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-pie-performance-capturegit 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-pie-performance-capture)<a href="https://agentmods.dev/skills/zajalist/hayba/hayba-pie-performance-capture"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-pie-performance-capture/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-pie-performance-capture"><img src="https://agentmods.dev/badge/skills/zajalist/hayba/hayba-pie-performance-capture.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 | $0.00347 |
| Opus 5.5 | $0.00012 | $0.00139 |
| Sonnet 5.5 | $0.00006 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
hayba-pie-performance-capture 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
Capture one repeatable PIE performance sample
When to use
Use when a change needs before/after evidence under the same map, route, viewport, quality settings, and machine load. Record target platform and actual frame or memory budget; if missing, report a baseline without a pass verdict.
Tool routing
- Take world_budget_snapshot for loaded structural counts and record its coverage. Check editor_get_state, start editor_start_pie, settle the scene, then call editor_pie_capture_start for a bounded sample. Poll editor_pie_capture_get by its capture identifier until complete or aborted. Stop with editor_stop_pie after the capture.
- Repeat the same route and sample count after one controlled change. Feed complete compatible snapshots and completed PIE captures to world_compare_snapshots. If scan coverage or captures differ, keep the observed values but withhold the delta verdict. Use editor_get_performance_stats as a separate editor metric, not as interchangeable frame time.
- Inspect warnings, truncated samples, world changes, and aborted captures before concluding anything. A safety refusal while the editor is unsafe is a stop signal, not permission to retry in a loop.
Evidence
Report protocol, capture identifiers and status, sample counts, timing and physical-memory proxies, structural coverage, comparison result, and unknowns. These are whole-editor measurements: GPU time, real World Partition cells, NPC AI cost, packaged-build memory, and a production-performance verdict remain unmeasured.
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 f644de53d918
hayba-pie-performance-capture 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 347 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-mcp
Automate Unreal Engine editor scenes, actors, and renders.
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.…
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.
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…
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…
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…