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 agentmods add skills/ukanwat/aaabench/save-systemsnpx skills add ukanwat/aaabench --skill save-systemsgit clone --depth 1 https://github.com/ukanwat/aaabenchWrote 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/ukanwat/aaabench/save-systems)<a href="https://agentmods.dev/skills/ukanwat/aaabench/save-systems"><img src="https://agentmods.dev/badge/skills/ukanwat/aaabench/save-systems.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.01848 |
| Opus 5 | $0.00037 | $0.00924 |
| Sonnet 5 | $0.00015 | $0.00370 |
| Haiku 4.5 | $0.00007 | $0.00185 |
Grade A, and why
save-systems 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 5d 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.
This is a copy
94% identical to save-systems — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save systems
A save file is a serialized snapshot of game state that survives restarts. The hard parts aren't writing bytes — they're choosing what to save, writing it so a crash mid-save can't corrupt it, and reading old saves after you ship a patch. Get those three right and the rest is plumbing.
When to use
- Use to persist progress: player stats, inventory, world flags, settings, positions — across sessions and game updates.
- Use to design save slots, quicksave/autosave, and crash-safe writes.
- Use when old save files break after a content/code change (versioning & migration).
When not to use: for Roblox cloud persistence specifics, use
roblox-datastores. For the data model the save serializes (resources/SOs), use
godot-resources / unity-scriptableobjects. For Godot's FileAccess/
ResourceSaver and user:// paths, defer to the Godot engine skill while
applying the patterns here.
Core workflow
- Decide what state is authoritative. Save the data (hp, position, seed, unlocked flags), not engine objects or scene nodes. You will reconstruct objects from data on load — never serialize live node references.
- Define a versioned schema. Every save embeds a
versioninteger. This is the single most important field for a game you intend to patch. - Pick a format. JSON/text for readability and debuggability; a binary format for size/speed or mild tamper-resistance. Start with JSON.
- Write atomically. Serialize to a temp file, flush, then rename over the real file. A crash leaves either the old save or the new one — never a half-written one.
- Load defensively. Read version → migrate up to current → validate → instantiate. Keep a backup of the last good save and fall back on parse error.
- Autosave on safe boundaries (level change, checkpoint), throttled, and to a separate slot so it can't clobber a manual save.
- Verify: save, fully quit, relaunch, load — and confirm by inspection that state matches. Test loading a save from the previous version.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 168 lines · 74 tokens per session scan A 20dba7985d2f
save-systems is a skill published in the GitHub repository ukanwat/aaabench (378 stars, last pushed 20d ago), licensed MIT. It adds 74 tokens to every session and 1,848 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to save-systems, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
unreal-pie
Domain skill - Unreal Engine Play-In-Editor (PIE) closed-loop verification. Provides PIE lifecycle control (enter/pause/resume/exit), controlled input injection (no OS dependency), viewport screenshot capture, output log snapshot, performance sampling, and Automation Test execution with async job polling. Use for…
unreal-playtest-agent
Domain skill - run screenshot-light PIE playtest episodes with structured entity observations, bounded semantic actions, transition polling, and in-memory traces for QA and external policy or RL runners.
unreal-actors
Domain skill - Unreal Engine actor management: list, spawn, transform, and delete level actors. Use when inspecting or editing actors in the current Unreal Editor level. Not for Content Browser asset import/export - use unreal-assets for that.
unreal-cinematics
Domain skill — Sequencer shot and keyframe orchestration, camera cut tracks, and Movie Render Queue job setup. Use when creating or editing Level Sequences, authoring camera animation, or preparing an MRQ job in Unreal Engine 5. Not for Blueprint scripting (unreal-blueprints) or runtime playback (unreal-runtime).
unreal-fab-assets
Acquire free Fab marketplace content through Unreal Engine's official Fab integration, then verify the imported Content Browser assets. Use when the user asks to find, download, add, or import Fab or Unreal Marketplace assets. Not for arbitrary file imports - use unreal-assets instead.
unreal-metasound
Unreal Engine MetaSound Source authoring through the reflected Builder API: create sources, add typed inputs and exact registered nodes, connect opaque vertex handles, set defaults, inspect nodes, build, save, and validate. Use for procedural audio graphs in Unreal Engine 5.4+. Not for arbitrary asset management or…