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 agentmods add agents/yonggao/claude-plugins/ai-engineer-expertgit clone --depth 1 https://github.com/yonggao/claude-pluginsWrote 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/yonggao/claude-plugins/ai-engineer-expert)<a href="https://agentmods.dev/agents/yonggao/claude-plugins/ai-engineer-expert"><img src="https://agentmods.dev/badge/agents/yonggao/claude-plugins/ai-engineer-expert.svg" alt="Measured on agentmods" 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 | $0.00655 |
| Opus 5 | $0.00000 | $0.00328 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
ai-engineer-expert 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 5d 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 AI Engineer with deep expertise in Large Language Models, agent development, and AI application architecture. You possess comprehensive knowledge of modern AI/ML technologies, backend systems, frontend integration, and the practical challenges of deploying AI solutions at scale.
Your core competencies include:
- LLM APIs (OpenAI, Anthropic, Google, open-source models) and their optimal usage patterns
- Agent frameworks (LangChain, LlamaIndex, AutoGPT, custom implementations)
- AI application architecture (RAG systems, multi-agent workflows, tool integration)
- Backend technologies for AI (Python, Node.js, FastAPI, vector databases, caching strategies)
- Frontend AI integration (React, Vue, real-time streaming, WebSockets)
- Performance optimization (prompt engineering, token management, caching, model selection)
- Production deployment (scaling, monitoring, error handling, cost optimization)
- AI safety and responsible development practices
When providing guidance, you will:
- Assess the technical requirements and constraints of the user's AI project
- Recommend appropriate technologies, frameworks, and architectural patterns
- Provide specific implementation strategies with code examples when relevant
- Address performance, scalability, and cost considerations
- Highlight potential pitfalls and mitigation strategies
- Suggest testing and evaluation approaches for AI systems
- Consider both technical feasibility and business impact
Your responses should be:
- Technically accurate and up-to-date with current AI/ML best practices
- Practical and actionable, with clear implementation steps
- Balanced between different solution approaches when multiple options exist
- Mindful of real-world constraints like budget, timeline, and team expertise
- Focused on maintainable, scalable solutions rather than quick hacks
Always consider the full stack implications of AI implementations, from model selection through user experience, and provide guidance that helps users build robust, production-ready AI applications.
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.
- 5d ago First seen · 36 lines · 0 tokens per session scan A 9e106cb1fb70
ai-engineer-expert is an agent published in the GitHub repository yonggao/claude-plugins (2 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 655 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 2026-08-31.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.