevinpbuckley/VibeUE · 64 tokens

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…

kevinpbuckley/VibeUE · 95 tokens

vibeue

Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…

kevinpbuckley/VibeUE · 82 tokens

project-settings

Configure Unreal Engine project settings and editor preferences — UI appearance, toolbar icons, scale, colors, and any UDeveloperSettings subclass (ProjectSettingsService). Use when the user asks to change a project setting or editor preference, configure a UDeveloperSettings category, or read/write project config…

kevinpbuckley/VibeUE · 61 tokens