agent-skills-vrc-udon: Skill for Claude Code

.claude/skills/unity-vrc-skills-renovator/SKILL.md

unity-vrc-skills-renovator is a skill for Claude Code from niaka3dayo/agent-skills-vrc-udon. It costs 101 tokens per session (2,303 once invoked), scanned A, original, MIT.

A maintenance guide for improving two VRChat development skills: one for UdonSharp code and one for building VRChat worlds with the World SDK.

In plain words
What is it for?
Use it to update SDK support, remove outdated guidance, add missing technical knowledge, improve examples, and raise the quality of those VRChat skills.
Why use it?
It helps keep their instructions accurate as SDK versions change and fills gaps in APIs, coding patterns, components, networking, and optimization advice.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is niaka3dayo/agent-skills-vrc-udon's own configuration. It tells Claude Code how to work on agent-skills-vrc-udon itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-skills-vrc-udon configures →

Reuse

Borrowing it

Nothing to install: this file belongs to niaka3dayo/agent-skills-vrc-udon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/niaka3dayo/agent-skills-vrc-udon/dev/.claude/skills/unity-vrc-skills-renovator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/niaka3dayo/agent-skills-vrc-udon

Made for: Claude Code.

Wrote 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.

agentmods badge for unity-vrc-skills-renovator

README.md
[![agentmods](https://agentmods.dev/badge/skills/niaka3dayo/agent-skills-vrc-udon/unity-vrc-skills-renovator/github.svg)](https://agentmods.dev/skills/niaka3dayo/agent-skills-vrc-udon/unity-vrc-skills-renovator)
Your own site
<a href="https://agentmods.dev/skills/niaka3dayo/agent-skills-vrc-udon/unity-vrc-skills-renovator"><img src="https://agentmods.dev/badge/skills/niaka3dayo/agent-skills-vrc-udon/unity-vrc-skills-renovator/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.

agentmods 80×15 button for unity-vrc-skills-renovator

Your own site · 80×15
<a href="https://agentmods.dev/skills/niaka3dayo/agent-skills-vrc-udon/unity-vrc-skills-renovator"><img src="https://agentmods.dev/badge/skills/niaka3dayo/agent-skills-vrc-udon/unity-vrc-skills-renovator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 8
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Agent Snooping · line 50
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 51
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 5.1 $0.00101 $0.02303
Opus 5 $0.00051 $0.01151
Sonnet 5 $0.00020 $0.00461
Haiku 4.5 $0.00010 $0.00230

Measured 7d ago against content hash e502b307196e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

unity-vrc-skills-renovator 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 7d 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.

.claude/skills/unity-vrc-skills-renovator/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VRC Skills Renovator

Overview

A guide for renovating (filling knowledge, refreshing, and improving quality of) VRChat-related skills in this repository.

Three Pillars of Renovation

Pillar Description Examples
Fill Adding missing knowledge Undocumented APIs, patterns, tips
Refresh Updating outdated information New SDK version support, removing deprecated APIs
Quality Improvement Improving accuracy and coverage of existing knowledge Adding code examples, improving explanations

Target Skills

Path notation: skills/ refers to the skills/ directory at the repository root. rules/ refers to files under skills/unity-vrc-udon-sharp/rules/. This skill itself resides at .claude/skills/unity-vrc-skills-renovator/ (dev-only, not distributed via npm).

Skill Directory Content
unity-vrc-udon-sharp skills/unity-vrc-udon-sharp/ UdonSharp coding, networking, events
unity-vrc-world-sdk-3 skills/unity-vrc-world-sdk-3/ VRC components, layer settings, world optimization

Renovation Procedure

Phase 1: Current State Analysis

  1. Check the active and verified SDK target for each skill
Read: skills/unity-vrc-udon-sharp/SKILL.md
Read: skills/unity-vrc-world-sdk-3/SKILL.md
→ Check the "Active support / last verified" line in each file
  1. Check the file list for each skill
Glob: skills/unity-vrc-udon-sharp/**/*
Glob: skills/unity-vrc-world-sdk-3/**/*

Phase 2: Information Gathering

Execute the following search queries in parallel to collect the latest information:

# Required searches (parallel execution recommended)
1. "VRChat SDK {current year} new features updates changelog"
2. "UdonSharp VRChat SDK 3.{next minor version} changes"
3. "VRChat Worlds SDK {current year} UdonSharp"
4. "VRChat World SDK components new features {current year}"

# Supplementary searches (as needed)
5. "VRChat SDK NetworkCallable parameters"
6. "VRChat SDK persistence PlayerData"
7. "VRChat SDK PhysBones Contacts worlds"

Read the full file on GitHub · 257 lines

Files

What ships with it

5 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.

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. 7d ago Changed e502b307196e
  2. 12d ago First seen · 257 lines · 101 tokens per session scan A ebb8fd15c59c

Subscribe to this mod's changes

unity-vrc-skills-renovator is a skill published in the GitHub repository niaka3dayo/agent-skills-vrc-udon (299 stars, last pushed 7d ago), licensed MIT. It adds 101 tokens to every session and 2,303 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.

Related

Other skills, from other repositories

neo4j-snowflake-graph-analytics-skill

Run Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra, KNN, Node2Vec, FastRP, GraphSAGE) directly inside Snowflake without moving data. Use when running graph algorithms against Snowflake tables via the Neo4j Snowflake Native App ("GDS Snowflake", "graph algorithms in Snowflake", "Neo4j Graph…

neo4j-contrib/neo4j-skills · 222 tokens

neo4j-aura-graph-analytics-skill

Serverless Aura Graph Analytics (AGA) GDS Sessions — covers GdsSessions, AuraGraphDataScience, AuraAPICredentials, DbmsConnectionInfo, SessionMemory, getorcreate, remote graph projection with gds.v2.graph.project and gds.graph.project.remote, gds.v2 session endpoints, gds.v2.graph.construct, AuraDB Cypher API…

neo4j-contrib/neo4j-skills · 189 tokens

neo4j-driver-dotnet-skill

Neo4j .NET Driver v6 — IDriver lifecycle, DI registration (singleton), ExecutableQuery fluent API, ExecuteReadAsync/ExecuteWriteAsync managed transactions, IResultCursor (FetchAsync/ ToListAsync), record value access (.Get /As ), null safety, UNWIND batching, temporal types, await using, EagerResult, object mapping…

neo4j-contrib/neo4j-skills · 187 tokens

neo4j-getting-started-skill

Orchestrates zero-to-running-app in 8 stages — prerequisites → context → provision → model → load → explore → query → build. Each stage reads its own reference file. Supports HITL and fully autonomous operation. Use when starting a new Neo4j project from scratch, provisioning Aura, generating synthetic data, building…

neo4j-contrib/neo4j-skills · 157 tokens

neo4j-aura-agent-skill

Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete, and invoke Aura agents backed by an AuraDB instance. Use when configuring Aura Agent tools (CypherTemplate, SimilaritySearch, Text2Cypher), setting system prompts, deploying agents to REST or MCP endpoints, or invoking agents with…

neo4j-contrib/neo4j-skills · 142 tokens

neo4j-driver-python-skill

Neo4j Python Driver v6 — driver lifecycle, executequery, managed and explicit transactions, async (AsyncGraphDatabase), result handling, data type mapping, error handling, UNWIND batching, connection pool tuning, and causal consistency. Use when writing Python code that connects to Neo4j via GraphDatabase.driver…

neo4j-contrib/neo4j-skills · 186 tokens