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-save-and-persistencegit 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-save-and-persistence)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/game-save-and-persistence"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-save-and-persistence/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-save-and-persistence"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-save-and-persistence.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 | $0.00056 | $0.01438 |
| Opus 5.5 | $0.00022 | $0.00575 |
| Sonnet 5.5 | $0.00011 | $0.00288 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
game-save-and-persistence 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Save and Persistence
Overview
A save file outlives the code that wrote it. Players carry saves across updates, crashes happen mid-write, and a lost 40-hour save is the bug players remember. Every save has a version, every older version has a tested migration, and a write never destroys the last good save.
Core principle: Versioned, migrated, written atomically, checked on load — and never deserialized with a format that can execute code.
The format
{
"version": 3,
"savedAtUtc": "2026-10-08T12:00:00Z",
"player": { "levelId": "forest_02", "position": [12.5, 0, -4.0], "hp": 72 },
"inventory": [{ "itemId": "sword_iron", "count": 1 }],
"flags": ["met_blacksmith", "boss_forest_defeated"]
}
- A plain DTO, separate from engine objects: no
GameObject,NodeorAActorreferences, no array indices into data tables — stable IDs only (data-driven-gameplay-design). - Settings (volume, bindings, accessibility) in a separate file from progress, so resetting one never touches the other.
- JSON is readable and diff-able; a compact binary format (MessagePack, protobuf, Godot's
store_varwithout objects) is fine when size matters — the version field stays first.
Migrations
type Migration = (save: any) => any;
const migrations: Record<number, Migration> = {
1: (s) => ({ ...s, version: 2, inventory: s.items.map((id: string) => ({ itemId: id, count: 1 })) }),
2: (s) => ({ ...s, version: 3, flags: Object.keys(s.questState ?? {}).filter((k) => s.questState[k] === "done") }),
};
export function upgrade(raw: any): SaveV3 {
if (typeof raw?.version !== "number") throw new SaveError("unversioned");
if (raw.version > CURRENT) throw new SaveError("from a newer game version"); // refuse, never guess
let s = raw;
while (s.version < CURRENT) s = migrations[s.version](s);
return SaveV3Schema.parse(s);
}
- One migration per version step, never edited after release; each tested with a fixture file captured from that version (
tests/fixtures/saves/v1.json,v2.json). - A save from a newer version is refused with a clear message, not loaded and overwritten.
- Changing a saved field's meaning without bumping the version is the bug this exists to prevent.
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 · 107 lines · 56 tokens per session scan A 09051172e4c8
game-save-and-persistence is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 56 tokens to every session and 1,438 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.
pokemon-player
Play Pokemon games autonomously via headless emulation. Starts a game server, reads structured game state from RAM, makes strategic decisions, and sends button inputs — all from the terminal.
pokemon-player
Play Pokemon via headless emulator + RAM reads.
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.