Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dyCuong03/unity-agent-teamnpx agentmods add commands/dycuong03/unity-agent-team/unity-agent-initWrote 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/commands/dycuong03/unity-agent-team/unity-agent-init)<a href="https://agentmods.dev/commands/dycuong03/unity-agent-team/unity-agent-init"><img src="https://agentmods.dev/badge/commands/dycuong03/unity-agent-team/unity-agent-init/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/commands/dycuong03/unity-agent-team/unity-agent-init"><img src="https://agentmods.dev/badge/commands/dycuong03/unity-agent-team/unity-agent-init.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 | $0.00038 | $0.00506 |
| Opus 5.5 | $0.00015 | $0.00202 |
| Sonnet 5.5 | $0.00008 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
unity-agent-init 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.
What it actually says
/unity-agent-init — Full Unity Agent Setup
One command to go from a bare Unity project to a fully configured agent team.
What it does
- Verifies Unity project markers (Assets/, Packages/, ProjectSettings/)
- Installs Unity CLI (beta) if not on PATH
- Configures Unity CLI MCP for Claude Code (
unity mcp configure claude-code) - Installs official Unity skills (
npx skills add Unity-Technologies/skills) - Copies missing framework scripts to target project
- Creates
.claude/project-config.json(Unity type, auto-detected paths) - Merges MCP servers into
.mcp.json(ai-game-developer, code-review-graph, agentmemory) - Seeds workspace knowledge files and directories
- Applies git perf tuning for WSL/slow filesystems
- Runs verification (roots.py + orchestrate.py preflight)
Usage
Run the initialization script. Pass through any flags the user provided:
python3 .claude/scripts/unity_init.py $ARGUMENTS
Report the output verbatim. If errors occur, surface them clearly.
On success, show the summary and confirm /team is ready to use.
Flags
| Flag | Effect |
|---|---|
--check |
Dry run — show what would change, exit 1 if work needed |
--force |
Overwrite existing project-config.json values |
--mcp-port <port> |
ai-game-developer HTTP port (default: 58511) |
--project-root <path> |
Target project root (default: auto-detected) |
--skip-unity-cli |
Skip Unity CLI install and MCP config |
--skip-skills |
Skip Unity official skills install |
After success
/team bug "describe the bug"
/team feature "describe the feature"
/team --team "full agent team task"
unity build ./ProjectPath --target Android --execute-method Builder.Build
unity test ./ProjectPath --mode EditMode
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 · 54 lines · 38 tokens per session scan A ccb2d8753b3d
unity-agent-init is a command published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 506 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.
Other commands, from other repositories
sim
Run the EmbodiedGen simulation rendering workflow with sim-cli.
cert-check
Review the current state against certification and platform compliance expectations.
combat-design
Design or revise combat rules, variables, readability, and tuning direction.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
web-build-fix
Diagnose and resolve web build, bundling, or deployment issues.
tech-debt
Track and prioritize technical debt.