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 nonlooped/roblox-suite --skill roblox-datastoresgit clone --depth 1 https://github.com/nonlooped/roblox-suiteWrote 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/nonlooped/roblox-suite/roblox-datastores)<a href="https://agentmods.dev/skills/nonlooped/roblox-suite/roblox-datastores"><img src="https://agentmods.dev/badge/skills/nonlooped/roblox-suite/roblox-datastores/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/nonlooped/roblox-suite/roblox-datastores"><img src="https://agentmods.dev/badge/skills/nonlooped/roblox-suite/roblox-datastores.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.03641 |
| Opus 5 | $0.00046 | $0.01820 |
| Sonnet 5 | $0.00018 | $0.00728 |
| Haiku 4.5 | $0.00009 | $0.00364 |
Grade A, and why
roblox-datastores 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 12d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
roblox-datastores
This skill delivers the authoritative, detailed knowledge required to implement robust, scalable, and safe persistent storage in Roblox experiences using Luau. LLMs often have outdated or incomplete information about the distinctions between datastore variants, the full power of versioning/metadata, configurable rate limits, precise caching behavior, and the exhaustive set of error conditions and quotas.
Primary official sources (consult these for the absolute latest):
- https://create.roblox.com/docs/cloud-services/data-stores
- https://create.roblox.com/docs/cloud-services/data-stores-vs-memory-stores
- https://create.roblox.com/docs/cloud-services/data-stores/versioning-listing-and-caching
- https://create.roblox.com/docs/cloud-services/data-stores/error-codes-and-limits
- https://create.roblox.com/docs/cloud-services/data-stores/best-practices
- https://create.roblox.com/docs/cloud-services/data-stores/data-stores-manager
- https://create.roblox.com/docs/cloud-services/data-stores/observability
- Engine classes: DataStoreService, GlobalDataStore, DataStore, OrderedDataStore, DataStoreOptions, DataStoreKeyInfo, DataStoreSetOptions, etc. (full reference at https://create.roblox.com/docs/reference/engine)
Progressive disclosure in this skill:
- Start here in SKILL.md for high-level decision making, recommended workflows, and checklists.
- Read specific files in
references/for exhaustive technical details, tables, code samples, and edge cases when you need to implement or debug a particular aspect. - Treat
scripts/as maturity-labeled examples; adapt and test them in a dedicated experience.
When to use this skill
Activate for:
- Implementing player data saving (progress, inventory, currency, settings, cosmetics).
- Creating or querying leaderboards (persistent sorted numeric data).
- Any cross-server or cross-place persistent state.
- Bulk operations, data migration, or cleaning up old data.
- Handling "right to be forgotten" (RTBF) / GDPR-style requests.
- Debugging data loss, throttling errors, quota issues, or inconsistent reads.
- Choosing between DataStores and MemoryStores (or combining them).
- Setting up monitoring via Data Stores Manager or the observability dashboard.
- Advanced patterns such as profile services, session locking, or safe concurrent updates.
What ships with it
8 files 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.
- references/best-practices-and-gotchas.md 7.4 KB
- references/core-operations-and-patterns.md 8.4 KB
- references/limits-quotas-throttling-error-codes.md 14 KB
- references/types-of-datastores.md 6.7 KB
- references/versioning-metadata-recovery.md 7.7 KB
- scripts/BudgetMonitor.lua 5.0 KB
- scripts/SafeDataStore.lua 15 KB
- tests/SafeDataStore.spec.lua 1.8 KB
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.
- 12d ago First seen · 249 lines · 91 tokens per session scan A 777897d66a39
roblox-datastores is a skill published in the GitHub repository nonlooped/roblox-suite (14 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 3,641 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
roblox-engineer
!cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/game-test-protocol.md 2>/dev/null || true !cat skills/shared/protocols/quality-gate.md 2>/dev/null || true !cat…
roblox-dev-skill
Core scripting and engine skill for Roblox game development. Covers full-lifecycle development: architecture, Luau scripting, debugging, security, performance, data persistence, networking, and the Roblox Studio environment. MUST use this skill whenever the user mentions: 'Roblox', 'Luau', 'Roblox Studio'…
roblox-best-practices
Framework-agnostic Roblox/Luau coding standards. Use when writing, reviewing, or refactoring any Luau code (Script, LocalScript, ModuleScript) in a Roblox project, or when the user asks to keep best practices in mind as standing guidance — enforces the VARIABLES/FUNCTIONS/INITIALIZATION layout, naming, performance…
professional-game-developer
Universal production game engineering skill — design, build, profile, test, and ship games across Unreal Engine 5, Unity 6 (DOTS), Godot 4.3+, Roblox (Luau), and Web/Custom engines with senior studio-grade architectural discipline. Encompasses all 42 specialized game studio job roles across 6 departments: Game Design…
weppy-roblox-mcp-guide
Use when controlling Roblox Studio through WEPPY Roblox MCP, choosing MCP tool actions, selecting among multiple connected Studio targets, creating or checking UI Studio interfaces, running playtests, inspecting logs, or verifying direct Studio workflows.
weppy-roblox-sync-guide
Use when working with WEPPY Roblox MCP Studio-local sync, effective policy, bidirectional file mirrors, multi-place project folders, conflicts, reverse apply and delete safety, sourcemaps, detector recovery, or Roblox Explorer context.