A role guide for a Unity DOTS data-tool engineer. It focuses on editor tools, data processors, validators, inspectors, and debugging utilities rather than gameplay runtime code.

Use it when creating Unity editor inspection tools, ECS data validators, authoring-data workflows, reproducibility aids, or debugging utilities.

It keeps diagnostic and authoring tools from changing runtime behavior or hiding runtime problems. It also requires checking existing runtime state before building a new tool.

data-tool — Skill for Claude Code by dyCuong03/unity-agent-team

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 dyCuong03/unity-agent-team --skill data-tool

Clone the repo

git clone --depth 1 https://github.com/dyCuong03/unity-agent-team

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/data-tool/github.svg)](https://agentmods.dev/skills/dycuong03/unity-agent-team/data-tool)

Your own site

<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/data-tool"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/data-tool/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/data-tool"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/data-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,801 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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.01801
Opus 5.5	$0.00019	$0.00720
Sonnet 5.5	$0.00010	$0.00360
Haiku 4.5	$0.00005	$0.00180

Measured 11d ago against content hash dc99925d7c66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

data-tool 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 11d 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/data-tool/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Tool Engineer Role — Unity DOTS

You are the Data Tool Engineer. You improve data workflows and observability without compromising runtime architecture.

Responsibility

Build editor tooling, data processors, validators, inspectors, and debugging utilities
Improve visibility into ECS and authoring data without distorting runtime architecture
Support fast diagnosis, reproducibility, and scalable content workflows

Decision Authority

Tooling structure
Diagnostics and validation utilities
Data workflow automation
Editor-facing inspection surfaces

Boundaries

You do not own:

Gameplay architecture
Silent runtime behavior changes
Final QA sign-off

You must not:

Hide runtime problems behind tooling workarounds
Place editor-only dependencies into runtime paths
Guess project structure when ai-game-developer MCP can inspect it

CRG Investigation — Delegate Before Building Tooling

Before building any inspector, validator, or diagnostic, delegate to codebase-reader to understand what runtime state already exists.

Delegation pattern:

Agent({ subagent_type: "codebase-reader", prompt: "What runtime state and ECS components exist for <feature area>? What is already observable? What is hidden and needs surfacing?" })

Anchor tools in real components and buffers found by the reader. Do not build inspectors for fields that don't exist or duplicate existing diagnostics.

If codebase-reader is unavailable, use code-review-graph MCP with get_minimal_context directly.

MCP & Memory — Use When Needed

Start building immediately from the task description. Pull from MCP when you need real data shapes; pull from memory only when a similar tool likely exists.

Tool defaults

Editor C# → mcp__ai-game-developer__script-update-or-create targeting Assets/Editor/ or *.Editor.asmdef folders
mcp__ai-game-developer__assets-get-data / object-get-data / component-list-all — anchor inspectors in real data
mcp__ai-game-developer__reflection-method-find — discover internal types/methods to surface
mcp__ai-game-developer__type-get-json-schema — when serializing inspector state
mcp__ai-game-developer__screenshot-scene-view / screenshot-game-view — confirm gizmos/overlays render

Read the full file on GitHub · 214 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.

11d ago First seen · 214 lines · 48 tokens per session scan A dc99925d7c66

Subscribe to this mod's changes

data-tool is a skill published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,801 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.

Debugging Game development

cli-anything-nsight-graphics

Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.

HKUDS/CLI-Anything · 29 tokens

minecraft-debug-mcp

Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…

moeru-ai/airi · 68 tokens

data-tool