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 TabooHarmony/roblox-brain --skill roblox-securitygit clone --depth 1 https://github.com/TabooHarmony/roblox-brainWrote 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/tabooharmony/roblox-brain/roblox-security)<a href="https://agentmods.dev/skills/tabooharmony/roblox-brain/roblox-security"><img src="https://agentmods.dev/badge/skills/tabooharmony/roblox-brain/roblox-security/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/tabooharmony/roblox-brain/roblox-security"><img src="https://agentmods.dev/badge/skills/tabooharmony/roblox-brain/roblox-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00026 | $0.00581 |
| Opus 5 | $0.00013 | $0.00291 |
| Sonnet 5 | $0.00005 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
roblox-security 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 3d 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.
What it actually says
Roblox Security
When to Load
Load for exploit audits and hardening. Covers classic replication, opt-in Server Authority, remote abuse, economy attacks, and DataStore flows. Use roblox-networking for validation and rate-limit implementations.
Quick Reference
Core: Client is always compromised. The server remains the source of truth, but the implementation depends on the authority model.
Authority Models
- Classic replication: validate client requests and custom movement against server state. Never trust client damage, currency, inventory, permissions, or positions.
- Server Authority: with
Workspace.AuthorityMode = Server, the server owns core simulation while clients predict and recover from misprediction. UseBindToSimulation()(requiresWorkspace.UseFixedSimulation), not blanketHeartbeatCFrame correction. Migration is cheap for stock characters but a rewrite-scale commitment for authored simulation (reality check in full.md). - Both: validate attacks, purchases, teleports, dashes, permissions, and custom remotes at the server boundary.
Audit Checklist
CRITICAL: Server-authoritative state · Choose and document the authority model · Validate all arg types · Rate limit remotes · Session-lock DataStore · No client currency mutations · ProcessReceipt verification · No secrets in client or replicated code
HIGH: Validate custom movement and action transitions · BindToClose protection · Atomic trading · Never trust client values · Use InputActions for simulation input in Server Authority projects
MEDIUM: Server cooldowns · server-computed leaderboards · anti-AFK reward checks · TextService filtering
Anti-Patterns
Don't obfuscate client code, use _G for security, kick without logging, over-validate movement, or rely on client anti-cheat.
See references/full.md for detailed examples.
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.
- 3d ago Changed 1550c1b0d36a
- 10d ago First seen · 43 lines · 26 tokens per session scan A 5b8e467a1ff1
roblox-security is a skill published in the GitHub repository TabooHarmony/roblox-brain (42 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 581 once invoked, about $0.0001 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
ai-navigation
Use when implementing AI movement — NavigationAgent2D/3D, steering behaviors, behavior trees, and patrol patterns.
animation-system
Use when implementing animations — AnimationPlayer, AnimationTree, blend trees, state machines, sprite animation, and code-driven animation.
csharp-godot
Use when working with C# in Godot — conventions, GodotSharp API differences from GDScript, project setup, and interop.
export-pipeline
Use when exporting and distributing Godot games — export presets, platform settings, CI/CD with GitHub Actions.
phantom-camera
Use when using the Phantom Camera addon — PhantomCamera2D/3D with priority-based switching, follow and look-at modes, and tween transitions.
3d-essentials
Use when working with 3D-specific systems — materials, lighting, shadows, environment, global illumination, fog, LOD, occlusion culling, and decals in Godot 4.3+.