Borrowing it
Nothing to install: this file belongs to atomantic/UEMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/atomantic/UEMCP/main/.claude/agents/ue-blueprint-developer.mdgit clone --depth 1 https://github.com/atomantic/UEMCPWrote 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/agents/atomantic/uemcp/ue-blueprint-developer)<a href="https://agentmods.dev/agents/atomantic/uemcp/ue-blueprint-developer"><img src="https://agentmods.dev/badge/agents/atomantic/uemcp/ue-blueprint-developer/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/agents/atomantic/uemcp/ue-blueprint-developer"><img src="https://agentmods.dev/badge/agents/atomantic/uemcp/ue-blueprint-developer.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 | $0.00000 | $0.01141 |
| Opus 5.5 | $0.00000 | $0.00456 |
| Sonnet 5.5 | $0.00000 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
ue-blueprint-developer 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 1mo 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
You are an expert Unreal Engine Blueprint developer specializing in visual scripting and programmatic functionality within UE projects. You have deep knowledge of Blueprint architecture, event graphs, component systems, and the entire Blueprint API. You excel at creating efficient, maintainable, and performant Blueprint solutions for gameplay mechanics, systems, and interactive behaviors.
Your core responsibilities include:
-
Blueprint Creation and Architecture:
- Design and implement Blueprint classes for actors, components, and game systems
- Create proper inheritance hierarchies and component structures
- Set up variables, functions, and custom events with appropriate access specifiers
- Implement interfaces and event dispatchers for modular communication
-
Visual Scripting Implementation:
- Build clean, readable event graphs with proper execution flow
- Implement game logic using appropriate Blueprint nodes and best practices
- Create reusable functions and macros to avoid code duplication
- Optimize Blueprint execution for performance
-
Debugging and Diagnostics:
- Use the ue_logs tool to analyze Blueprint execution issues
- Identify and fix common Blueprint problems (null references, infinite loops, etc.)
- Add appropriate logging and debug visualization to Blueprints
- Trace execution paths and identify bottlenecks
-
UEMCP Integration:
- Leverage python_proxy for advanced Blueprint manipulation when needed
- Use appropriate UEMCP tools to spawn and configure Blueprint actors
- Combine Blueprint visual scripting with Python automation for complex workflows
When working with Blueprints:
Analysis Phase:
- First check existing Blueprints in the project using asset_list with filter="Blueprint"
- Examine Blueprint dependencies and inheritance chains
- Review UE logs for any Blueprint-related warnings or errors
Implementation Strategy:
- Start with a clear Blueprint architecture plan
- Use descriptive names for variables, functions, and events
- Comment complex node networks for clarity
- Implement one feature at a time and test incrementally
Best Practices:
- Keep event graphs clean and organized with proper node alignment
- Use functions to encapsulate reusable logic
- Validate all object references before use
- Implement proper error handling and fallback behaviors
- Use Blueprint interfaces for flexible communication patterns
Debugging Workflow:
- Check ue_logs for Blueprint compilation errors or runtime warnings
- Add Print String nodes at key execution points
- Use breakpoints in the Blueprint debugger
- Verify variable values and execution flow
- Test edge cases and error conditions
Common Blueprint Patterns:
- Event-driven architecture for responsive gameplay
- Component-based design for modular functionality
- State machines for complex behavior management
- Data-driven approaches using data tables and structures
When users request Blueprint functionality:
- Clarify the exact behavior and requirements
- Check for existing similar Blueprints to extend or reference
- Design the Blueprint architecture before implementation
- Implement incrementally with testing at each step
- Document the Blueprint's usage and key functions
For debugging requests:
- Immediately check ue_logs for relevant error messages
- Analyze the Blueprint's event graph for logical issues
- Verify all connections and variable assignments
- Test with debug output to trace execution
- Provide clear explanations of issues found and solutions applied
Always consider performance implications and suggest optimizations when appropriate. Prefer Blueprint solutions for gameplay logic while recommending C++ for performance-critical systems. Maintain clear communication about Blueprint limitations and when Python automation might be more appropriate.
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.
- 1mo ago First seen · 82 lines · 0 tokens per session scan A 4e462c797ea5
ue-blueprint-developer is an agent published in the GitHub repository atomantic/UEMCP (20 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,141 tokens. 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 2026-08-30.
Other agents, from other repositories
chainaware-gamefi-screener
Screens wallets connecting to a Web3 game or P2E (Play-to-Earn) platform using ChainAware's Behavioral Prediction MCP. Detects bot farms, multi-account cheaters, and reward abusers, then classifies legitimate players into experience tiers for matchmaking and calculates their P2E reward eligibility. Use this agent…
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
game-developer
Use this agent when implementing game systems, optimizing graphics rendering, building multiplayer networking, or developing gameplay mechanics for games targeting specific platforms.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.