vrc-udon-project-docs

vrc-udon-project-docs is a skill for Codex from sechiro/VRCUdonSkills-for-Codex. It costs 142 tokens per session (787 once invoked), scanned A, original, MIT.

A set of project-owned starter documents for VRChat UdonSharp projects, including setup, system, scene, reference, and agent guidance. Project-owned means the documents describe the specific project's rules and environment.

In plain words
What is it for?
Use it to prepare README and AGENTS.md files, system and environment specifications, official reference maps, scene object rules, Unity editor templates, and optional MCP configuration.
Why use it?
It gives contributors a shared specification and reproducible setup, while keeping project decisions separate from general skill documentation.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions AGENTS.md.

Good fit Use it to prepare README and AGENTS.md files, system and environment specifications, official reference maps, scene object rules, Unity editor templates, and optional MCP configuration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sechiro/vrcudonskills-for-codex/vrc-udon-project-docs
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.

Any agent
npx skills add sechiro/VRCUdonSkills-for-Codex --skill vrc-udon-project-docs
Clone the repo
git clone --depth 1 https://github.com/sechiro/VRCUdonSkills-for-Codex

Made for: Codex.

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 vrc-udon-project-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/sechiro/vrcudonskills-for-codex/vrc-udon-project-docs/github.svg)](https://agentmods.dev/skills/sechiro/vrcudonskills-for-codex/vrc-udon-project-docs)
Your own site
<a href="https://agentmods.dev/skills/sechiro/vrcudonskills-for-codex/vrc-udon-project-docs"><img src="https://agentmods.dev/badge/skills/sechiro/vrcudonskills-for-codex/vrc-udon-project-docs/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 vrc-udon-project-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/sechiro/vrcudonskills-for-codex/vrc-udon-project-docs"><img src="https://agentmods.dev/badge/skills/sechiro/vrcudonskills-for-codex/vrc-udon-project-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 787 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.
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 $0.00142 $0.00787
Opus 5 $0.00071 $0.00394
Sonnet 5 $0.00028 $0.00157
Haiku 4.5 $0.00014 $0.00079

Measured 10d ago against content hash a9b850b47ddc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vrc-udon-project-docs 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 10d 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.

skills/vrc-udon-project-docs/SKILL.md · 57 lines

What it actually says

VRC Udon Project Docs

役割

外部の VRChat UdonSharp プロジェクトに、そのプロジェクト自身が持つべき基本文書一式を入れる。Skill 側の知識と、導入先プロジェクト固有の仕様を分離するための土台を作る。

この Skill を最初に使う場面

  • 新規プロジェクトや外部配布の土台を作る
  • project-owned 文書を先にそろえたい
  • 環境再現手順や公式参照先も含めて渡したい

この Skill を使わない場面

  • モジュールの構造設計だけを進めたい場合: vrc-udon-core-module
  • networking 文書だけを配りたい場合: vrc-udon-networking-rules

進め方

  1. references/doc-pack-guide.md を読む。
  2. assets/templates/ から必要なテンプレートを配置する。
  3. 導入先プロジェクト固有の内容で埋める。
  4. 最低限そろえる。
    • AGENTS.md
    • 必要なら .mcp.json
    • docs/SYSTEM_SPEC.md
    • docs/ENVIRONMENT_SETUP.md
    • docs/OFFICIAL_REFERENCE_MAP.md
    • 必要なら docs/UdonSharpProgramAsset_AutoGeneration.md
    • Builder があるなら docs/SCENE_OBJECT_SPEC.md
    • 入口になる README.md
  5. 仕様追加時の更新責任を project-owned 文書側に寄せる。
  6. imported 情報はそのまま正本にせず、project-owned 文書へ整理して反映する。
  7. UdonSharp の .asset 手動生成漏れを減らしたい案件では assets/templates/Editor/UdonSharpProgramAssetAutoGenerator.cs も配る。
  8. Unity MCP を使う案件では assets/templates/.mcp.json も配り、接続先を project root で管理する。

担当範囲

  • project-owned 文書雛形の配布
  • 環境再現文書の配布
  • 公式参照マップの配布
  • 外部由来コードのライセンス同梱
  • 必要な Editor 補助設定テンプレートの配布

注意点

  • Skill 側の説明をそのまま仕様書にしない
  • 実装責務と Ownership を文書で言い切る
  • imported 参照は project-owned な文章へ翻訳してから残す
  • 環境再現に必要な公式参照先も project-owned 文書として残す
  • .mcp.json は Unity MCP を使う案件だけに配る
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. 10d ago First seen · 57 lines · 142 tokens per session scan A a9b850b47ddc

Subscribe to this mod's changes

vrc-udon-project-docs is a skill published in the GitHub repository sechiro/VRCUdonSkills-for-Codex (58 stars, last pushed 4mo ago), licensed MIT. It adds 142 tokens to every session and 787 once invoked, 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 2026-08-30.

Related

Other skills, from other repositories