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 aadeshrao123/Unreal-MCP --skill setupgit clone --depth 1 https://github.com/aadeshrao123/Unreal-MCPWrote 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/aadeshrao123/unreal-mcp/setup)<a href="https://agentmods.dev/skills/aadeshrao123/unreal-mcp/setup"><img src="https://agentmods.dev/badge/skills/aadeshrao123/unreal-mcp/setup/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/aadeshrao123/unreal-mcp/setup"><img src="https://agentmods.dev/badge/skills/aadeshrao123/unreal-mcp/setup.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 | $0.00052 | $0.00461 |
| Opus 5.5 | $0.00021 | $0.00184 |
| Sonnet 5.5 | $0.00010 | $0.00092 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
setup 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 2d 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
Set up the CodeFizz Editor Agent
The plugin starts an MCP server with cfa mcp, so the cfa CLI must be installed first.
Windows x64 only. Run each step, read its output, and stop on an error.
- Check for the CLI:
cfa --version. If it prints a version, go to step 3. - Install the CLI (no Node needed):
powershell -c "irm https://codefizz.dev/install.ps1 | iex"It installs to%LOCALAPPDATA%\CodeFizz\bin\cfa.exeand adds that folder to the user PATH. Until a new terminal opens, call it by that full path. - Sign in:
cfa login. It opens the browser. The user signs in with their CodeFizz account; a new account starts a free 3-day trial at https://codefizz.dev/pricing. Never type the user's password for them. - Install the Unreal plugin into an engine. List engines with
cfa engines, then runcfa install-plugin "<engine folder>", for examplecfa install-plugin "E:/Unreal/UE_5.8". Supported: UE 5.6, 5.7 and 5.8. - Install the full skill, which teaches every command and workflow:
cfa skill install. Do not runcfa install claude; this plugin already provides the MCP server. - Open the project and check the connection:
cfa launch "<path to .uproject>", thencfa health_check. - Ask the user to run
/reload-plugins(or restart Claude Code) so thecfaMCP server connects.
When a step fails, run cfa doctor and show its output. Docs: https://codefizz.dev/docs/quick-start
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.
- 2d ago First seen · 29 lines · 52 tokens per session scan A b9c24228ce02
setup is a skill published in the GitHub repository aadeshrao123/Unreal-MCP (40 stars, last pushed 3d ago), licensed MPL-2.0. It adds 52 tokens to every session and 461 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 2026-11-04.
setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setupaadeshrao123/Unreal-MCP | Skill | 40 | 3d ago | MPL-2.0 | A | 52 | Claude Code |
| sprite-genaldegad/sprite-gen | Skill | 3.6k | 4d ago | Apache-2.0 | A | 238 | Claude Code, Codex |
| game-craftalfredxw/denova | Skill | 986 | yesterday | Apache-2.0 | A | 92 | Claude Code, Codex |
| extension-developmentalfredxw/denova | Skill | 986 | yesterday | Apache-2.0 | A | 21 | Claude Code, Codex |
| clayseaworld008/Commonly-used-high-value-skills | Skill | 74 | 2d ago | MIT | A | 73 | Claude Code, Codex |
| ar-vr-xrtravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 50 | Claude Code, Codex |
| ue5-mcpibrews/ue5-mcp | Skill | 47 | 8d ago | MIT | A | 156 | Claude Code |