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-gameplay-ability-slicegit 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-gameplay-ability-slice)<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-gameplay-ability-slice"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-gameplay-ability-slice/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-gameplay-ability-slice"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-gameplay-ability-slice.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 | $0.00450 |
| Opus 5.5 | $0.00013 | $0.00180 |
| Sonnet 5.5 | $0.00007 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
hayba-gameplay-ability-slice 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.
How it starts
The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a bounded GAS slice
When to use
Use for one ability or attribute effect with an activation trigger and expected state change. Identify the target actor, Ability System Component, authority context, and the effect's duration and magnitude. Define the expected runtime observation before creating assets.
Tool routing
- Check project_list_plugins and get_tool_signature. GAS commands live in an optional satellite plugin; an unknown command can mean that plugin is unavailable. Inspect an existing ability with blueprint_get_info before creating a duplicate.
- Use gas_create_ability and gas_create_effect only for the assets the slice needs. A newly created ability is empty. Use blueprint_inspect_graph, then blueprint_add_node and blueprint_connect_nodes only for confirmed classes and pins, followed by blueprint_compile for actual behavior; never claim the create call wired activation. Read back effect settings with asset_get_info.
- gas_grant_ability and gas_apply_effect can check actor prerequisites in the editor world, but editor grants are not runtime grants. Save compiled assets with asset_save. Verify the real activation path in a configured PIE scenario with editor_get_state, editor_start_pie, editor_pie_actor_inspect, and editor_stop_pie. Do not start a new PIE session when a user session is running.
- Treat an editor-world grant or effect as a probe unless a persistent placed-actor change is explicitly accepted. For an accepted map change, read back that actor, save the exact active map with level_save, inspect saved, dirty, and verified status, and re-read it. If persistence is uncertain, mark the editor change unsaved and route it to hayba-world-save-integrity.
Evidence
List asset paths, component and plugin presence, compile diagnostics, effect policy, editor-world probe result, and the actual PIE activation/attribute observation. If no runtime grant or input path exists, report the slice as incomplete instead of treating asset creation or an editor-world application as gameplay proof.
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 · 33 tokens per session scan A 31c6757ce5f0
hayba-gameplay-ability-slice 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 450 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
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.
ux-acceptance-coordinator
Coordinate black-box, agent-driven UX acceptance journeys against a disposable EmDash admin site. Use when preparing, dispatching, verifying, or reporting a manual browser journey performed by a separate tester agent. Do not use for deterministic Playwright tests or ordinary code review.
ux-acceptance-tester
Perform a goal-driven, black-box UX acceptance journey in a browser and report the path, friction, and observable outcome. Use only in an isolated tester context with a supplied start URL and brief.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
test-playable-web-games
Test a playable browser game end to end with deterministic fixtures and real browser evidence. Use for gameplay QA, regression testing, controls, accessibility, responsive/mobile testing, save flows, console checks, performance smoke tests, and release verification.
godot-e2e
Write and run E2E (end-to-end) game tests using the godot-e2e framework. Python controls a live Godot game over TCP — Locator-based semantic queries, expect() auto-retry assertions, and engine log capture make failures self-diagnosing. Use this skill whenever you need to: Test actual gameplay: player movement…