hayba-traversal-playtest

hayba-traversal-playtest is a skill for Claude Code, Codex from zajalist/hayba. It costs 32 tokens per session (409 once invoked), scanned A, original, MIT.

A game-testing workflow for walking a defined, non-combat route in an Unreal level and checking its waypoints, exits, obstacles, visibility, and loading behavior.

In plain words
What is it for?
Use it to replay a bounded player path, capture views at waypoints, validate suspected collisions, and make a narrowly scoped actor adjustment when an obstacle blocks the route.
Why use it?
It finds blocked paths, confusing landmarks, unreachable goals, and route problems that static scene checks may miss. It tests the route during actual play rather than judging only from editor geometry.

Skill for Claude CodeCodex

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

Good fit Use it to replay a bounded player path, capture views at waypoints, validate suspected collisions, and make a narrowly scoped actor adjustment when an obstacle blocks the route.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-traversal-playtest"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-traversal-playtest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 409 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 $0.00032 $0.00409
Opus 5.5 $0.00013 $0.00164
Sonnet 5.5 $0.00006 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 13d ago against content hash 105df98c1357, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hayba-traversal-playtest 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-traversal-playtest/SKILL.md · 25 lines

What it actually says

Walk one player route

When to use

Use for a defined start-to-goal path after geometry or terrain changes. Record the player movement mode, intended waypoints, maximum detour, and which landmarks should be visible. Include the target platform's streaming or frame budget only if supplied.

Tool routing

  • Read scene_export and actor_list to identify route geometry and goal actors. Run placement_validate and scene_validate_physics around suspected blockages. Capture the route entrance with editor_capture_viewport before touching actors.
  • Check editor_get_state, start editor_start_pie, and replay a bounded movement sequence with editor_pie_press_key or repeated editor_pie_axis frames. Use editor_pie_actor_list to locate the runtime goal and editor_pie_screenshot at each waypoint; a screenshot request needs a later readiness check. Use editor_pie_sightlines only for sampled collision visibility, not walkability. Always finish with editor_stop_pie if this workflow started the session.
  • If a confirmed obstacle blocks the intended route, change only that actor with actor_transform, then repeat the same path and validators. Route streaming uncertainty to the World Partition workflow.
  • For an accepted obstacle edit, read the actor with actor_inspect, save the exact active map through level_save, inspect saved, dirty, and verified status, and re-read the actor. If persistence is uncertain, mark the fix unsaved and route it to hayba-world-save-integrity.

Evidence

Report waypoints reached, input path, screenshots, obstruction identity, before/after placement findings, and any load or collision warnings. A clear visibility trace or actor presence does not prove navigation or comfortable movement. Mark untraversed branches and subjective readability for manual playtest.

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 · 32 tokens per session scan A 105df98c1357

Subscribe to this mod's changes

hayba-traversal-playtest is a skill published in the GitHub repository zajalist/hayba (13 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 409 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