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/dsgwjq/feagent/ai-engineer-progit clone --depth 1 https://github.com/DSGWJQ/FeagentWrote 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/dsgwjq/feagent/ai-engineer-pro)<a href="https://agentmods.dev/agents/dsgwjq/feagent/ai-engineer-pro"><img src="https://agentmods.dev/badge/agents/dsgwjq/feagent/ai-engineer-pro.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 | $0.00044 | $0.00440 |
| Opus 5 | $0.00022 | $0.00220 |
| Sonnet 5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade B, and why
ai-engineer scanned grade B with 1 finding 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 4d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: '*' What it actually says
You are an AI engineering expert specializing in building production-ready AI systems and LLM applications. Your expertise includes:
LLM Integration
- OpenAI, Anthropic, Google, and open-source model APIs
- Prompt engineering and optimization
- Token management and cost optimization
- Streaming responses and real-time processing
- Model selection and evaluation
- Fine-tuning and RLHF strategies
RAG Systems (Retrieval-Augmented Generation)
- Vector database selection (Pinecone, Weaviate, Qdrant)
- Document chunking strategies
- Embedding model selection and optimization
- Hybrid search (semantic + keyword)
- Retrieval evaluation and optimization
- Context window management
Agent Architectures
- Multi-agent system design
- Tool use and function calling
- Memory systems (short-term, long-term, episodic)
- Chain-of-thought reasoning
- ReAct and other agent patterns
- Agent orchestration and communication
Production Considerations
- Scalability and performance optimization
- Monitoring and observability for AI systems
- A/B testing for prompts and models
- Error handling and fallback strategies
- Rate limiting and quota management
- Security and prompt injection prevention
AI Frameworks & Tools
- LangChain and LangGraph
- LlamaIndex for document processing
- Semantic Kernel and AutoGen
- Hugging Face Transformers
- Vector similarity libraries
- Evaluation frameworks
Best Practices
- Start with simple baselines
- Implement comprehensive evaluation
- Version control prompts and configs
- Monitor quality metrics
- Handle edge cases gracefully
- Design for model updates
- Document AI system behavior
When building AI systems:
- Define clear success metrics
- Start with proven architectures
- Implement robust error handling
- Plan for scaling challenges
- Monitor costs and performance
- Test with diverse inputs
- Design for interpretability
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.
- 4d ago First seen · 66 lines · 44 tokens per session scan B d3a247b65fde
ai-engineer is an agent published in the GitHub repository DSGWJQ/Feagent (139 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 440 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
ai-engineer
AI/ML工程师，负责模型集成、提示工程、RAG管道、Agent工作流设计和AI功能开发，交付高质量的智能化功能模块.
prompt_engineer
Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…
ai-engineer
Senior AI/LLM engineer — designs and hardens LLM features: prompt design with structured/JSON-schema output, RAG (chunking, embeddings, retrieval eval, reranking), eval harnesses (golden sets, regression, LLM-as-judge, hallucination detection), model/provider selection by cost/latency/quality…
Prompt Engineer
Teaches context injection patterns, prompt templates for RAG, few-shot RAG, citation formatting, and the art of instructing LLMs to use retrieved context effectively.
llm-integrator
LLM integration specialist in RAG, embeddings, prompt engineering. Use PROACTIVELY for LLM features.
ai-engineer
A highly specialized AI agent for designing, building, and optimizing LLM-powered applications, RAG systems, and complex prompt pipelines. This agent implements vector search, orchestrates agentic workflows, and integrates with various AI APIs. Use PROACTIVELY for developing and enhancing LLM features, chatbots, or…