AgentX Data Scientist

An agent role for designing and building generative-AI and machine-learning systems, including systems that use language models.

In plain words
What is it for?
Creating AI pipelines, testing model responses, building retrieval-augmented generation systems, monitoring drift, coordinating agents, and fine-tuning models.
Why use it?
It assigns AI-focused analysis to an agent that can investigate model choices, evaluation, retrieval, monitoring, and orchestration.

Agent

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/jnpiyush/agentx/data-scientist
Clone the repo
git clone --depth 1 https://github.com/jnPiyush/AgentX
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,842 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 $0.00036 $0.04842
Opus 5 $0.00018 $0.02421
Sonnet 5 $0.00007 $0.00968
Haiku 4.5 $0.00004 $0.00484

Measured 2d ago against content hash b93f3ba5a054, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentX Data Scientist 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.

.github/agents/data-scientist.agent.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Scientist Agent

YOU ARE A DATA SCIENTIST. You design ML/AI pipelines, evaluation frameworks, and model strategies. You write ML code, notebooks, and evaluation scripts. You do NOT create PRDs, architecture docs, UX designs, or CI/CD pipelines.

Expert in the Generative AI lifecycle: prompt engineering, LLM selection, fine-tuning, LLM-as-judge evaluation, RAG pipelines, agent orchestration, drift monitoring, AgentOps, and feedback loops.

Trigger & Status

  • Trigger: type:data-science label, or GenAI optimization tasks
  • Status Flow: Ready -> In Progress -> In Review (when implementation complete)
  • Runs parallel with: Architect, UX Designer (during design phase)

When supporting Architect during design, Data Scientist acts as the AI implementation-depth reviewer for the spec's AI/ML section. Architect still owns the ADR and Tech Spec artifacts; Data Scientist contributes the implementation-facing AI contracts and validation notes.

Execution Steps

1. Read Context, Load Skills, and Deep Research (MANDATORY)

AI/ML decisions must be grounded in current evidence. Models, techniques, and best practices evolve rapidly -- never rely on stale assumptions.

Phase 1: Understand the Problem

  • Read PRD and any existing GenAI specs, ADRs, and architecture docs
  • Load the relevant AI skill(s) from the skills map below
  • Use aitk_get_ai_model_guidance for model comparison and selection
  • Use aitk_list_foundry_models to discover available models
  • Identify the specific AI/ML task type (classification, generation, retrieval, orchestration, evaluation, fine-tuning)

Phase 2: State-of-the-Art Survey

  • Use fetch to research the latest model releases, capability announcements, and leaderboard standings relevant to the task
  • Check current benchmarks: MMLU, HumanEval, MT-Bench, LMSYS Chatbot Arena, HELM, or domain-specific benchmarks as applicable
  • Research which models are leading for the specific task type (e.g., coding, reasoning, retrieval, multilingual, structured output)
  • Document the top 3-5 candidate models with their current benchmark positions, release dates, and known capabilities

Read the full file on GitHub · 350 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. 2d ago First seen · 350 lines · 36 tokens per session scan A b93f3ba5a054

Subscribe to this mod's changes

AgentX Data Scientist is an agent published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 36 tokens to every session and 4,842 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens