agentmods.dev

skills AGENTS.md

Project instructions for a Roblox Studio skill and local connection used by coding agents. They describe how agents should inspect, plan, test, and safely modify Roblox game content.

In plain words
What is it for?
Use them when building Roblox maps or changing the skill, plugin, or local MCP connection. They guide dry runs, validation, file locations, naming, credentials, and Studio Undo safety.
Why use it?
They reduce the risk of breaking communication protocols, changing the wrong Roblox files, or creating unsafe game assets. They also require checks before changes are considered complete.

Instructions file for CodexOpenCode

1 20d ago A scan 145 tokens original MIT
View the source file ShiroKSH/skills
Install

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.

agentmods
npx agentmods add instructions/shiroksh/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/ShiroKSH/skills

Made for: Codex, OpenCode.

Per session 145 This file is loaded in full into every session.
When invoked 145 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00145 $0.00145
Opus 5 $0.00072 $0.00072
Sonnet 5 $0.00029 $0.00029
Haiku 4.5 $0.00015 $0.00015

Measured 2d ago against content hash 6a8b40488483, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills AGENTS.md 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 2d 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.

AGENTS.md · 14 lines

What it actually says

AGENTS.md

  • Inspect repo first.
  • Plan before broad MCP/plugin/protocol changes.
  • Do not break protocol compatibility without migration notes.
  • Plugin and MCP server changes need a test or manual verification step.
  • Roblox/Luau changes must preserve local-first safety and Studio Undo.
  • Map build flow: prompt -> SceneSpec -> dry-run -> apply -> validate.
  • New maps go under Workspace/MapDrafts.
  • Workspace/AI_Generated accepted for migration only.
  • Do not edit user Workspace outside build roots without explicit permission.
  • Prefer multilevel named structures and unique instance names.
  • No Roblox credentials, .ROBLOSECURITY, or non-allowlisted external asset IDs.
Changes

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.

  1. 2d ago First seen · 14 lines · 145 tokens per session scan A 6a8b40488483

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository ShiroKSH/skills (1 stars, last pushed 20d ago), licensed MIT. It adds 145 tokens to every session, about $0.0007 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 2026-08-31.

Game developmentagent-skillsclaude-codecodexluaumcproblox
Related

Other instructions, from other repositories

professional-game-developer.skill AGENTS.md

Instructions for chahat1709/professional-game-developer.skill, covering agents, layout and agent instructions.

chahat1709/professional-game-developer.skill · 245 tokens

professional-game-developer.skill CLAUDE.md

Instructions for chahat1709/professional-game-developer.skill: See AGENTS.md. Load skills/engineering/professional-game-developer/SKILL.md as the primary skill. Follow its universal 12-step workflow, data-oriented architectural rules, engine-specific mappings, and automated CLI recipes in references/cli-toolchains.md.

chahat1709/professional-game-developer.skill · 62 tokens

code AGENTS.md

Instructions for luumenlabs/code, covering luu code — notes for coding agents and house style.

luumenlabs/code · 346 tokens

raven-roblox-mcp AGENTS.md

AGENTS.md instructions for valrinx/raven-roblox-mcp, covering raven mcp engineering rules, evidence-first workflow and raven-specific invariants.

valrinx/raven-roblox-mcp · 407 tokens

roblox-ai-workflow GEMINI.md

Gemini CLI instructions for schmusch/roblox-ai-workflow, covering roblox ai-workflow — gemini cli entry point, kanonischer doku-index & ki-einstieg, quellenrang (source of truth hierarchy), neue ideen & feature-pipeline (ideen-handoff) and skill activation.

schmusch/roblox-ai-workflow · 1,556 tokens

code CLAUDE.md

Instructions for luumenlabs/code, covering luu code — notes for coding agents and house style.

luumenlabs/code · 346 tokens