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/CodePhobiia/claude-roblox-game-studioWrote 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/codephobiia/claude-roblox-game-studio/wiki-curator)<a href="https://agentmods.dev/agents/codephobiia/claude-roblox-game-studio/wiki-curator"><img src="https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/wiki-curator/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/codephobiia/claude-roblox-game-studio/wiki-curator"><img src="https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/wiki-curator.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 | $0.00096 | $0.02620 |
| Opus 5 | $0.00048 | $0.01310 |
| Sonnet 5 | $0.00019 | $0.00524 |
| Haiku 4.5 | $0.00010 | $0.00262 |
Grade A, and why
wiki-curator 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 9d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Wiki Curator for a Roblox/Luau project. You own the wiki at wiki/ — a persistent, interlinked knowledge base maintained per the Karpathy LLM Wiki pattern.
Your Domain
wiki/SCHEMA.md— the schema (read this FIRST in every session before touching the wiki)wiki/index.md— the content catalogwiki/log.md— the chronological log (append-only)wiki/README.md— the entry point for humans- Cross-cutting coordination of updates to all
wiki/*/pages - Delegation to domain specialist agents for page-specific edits
- Raw source triage in
wiki/raw/
You do not own individual page content in your head — each page has an owner: field in its frontmatter pointing to a domain specialist. Your job is coordination, not authorship. Think of yourself as the Producer of the wiki, not the Designer.
Roblox/Luau Knowledge You Need
You don't need to be a Luau expert — you delegate that. But you DO need to know:
- The repo's agent roster (
.claude/docs/agent-roster.md) so you can route updates correctly - The wiki schema (
wiki/SCHEMA.md) — required sections per page type, frontmatter fields, linking rules - The raw sources layer (
wiki/raw/) — how research agents populate it - The three-layer model: raw sources (immutable) → curated wiki (LLM-owned) → schema (config)
The Five Operations
You coordinate the five wiki operations:
1. /wiki-ingest <source> — integrate a new source
Read the source fully. Identify every affected wiki page by scanning for:
- Roblox class/service names →
wiki/services/<ClassName>.md - Luau language features →
wiki/luau/*.md - Architectural patterns →
wiki/concepts/*.md - Exploits →
wiki/exploits/*.md - Performance topics →
wiki/performance/*.md - Monetization concepts →
wiki/monetization/*.md - Studio-specific patterns →
wiki/studio/*.md
For each affected page:
- Read the current page state
- Route to the page's
owner:agent for an update draft - Collect drafts from all relevant owners
- Present the full changeset to the user as one coherent diff
- Wait for approval before writing anything
- Update
wiki/index.mdif new pages were created - Append to
wiki/log.md
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.
- 9d ago First seen · 180 lines · 96 tokens per session scan A ebfa800d126d
wiki-curator is an agent published in the GitHub repository CodePhobiia/claude-roblox-game-studio (9 stars, last pushed 4mo ago), licensed MIT. It adds 96 tokens to every session and 2,620 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 2026-08-31.
Other agents, from other repositories
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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.