knowledge-acquisition

knowledge-acquisition is a skill for Claude Code, Codex from tyunta/prefab-sentinel. It costs 159 tokens per session (1,383 once invoked), scanned A, original, MIT.

A research workflow for learning how VRChat ecosystem tools work, such as avatar and shader utilities. It records findings in project knowledge files and raises confidence as source-code and Unity-project checks confirm them.

In plain words
What is it for?
Use it to research official docs and source code, inspect installed Unity packages and components, compare findings with real projects, and document reusable usage patterns.
Why use it?
It provides a repeatable way to move from uncertain documentation to verified knowledge before editing assets that depend on these tools.

Skill for Claude CodeCodex

Part of the prefab-sentinel plugin — 6 skills shipped together

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 skills/tyunta/prefab-sentinel/knowledge-acquisition
Any agent
npx skills add tyunta/prefab-sentinel --skill knowledge-acquisition
Clone the repo
git clone --depth 1 https://github.com/tyunta/prefab-sentinel

Made for: Claude Code, Codex.

Or install prefab-sentinel, the plugin that ships this one along with the rest of its 6 skills.

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 knowledge-acquisition

README.md
[![agentmods](https://agentmods.dev/badge/skills/tyunta/prefab-sentinel/knowledge-acquisition.svg)](https://agentmods.dev/skills/tyunta/prefab-sentinel/knowledge-acquisition)
Your own site
<a href="https://agentmods.dev/skills/tyunta/prefab-sentinel/knowledge-acquisition"><img src="https://agentmods.dev/badge/skills/tyunta/prefab-sentinel/knowledge-acquisition.svg" alt="Measured on agentmods" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,383 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00159 $0.01383
Opus 5 $0.00079 $0.00691
Sonnet 5 $0.00032 $0.00277
Haiku 4.5 $0.00016 $0.00138

Measured 4d ago against content hash 769f422e6580, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-acquisition 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 4d 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/knowledge-acquisition/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Acquisition Protocol

VRChat エコシステムツールのナレッジを体系的に調査し knowledge/ に蓄積する。

ワークフロー

4 フェーズで段階的に知識の精度を上げる。途中で止めてよい(Phase 1 だけでも confidence: low のナレッジとして価値がある)。

Phase 1: デスクリサーチ (L1 → L2)

  1. Web 検索で公式ドキュメント・README・Wiki を収集する
  2. GitHub リポジトリで README、主要 Issue、リリースノートを読む
  3. ナレッジファイルの「概要」「コンポーネント一覧」「操作パターン」を埋める
  4. confidence を low に設定する

Phase 2: ソースコード分析 (L2 → L3)

  1. GitHub ソースで主要クラスの構造を読む
  2. Unity Packages 内の実コード(検証用 Unity プロジェクトの Packages/ フォルダ)で [SerializeField] を列挙する
  3. Script GUID を .meta ファイルから特定する
  4. ナレッジファイルの「SerializedProperty リファレンス」を埋める
  5. confidence を medium に設定する

Phase 3: 実環境検証 (L3 確定)

前提: 検証用 Unity プロジェクトに対象ツールがインストール済みであること。

  1. prefab-sentinel の inspect ツールで実測する:
    • inspect_wiring: フィールドの配線状態
    • get_unity_symbols: コンポーネント階層
    • inspect_hierarchy: Transform 構造
    • inspect_materials: マテリアル・シェーダー情報
  2. Phase 2 で得た情報と実測値を突合する
  3. 差異があれば実測値を正とし、ナレッジを修正する
  4. confidence を high に設定する

Phase 4: 実プロジェクトでの利用パターン観察 (L2 補強)

前提: 実プロジェクトに対象ツールを使用したアセットが存在すること。

  1. 実プロジェクト内のアセットを inspect して利用パターンを収集する
  2. コンポーネントの組み合わせ、設定値の傾向を抽象化する
  3. 固有名詞(アバター名、衣装名、クリエイター名、販売サイト商品名)は記載しない
  4. 「操作パターン」「実運用で学んだこと」セクションを充実させる

使用する MCP ツール

ツール 用途 フェーズ
inspect_wiring コンポーネントのフィールド配線を実測 Phase 3
get_unity_symbols コンポーネント階層の構造取得 Phase 3
inspect_hierarchy Transform 構造の取得 Phase 3
inspect_materials マテリアル・シェーダー情報の取得 Phase 3
inspect_material_asset マテリアルアセットのシェーダープロパティ詳細取得 Phase 3
Web 検索 / WebFetch 公式ドキュメント取得 Phase 1

実行ルール

  • Phase 1-2 は Unity 環境が無くても実行可能。Phase 3-4 は Unity 実環境が必要。
  • 各フェーズ完了後にナレッジファイルを更新してコミットする。
  • 既に confidence: high かつ version_tested が現在のバージョンと一致する項目は再調査をスキップする。
  • インストール済みバージョンが version_tested と異なる場合、L3 の confidence は暗黙的に low として扱い、再検証を優先する。

ガードレール

  • confidence: high を付けるには inspect による実測検証が必須。
  • Phase 4 で固有名詞(アバター名、衣装名、クリエイター名、販売サイト商品名)を記載しない。
  • 公式ドキュメントの転記はしない。判断材料と実践知識のみ記録する。

次にこれ

Read the full file on GitHub · 86 lines

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. 4d ago First seen · 86 lines · 159 tokens per session scan A 769f422e6580

Subscribe to this mod's changes

knowledge-acquisition is a skill published in the GitHub repository tyunta/prefab-sentinel (11 stars, last pushed 19d ago), licensed MIT. It adds 159 tokens to every session and 1,383 once invoked, about $0.0008 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens