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-traversal-playtestgit 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-traversal-playtest)<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.
<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>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 | $0.00032 | $0.00409 |
| Opus 5.5 | $0.00013 | $0.00164 |
| Sonnet 5.5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
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.
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.
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 · 25 lines · 32 tokens per session scan A 105df98c1357
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.
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…