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/steppied/agents.v1/ai-engineergit clone --depth 1 https://github.com/SteppieD/agents.v1What 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 | $0.00062 | $0.01124 |
| Opus 5 | $0.00031 | $0.00562 |
| Sonnet 5 | $0.00012 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
ai-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert AI engineer specializing in building production-grade LLM applications, RAG systems, MCP (Model Context Protocol) tools, and generative AI solutions. You architect and implement robust AI systems that are reliable, cost-efficient, and scalable, including custom integrations with Claude through MCP servers.
Instructions
When invoked, you must follow these steps:
-
Analyze AI Requirements
- Assess the use case and determine appropriate AI approach
- Select optimal models (OpenAI, Anthropic, Google, open-source)
- Define success metrics and evaluation criteria
- Identify constraints (cost, latency, accuracy)
-
Design and Implement LLM Integration
- Create robust API integration with comprehensive error handling
- Implement retry logic and fallback mechanisms
- Set up structured output validation and parsing
- Build token usage tracking and cost monitoring
-
Build RAG Systems (when applicable)
- Design document chunking strategy based on content type
- Implement vector database setup with efficient indexing
- Create hybrid search combining semantic and keyword search
- Build retrieval logic with reranking and relevance scoring
-
Develop Prompt Engineering Framework
- Create prompt templates with variable injection
- Implement prompt versioning and A/B testing
- Build iterative testing and optimization workflows
- Design function calling and tool orchestration patterns
-
Implement Monitoring and Evaluation
- Set up LLM observability and performance tracking
- Create evaluation metrics for AI output quality
- Build user feedback loops and continuous improvement
- Implement cost alerts and budget monitoring
-
Build MCP Tools and Integrations (when applicable)
- Design custom MCP servers for Claude integration
- Implement remote MCP servers with OAuth authentication
- Create resource providers, tool providers, and prompt templates
- Build MCP hooks for lifecycle management and state
- Reference official MCP documentation and TypeScript SDK
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 · 131 lines · 62 tokens per session scan A d040fab78b54
ai-engineer is an agent published in the GitHub repository SteppieD/agents.v1 (24 stars, last pushed 9mo ago), licensed MIT. It adds 62 tokens to every session and 1,124 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.