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.
npx skills add dcc-mcp/dcc-mcp-unity --skill unity-scenegit clone --depth 1 https://github.com/dcc-mcp/dcc-mcp-unityWrote 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/skills/dcc-mcp/dcc-mcp-unity/unity-scene)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-unity/unity-scene"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-unity/unity-scene/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/skills/dcc-mcp/dcc-mcp-unity/unity-scene"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-unity/unity-scene.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 | $0.00045 | $0.01317 |
| Opus 5.5 | $0.00018 | $0.00527 |
| Sonnet 5.5 | $0.00009 | $0.00263 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
unity-scene 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 8d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Scene
Inspect the hierarchy immediately before using instance IDs. Treat every Unity instance ID as an opaque, session-scoped value and return it unchanged; Unity 6000.5+ emits decimal strings while older Editors retain integer output for compatibility. Both forms are accepted as input. Object creation and transform edits register with Unity Undo.
Do not automatically retry a timed-out mutation. Inspect the project and scene first because the Editor may have completed the original request near the timeout boundary.
Component authoring
Call list_components with a fresh hierarchy ID. Its object_id and component_id
handles expire on domain reload or object destruction. Add by fully qualified type
name; inspect the component before setting exact serialized property paths. Supply
expected_fingerprint to reject concurrent edits. Values support booleans, integers,
floats, strings, enum indices, vectors, colors, rectangles, bounds, and compatible
object references (object_id or an exact Assets/ path). Existing nested fields
and array elements use Unity property paths; array resizing, curves, managed
references, event wiring, and direct prefab asset edits are unsupported in this
iteration. Unsupported fields are marked non-editable.
Batches validate in a SerializedObject before applying and use the command Undo
transaction for failures. Project component lifecycle callbacks can have their own
external side effects; Undo cannot roll those back. Results include normalized
readback and scene/prefab override state. No operation saves content. Review dirty
scenes before the existing save_scene, which saves all open scenes.
Reuse local assets
Use find_assets within Assets or installed Packages, then inspect_asset for
identity and recursive dependency paths. Results are bounded and indicate truncation.
Project and UPM assets are distinguished; their presence does not prove licensing.
These tools do not search or purchase Asset Store products, install packages, import
archives, execute downloaded code, or generate visual previews.
What ships with it
19 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.
- metadata/depends.md 34 B
- scripts/add_component.py 506 B runs code
- scripts/create_game_object.py 513 B runs code
- scripts/create_isolated_scene.py 424 B runs code
- scripts/delete_game_object.py 435 B runs code
- scripts/find_assets.py 493 B runs code
- scripts/inspect_asset.py 440 B runs code
- scripts/inspect_component.py 539 B runs code
- scripts/inspect_game_object.py 438 B runs code
- scripts/inspect_scene.py 472 B runs code
- scripts/instantiate_prefab.py 629 B runs code
- scripts/list_components.py 470 B runs code
- scripts/remove_component.py 556 B runs code
- scripts/reopen_exact_scene.py 468 B runs code
- scripts/save_exact_scene.py 491 B runs code
- scripts/save_scene.py 306 B runs code
- scripts/set_component_properties.py 599 B runs code
- scripts/set_transform.py 820 B runs code
- tools.yaml 16 KB
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.
- 8d ago Changed aafafcc2c459
- 10d ago Changed · +55 lines fc27260c6676
- 22d ago Changed ed100c273aef
- 1mo ago Changed · +18 lines 018d9673f97f
- 1mo ago First seen · 30 lines · 45 tokens per session scan A bcd836a036da
unity-scene is a skill published in the GitHub repository dcc-mcp/dcc-mcp-unity (0 stars, last pushed 10d ago), licensed MIT. It adds 45 tokens to every session and 1,317 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 2026-08-31.
Other skills, from other repositories
unreal-playtest-agent
Domain skill - run screenshot-light PIE playtest episodes with structured entity observations, bounded semantic actions, transition polling, and in-memory traces for QA and external policy or RL runners.
unreal-level
Domain skill - Unreal Engine level and world management: inspect level state, load and save maps, read or edit world settings, and measure native collision distances in Editor or PIE worlds. Not for individual actor transform edits - use unreal-actors for that.
unreal-fab-assets
Acquire free Fab marketplace content through Unreal Engine's official Fab integration, then verify the imported Content Browser assets. Use when the user asks to find, download, add, or import Fab or Unreal Marketplace assets. Not for arbitrary file imports - use unreal-assets instead.
unreal-pie
Domain skill - Unreal Engine Play-In-Editor (PIE) closed-loop verification. Provides PIE lifecycle control (enter/pause/resume/exit), controlled input injection (no OS dependency), viewport screenshot capture, output log snapshot, performance sampling, and Automation Test execution with async job polling. Use for…
unreal-actors
Domain skill - Unreal Engine actor management: list, spawn, transform, and delete level actors. Use when inspecting or editing actors in the current Unreal Editor level. Not for Content Browser asset import/export - use unreal-assets for that.
unreal-assets
Domain skill - Unreal Engine Content Browser asset management: list, import, export, inspect, and delete assets. Use for package and asset operations in the Unreal Editor. Not for actor placement or transforms - use unreal-actors for that.