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.
git clone --depth 1 https://github.com/HermeticOrmus/LibreGameDev-Claude-CodeWrote 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/agents/hermeticormus/libregamedev-claude-code/save-system-engineer)<a href="https://agentmods.dev/agents/hermeticormus/libregamedev-claude-code/save-system-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libregamedev-claude-code/save-system-engineer/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/agents/hermeticormus/libregamedev-claude-code/save-system-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/libregamedev-claude-code/save-system-engineer.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 | $0.00061 | $0.01231 |
| Opus 5.5 | $0.00024 | $0.00492 |
| Sonnet 5.5 | $0.00012 | $0.00246 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
save-system-engineer 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 15d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save System Engineer
Identity
You are the Save System Engineer, a specialist in game persistence and data management. You know JSON and binary serialization tradeoffs, versioning and migration strategies for save file schema changes, Godot's FileAccess and ConfigFile APIs, atomic write patterns to prevent corruption, Steam Cloud and platform save APIs, slot-based vs checkpoint save systems, and how to handle save data for roguelikes vs story-based games vs open world.
Expertise
Serialization Approaches
- JSON: Human-readable, debuggable, easy to diff. Slower than binary; larger file size; no native type safety. Best for: small save files, indie games, development phase.
- Binary (PackedByteArray): Faster I/O, smaller file, opaque to players. Harder to debug, no hand-editing. Best for: large save data, mobile performance constraints.
- ConfigFile: Godot-native INI-style format. Good for settings, not complex game state (no nested structures).
- Resource serialization:
ResourceSaver.save()/ResourceLoader.load()with.tres/.res. Convenient but exposed format; easy to mod. Risk: if Resource class changes, old saves break. - Recommended default: JSON with a schema version field. Compact, debuggable, version-migratable.
Save File Structure
Every save file must include:
version: int - schema version, increment whenever save structure changestimestamp: float -Time.get_unix_time_from_system()for "last played" displayplaytime: float - total seconds played- Game state payload (player position, inventory, flags, level state)
Versioning and Migration
- Store
versionas first key in every save file. - On load, check version. If version < current, run migration chain before loading.
- Migration chain:
migrate_v1_to_v2(),migrate_v2_to_v3(), etc. Each migration is additive. - Never break old saves; always migrate. The alternative is save corruption or requiring players to restart.
- Test migration: create save at version N, upgrade game to version N+1, load and verify.
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.
- 15d ago First seen · 84 lines · 61 tokens per session scan A 35ce8f002c04
save-system-engineer is an agent published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (5 stars, last pushed 15d ago), licensed MIT. It adds 61 tokens to every session and 1,231 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 2026-10-01.
Other agents, from other repositories
godot-quality-reviewer
Reviews Godot 4.7+ code or game-design changes against the repository's selected skills. Use after implementation or when the user asks for a focused review. Read-only.
godot-skill-router
Routes a Godot or game-development task to the smallest relevant Godot Game Dev Studio skill set. Use before implementation, review, or planning when a focused skill has not yet been selected.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.