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-world-save-integritygit 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-world-save-integrity)<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-world-save-integrity"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-world-save-integrity/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-world-save-integrity"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-world-save-integrity.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 | $0.00029 | $0.00345 |
| Opus 5.5 | $0.00012 | $0.00138 |
| Sonnet 5.5 | $0.00006 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
hayba-world-save-integrity 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
Verify a level save and reload
When to use
Use after a bounded level edit on a scratch or otherwise authorized map, especially before handoff. Identify the exact map, changed actors, expected transforms or folders, and other editors or users who may have unsaved work. This tests authored level persistence, not a player's SaveGame.
Tool routing
- Read level_get_info, actor_list, and world_semantic_snapshot for an identifiable baseline. Check editor_get_state and confirm no conflicting PIE or unsaved work outside the target. Save the current map with level_save using its exact-path guard, and inspect saved, dirty, and verified readback. A map-save result may not prove every external actor package was persisted.
- Reload the same map with level_load only after the save has completed and the current editor session can be replaced safely. Re-read level_get_info, actor_list, and the changed actors with actor_inspect; compare names, paths, transforms, and relationships. Run validator_run after reload.
- If a package is read-only or save verification is uncertain, stop before loading away the editor state. Resolve the package issue or preserve the current session for manual inspection rather than assuming it will survive.
Evidence
Report map path, changed actor identities, before/after readbacks, save response, reload result, validator findings, and unresolved external actor coverage. Matching loaded actors do not prove unloaded World Partition cells or gameplay state persisted.
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 · 29 tokens per session scan A 75bf570268aa
hayba-world-save-integrity 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 345 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…