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 makifbaysal/tasktrooper --skill game-performance-budgetgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/game-performance-budget)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/game-performance-budget"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-performance-budget/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/makifbaysal/tasktrooper/game-performance-budget"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-performance-budget.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 | $0.00053 | $0.01698 |
| Opus 5.5 | $0.00021 | $0.00679 |
| Sonnet 5.5 | $0.00011 | $0.00340 |
| Haiku 4.5 | $0.00005 | $0.00170 |
Grade A, and why
game-performance-budget 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 4d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Performance Budget
Overview
A game has a hard deadline every frame. Miss it and the player sees a hitch, whatever the average says. Performance work is therefore budgeting and measuring, not guessing: know the budget, measure before, change one thing, measure after, write both numbers down.
Core principle: No optimisation without a before and after measurement on the same scene, build type and machine. No hot-path change without proof it did not get slower.
The budget
| Target | Frame budget | Typical for |
|---|---|---|
| 30 FPS | 33.3 ms | low-end mobile, some console cinematics |
| 60 FPS | 16.67 ms | default for this agent unless the task or repo says otherwise |
| 90 FPS | 11.1 ms | VR minimum |
| 120 FPS | 8.33 ms | high-refresh displays, competitive games |
| 144 FPS | 6.94 ms | PC competitive |
Split it per system and leave headroom. An example 60 FPS CPU split (replace with the repository's own if it has one):
| System | Budget |
|---|---|
| Gameplay scripts | 3.0 ms |
| Physics | 2.0 ms |
| AI and pathfinding | 2.0 ms |
| Animation | 1.5 ms |
| Rendering (CPU submit) | 4.5 ms |
| UI | 1.0 ms |
| Audio | 0.5 ms |
| Headroom (OS, spikes, GC) | 2.17 ms |
GPU time is a separate 16.67 ms; a frame is bound by whichever of CPU or GPU is slower. Memory gets a per-platform ceiling, and mobile adds thermal throttling: a game that holds 60 for two minutes and then drops is over budget.
Measure with the engine's tools
| Engine | Frame/CPU | Allocations / memory | Instrument your code |
|---|---|---|---|
| Unity | Profiler (CPU, Rendering, Physics modules), Profile Analyzer for before/after | Profiler GC Alloc column, Memory Profiler | ProfilerMarker / using (marker.Auto()); Performance Testing package Measure.Method |
| Godot | Debugger → Profiler, Visual Profiler, Monitors | Monitors: object/resource/node counts, static memory | Performance.get_monitor(...), Time.get_ticks_usec() around a block |
| Unreal | stat unit, stat game, stat gpu, Unreal Insights (-trace=cpu,frame,gpu) |
memreport -full, LLM (-llm) |
TRACE_CPUPROFILER_EVENT_SCOPE(Name), SCOPE_CYCLE_COUNTER |
| Web | Chrome Performance panel (Bottom-up), renderer.info (three.js), Babylon Inspector |
Memory panel heap snapshots before/after a scene change | performance.mark / performance.measure |
| Bevy | FrameTimeDiagnosticsPlugin + LogDiagnosticsPlugin, Tracy via the trace_tracy feature |
Tracy memory | info_span!("name").entered() |
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.
- 4d ago First seen · 122 lines · 53 tokens per session scan A b16342a9fa29
game-performance-budget is a skill published in the GitHub repository makifbaysal/tasktrooper (112 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 1,698 once invoked, about $0.0002 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 2026-10-09.
Other skills, from other repositories
i4h-workflow-train-rl
Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.
openclaw-plugin
You are an autonomous agent in a persistent world. Your character is in SOUL.md. World rules are in WORLD.md.
ramp
Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.
LLM Wiki Maintainer
Use the LLM Wiki plugin tools to maintain a cited local company wiki.