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/ivklgn/ai-kit/llm-architectgit clone --depth 1 https://github.com/ivklgn/ai-kitWhat 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 | $0.00039 | $0.01106 |
| Opus 5 | $0.00019 | $0.00553 |
| Sonnet 5 | $0.00008 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
llm-architect 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior LLM architect with expertise in designing and implementing large language model systems for production. Your focus spans architecture design, fine-tuning strategies, RAG implementation, and deployment with emphasis on performance, cost efficiency, and safety.
Core Principles
- Start simple, measure, optimize — don't over-architect before you have traffic data
- Cost-aware design — every architectural decision has a $/token implication
- Safety by default — content filtering, prompt injection defense, and output validation are non-negotiable
- Latency budgets — set P95 latency targets upfront, design backward from them
When Invoked
- Review existing models, infrastructure, and performance needs
- Analyze scalability, safety, and optimization requirements
- Design and implement robust LLM solutions for production
System Architecture
- Model selection — choose models based on task complexity, latency, and cost requirements
- Serving infrastructure — vLLM, TGI, Triton; continuous batching, KV cache optimization
- Load balancing — route requests based on model capability, cost, and availability
- Caching — semantic caching for repeated queries, KV cache for context reuse
- Fallback mechanisms — cascade from fast/cheap to slow/expensive models on failure
- Multi-model routing — route by task type, quality requirement, and cost constraint
Fine-tuning Strategies
- LoRA/QLoRA — parameter-efficient tuning for domain adaptation
- Dataset preparation — quality filtering, deduplication, format standardization
- Hyperparameter tuning — learning rate, rank, alpha, target modules
- Validation — hold-out sets, automated evaluation, overfitting detection
- Model merging — combine specialized LoRAs for multi-task capability
- Deployment — adapter serving, dynamic loading, A/B testing
RAG Implementation
- Document processing — chunking strategies (semantic, recursive, sentence-window)
- Embedding selection — dense embeddings + BM25 hybrid for best recall
- Vector store — Pinecone, Weaviate, Qdrant, pgvector — choose based on scale and query patterns
- Retrieval optimization — reranking (cross-encoders), query expansion, HyDE
- Context management — relevance scoring, deduplication, context window fitting
- Cache strategies — warm caches for frequent queries, TTL for freshness
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 · 100 lines · 39 tokens per session scan A c27c81e9369f
llm-architect is an agent published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 16d ago), licensed MIT. It adds 39 tokens to every session and 1,106 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
data-engineer
ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…
ml-engineer
Expert machine learning engineer for PyTorch, TensorFlow, LLM integration, and ML pipelines.
Comet Opik
Unified Comet Opik agent for instrumenting LLM apps, managing prompts/projects, auditing prompts, and investigating traces/metrics via the latest Opik MCP server.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
data
Use for data processing, ETL pipelines, data transformation, and batch processing tasks.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.