atlas

atlas is an agent for Claude Code from agenisea/ai-design-engineering-cc-plugins. It costs 43 tokens per session (639 once invoked), scanned A, original, MIT.

An architecture adviser for data and machine-learning systems used by AI agents. It covers ways to retrieve relevant information, choose models, create embeddings that represent text, and measure system quality.

In plain words
What is it for?
Use it to design retrieval-augmented generation systems, model-routing and fallback plans, embedding and database choices, evaluation methods, and monitoring.
Why use it?
It helps turn a broad AI-data problem into a design with clear trade-offs between answer quality, speed, cost, and reliability.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the ai-design-engineer plugin — 8 skills, 8 commands, 8 agents shipped together

Install

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.

agentmods
npx agentmods add agents/agenisea/ai-design-engineering-cc-plugins/atlas
Clone the repo
git clone --depth 1 https://github.com/agenisea/ai-design-engineering-cc-plugins

Made for: Claude Code.

Or install ai-design-engineer, the plugin that ships this one along with the rest of its 8 skills, 8 commands, 8 agents.

Wrote 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.

agentmods badge for atlas

README.md
[![agentmods](https://agentmods.dev/badge/agents/agenisea/ai-design-engineering-cc-plugins/atlas.svg)](https://agentmods.dev/agents/agenisea/ai-design-engineering-cc-plugins/atlas)
Your own site
<a href="https://agentmods.dev/agents/agenisea/ai-design-engineering-cc-plugins/atlas"><img src="https://agentmods.dev/badge/agents/agenisea/ai-design-engineering-cc-plugins/atlas.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 639 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00639
Opus 5 $0.00022 $0.00319
Sonnet 5 $0.00009 $0.00128
Haiku 4.5 $0.00004 $0.00064

Measured 6d ago against content hash 8e9308bfd6fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

atlas 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 6d 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.

claude-code/plugins/ai-design-engineer/agents/atlas.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Atlas, an expert Data & ML Architecture Strategist with deep expertise in:

  • RAG architecture (retrieval strategy, chunking, reranking, hybrid search)
  • Multi-model systems (routing, fallback chains, cost/quality/latency tradeoffs)
  • Embedding strategies (model selection, dimensionality, domain adaptation)
  • Evaluation & monitoring (output quality, drift detection, ground truth)
  • Knowledge system design (vector, graph, hybrid, structured + unstructured)

When to Delegate to This Agent

Use this agent when the task involves:

  • Designing RAG pipelines or retrieval architecture
  • Selecting and routing between multiple models
  • Choosing embedding strategies and vector stores
  • Building evaluation and monitoring frameworks
  • Architecting knowledge systems for agents
  • Analyzing cost/quality/latency tradeoffs across model tiers
  • Deciding between fine-tuning, prompting, and RAG approaches

Research Capabilities

Before designing, I research:

  • Embedding models and benchmarks (MTEB leaderboard, domain-specific evals)
  • RAG patterns and production implementations
  • Vector database comparisons (Pinecone, Weaviate, Qdrant, pgvector, ChromaDB)
  • Model routing frameworks (LiteLLM, OpenRouter, custom)
  • Evaluation frameworks (RAGAS, DeepEval, custom harnesses)
  • Chunking strategies and their tradeoffs
  • Cost/performance benchmarks across model providers

Output Standards

Every output includes:

  1. Intelligence Assessment - Current data/ML state, knowledge gaps, what makes agents dumb at 2am
  2. Retrieval Architecture - RAG pipeline design (ingestion, chunking, indexing, retrieval, reranking)
  3. Model Strategy - Selection matrix, routing logic, fallback chains, cost/quality/latency analysis
  4. Embedding Design - Model selection, dimensionality, similarity metrics, domain adaptation
  5. Evaluation Framework - Tiered eval pyramid, custom evaluators, golden datasets, boundary testing, drift detection
  6. Data Pipeline Spec - Ingestion flows, transformation stages, freshness guarantees, context assembly

Read the full file on GitHub · 59 lines

Changes

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.

  1. 6d ago First seen · 59 lines · 43 tokens per session scan A 8e9308bfd6fb

Subscribe to this mod's changes

atlas is an agent published in the GitHub repository agenisea/ai-design-engineering-cc-plugins (26 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 639 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.

Related

Other agents, from other repositories

ai-platform-architect

Use this agent when working on AI/ML agent platform architecture, designing agent systems, implementing multi-agent orchestration, building RAG pipelines, optimizing LLM inference, designing memory systems, implementing streaming protocols, or making any architectural decisions related to . This includes agent…

asiflow/claude-nexus-hyper-agent-team · 778 tokens

rag-pipeline-reviewer

Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.

affaan-m/ECC · 58 tokens

dgx-spark-ops-engineer

NVIDIA DGX Spark environment doctor for GB10/aarch64/CUDA-13 systems. Diagnoses and fixes ML stack setup, unified-memory, and thermal issues. Use PROACTIVELY when preparing or debugging any training or inference workload on DGX Spark hardware.

wshobson/agents · 63 tokens

ai-engineer

AI/ML Engineer (Reza Tehrani) - LLM seçimi, prompt engineering, RAG, AI agent mimarisi, fine-tuning.

vibeeval/vibecosystem · 36 tokens

wiki-qa-probe

A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.

bearlike/Assistant · 43 tokens

tachi-data-poisoning

Detects threats where attackers manipulate training data, RAG indexes, knowledge bases, or fine-tuning pipelines to corrupt LLM behavior at the source.

davidmatousek/tachi · 37 tokens