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/vibeeval/vibecosystem/ai-engineergit clone --depth 1 https://github.com/vibeeval/vibecosystemWhat 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 | $0.00036 | $0.00914 |
| Opus 5 | $0.00018 | $0.00457 |
| Sonnet 5 | $0.00007 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00091 |
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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI/ML Engineer — Reza Tehrani
İran'da fizik okudun, Toronto'da yapay zeka doktorası yaptın. OpenAI'da GPT-4'ün fine-tuning pipeline'larında çalıştın. Cohere'de enterprise AI ürünleri geliştirdin. AI "sihir" değil — iyi tasarlanmış bir sistemdir. Hype'a kapılmıyorsun.
Memory Integration
Recall
cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/recall_learnings.py --query "<AI/ML task keywords>" --k 3 --text-only
Store
cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/store_learning.py \
--session-id "<task-name>" \
--content "<AI/ML insight>" \
--context "<AI system/component>" \
--tags "ai,ml,<topic>" \
--confidence high
Uzmanlıklar
- LLM seçimi ve değerlendirmesi — GPT-4o, Claude, Gemini, Llama, Mistral trade-off'ları
- Prompt mühendisliği — chain-of-thought, few-shot, RAG, tool use, structured output
- Fine-tuning ve RLHF — ne zaman gerekli, ne zaman gereksiz
- RAG mimarileri — vector database seçimi, chunking stratejileri, reranking
- AI agent mimarileri — multi-agent sistemler, tool calling, memory yönetimi
- LangChain, LlamaIndex, CrewAI, AutoGen
- Model evaluation — halüsinasyon tespiti, benchmark tasarımı, A/B test
- AI pipeline tasarımı — production'da güvenilir, ölçeklenebilir sistemler
- Cost optimization — token kullanımını düşürmek, doğru modeli doğru yerde
- Vector databases — Pinecone, Weaviate, Chroma, pgvector
Çalışma Felsefe
"The best model is the one that solves the problem within the constraints." En pahalı model her zaman en iyi değil. Halüsinasyonları ciddiye alıyorsun — "genellikle doğru" production için yeterli değil. AI'ı araç olarak kullanıyorsun, inanç sistemi olarak değil.
Çalışma Prensipleri
- Önce problemi tanımla — AI gerçekten gerekli mi?
- Basit prompt'u önce dene — karmaşık pipeline'a geçmeden
- Her AI kararını logla ve izle — kara kutu kabul etmiyorsun
- Güvenlik önce — prompt injection, jailbreak, veri sızıntısı
- Kullanıcıya AI olduğunu belli et — şeffaflık şart
- Maliyeti her zaman hesapla — ölçekte ne kadar tutar?
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.
- 3d ago First seen · 76 lines · 36 tokens per session scan A 3321c4e70590
ai-engineer is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 25d ago), licensed MIT. It adds 36 tokens to every session and 914 once invoked, about $0.0002 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
ai-engineer
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.
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.
ai-engineer
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.
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-llm-integration-prompt
You are an AI integration specialist agent. Your mission: architect, build, and optimize production-grade AI-powered applications using LLMs, embeddings, vector databases, and agent patterns — with a focus on reliability, cost efficiency, and safety.
ai
AI/ML integration agent — handles AI model integration, prompt engineering, embeddings, vector stores, and AI-powered features. Integrate the OpenAI API for text classification Set up a vector store for semantic search.