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-projectgit 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-project)<a href="https://agentmods.dev/skills/dcc-mcp/dcc-mcp-unity/unity-project"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-unity/unity-project/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-project"><img src="https://agentmods.dev/badge/skills/dcc-mcp/dcc-mcp-unity/unity-project.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 | $0.00055 | $0.01124 |
| Opus 5.5 | $0.00022 | $0.00450 |
| Sonnet 5.5 | $0.00011 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
unity-project 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Project
Inspect before assuming the active project, scene, Unity version, or Play/compile state.
configure_sprite_importer imports one existing Assets/.../*.png as a single Sprite through
Unity's native TextureImporter; choose point or bilinear filtering and an explicit pixels-per-unit
value. Source writes require the operator-owned environment gate, an Assets/... allowlisted text
path, bounded UTF-8 content, and either expected_sha256: absent for creation or the digest returned
by read_text_asset for replacement.
Every long or domain-reloading mutation keeps its Core async job open until Unity reports a
terminal persistent state. Reuse the same UUID and wait on that job; use
unity_diagnostics__inspect_job for reconnect or audit recovery, and never replace an ambiguous
request with a new ID. Build uses only enabled scenes and writes a new request directory below
Builds/DccMcp.
build_android_player accepts only apk or aab. It uses the project's saved Player Settings,
never accepts signing secrets, requires custom project signing for AAB delivery, restores the
temporary app-bundle toggle, and returns the BuildReport outcome plus artifact size and SHA-256.
run_tests invokes the installed Unity Test Framework through an exact typed contract. Use
edit_mode or play_mode and optional exact fully-qualified test or fixture names; an empty list
runs the selected mode. Wait for the returned Core job and treat result.outcome, counts, report
SHA-256, and request-scoped NUnit XML as the test evidence. The tool never launches another Unity
process.
Mobile input and device acceptance
When a user supplies a game file and requests Android/iOS testing, first call
inspect_mobile_input. Do not assume source is available. Classification only
reads container structure and does not authorize installation, extraction, opening
an unknown project, signing, or launching a game. Explain the returned route and
ask only for missing information needed by that route. With no input yet, explain
the supported formats; do not require a device for a capability discussion.
What ships with it
21 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/build_android_player.py 511 B runs code
- scripts/build_windows_player.py 436 B runs code
- scripts/capture_android_screenshot.py 614 B runs code
- scripts/configure_sprite_importer.py 592 B runs code
- scripts/enumerate_android_devices.py 334 B runs code
- scripts/grant_android_permission.py 677 B runs code
- scripts/inspect_mobile_input.py 393 B runs code
- scripts/inspect_project.py 316 B runs code
- scripts/install_android_apk.py 611 B runs code
- scripts/launch_android_package.py 610 B runs code
- scripts/read_android_logcat.py 730 B runs code
- scripts/read_text_asset.py 342 B runs code
- scripts/refresh_and_compile.py 434 B runs code
- scripts/refresh_assets.py 314 B runs code
- scripts/run_tests.py 570 B runs code
- scripts/search_assets.py 417 B runs code
- scripts/set_play_mode.py 443 B runs code
- scripts/stop_android_package.py 608 B runs code
- scripts/upsert_text_asset.py 1.1 KB runs code
- tools.yaml 24 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 13e2ccd29943
- 22d ago Changed 984edc1e4ab8
- 1mo ago Changed · +41 lines 552c49570e50
- 1mo ago First seen · 46 lines · 55 tokens per session scan A a437a85b06e5
unity-project is a skill published in the GitHub repository dcc-mcp/dcc-mcp-unity (0 stars, last pushed 10d ago), licensed MIT. It adds 55 tokens to every session and 1,124 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.