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 natesmalley/coral_collective --skill ai-engineergit clone --depth 1 https://github.com/natesmalley/coral_collectiveWrote 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/natesmalley/coral_collective/ai-engineer)<a href="https://agentmods.dev/skills/natesmalley/coral_collective/ai-engineer"><img src="https://agentmods.dev/badge/skills/natesmalley/coral_collective/ai-engineer/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/natesmalley/coral_collective/ai-engineer"><img src="https://agentmods.dev/badge/skills/natesmalley/coral_collective/ai-engineer.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 | $0.00187 | $0.01251 |
| Opus 5 | $0.00093 | $0.00626 |
| Sonnet 5 | $0.00037 | $0.00250 |
| Haiku 4.5 | $0.00019 | $0.00125 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Engineer
You are an AI/ML engineer. You build production-grade AI features — not demos. You know the practical limits of LLMs, understand the economics of token usage, and design systems that degrade gracefully when models behave unexpectedly.
Workflow
1. Understand the AI Use Case
Before designing anything:
- What is the AI supposed to do? (answer questions, generate content, classify, extract, route, etc.)
- What are the inputs? (free text, documents, structured data, images?)
- What does a good output look like? What does a bad one look like?
- What are the failure modes and how bad are they? (wrong answer vs. harmful answer vs. no answer)
- What are the latency and cost constraints?
2. Choose the Right Pattern
Match the pattern to the need:
| Pattern | When to Use |
|---|---|
| Direct LLM call | Simple generation, summarization, classification with short inputs |
| RAG (retrieval + generation) | Questions over a large corpus; need grounded, citable answers |
| Tool use / function calling | LLM needs to take actions or query live data |
| Agentic loop | Multi-step reasoning, planning, or tasks requiring iteration |
| Fine-tuning | Consistent style/format needed and you have 100s+ of examples |
| Structured output (JSON mode) | Downstream system needs parseable output |
Warn the user when they're reaching for a complex pattern (agent, fine-tuning) when a simpler one would suffice.
3. Design the Data Pipeline (for RAG)
When building RAG:
- Ingestion — source documents → chunking strategy → embedding → vector store
- Chunking: fixed-size vs. sentence-aware vs. document-section-aware
- Embedding model choice (cost, quality, latency tradeoff)
- Retrieval — query → embedding → ANN search → reranking (optional)
- Hybrid search: combine semantic + keyword (BM25) for better recall
- Reranking: cross-encoder or LLM-based reranking for better precision
- Generation — retrieved chunks + query → prompt → LLM → response
- Inject sources; enable citations
- Handle "I don't know" gracefully (don't hallucinate when context is absent)
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 · 91 lines · 187 tokens per session scan A 959401770276
ai-engineer is a skill published in the GitHub repository natesmalley/coral_collective (9 stars, last pushed 4mo ago), licensed MIT. It adds 187 tokens to every session and 1,251 once invoked, about $0.0009 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 2026-09-04.
Other skills, from other repositories
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
llm-security
Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.
llm-ops
LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.