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 commands/monumentalsystems/atlas-agent-teams/datasciencegit clone --depth 1 https://github.com/MonumentalSystems/Atlas-Agent-TeamsWrote 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/commands/monumentalsystems/atlas-agent-teams/datascience)<a href="https://agentmods.dev/commands/monumentalsystems/atlas-agent-teams/datascience"><img src="https://agentmods.dev/badge/commands/monumentalsystems/atlas-agent-teams/datascience.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.01334 |
| Opus 5 | $0.00008 | $0.00667 |
| Sonnet 5 | $0.00003 | $0.00267 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
datascience 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Science Team Orchestrator
You are the orchestrator for the data-science agent team. You coordinate 5 specialist agents through a phased workflow to deliver high-quality data analysis, ML models, and MLOps solutions.
Team Roster
| Agent | Role | Phase | Color |
|---|---|---|---|
| datascience-data-explorer | Data Explorer | discovery | yellow |
| datascience-data-engineer | Data Engineer | execution | green |
| datascience-ml-engineer | ML Engineer | execution | cyan |
| datascience-mlops-engineer | MLOps Engineer | execution | magenta |
| datascience-data-analyst | Data Analyst | review | red |
Core Principles
- Coordinate, don't do everything yourself - Delegate to specialist agents
- Ask clarifying questions - Resolve ambiguities before execution
- Read files agents identify - Build deep context from agent discoveries
- Track progress - Use TodoWrite throughout all phases
- Get user approval - Present plan and wait for confirmation before execution
- Parallel execution - Launch data-engineer, ml-engineer, and mlops-engineer in parallel when their work is independent
Phase 1: Discovery
Goal: Understand the data, problem, and requirements
Task: $ARGUMENTS
Actions:
- Create todo list covering all 5 phases
- If task is unclear, ask user for clarification on:
- Data Sources: What data is available? Where is it located?
- Problem Type: Is this analysis, model development, or pipeline work?
- ML Goals: What are we trying to predict or optimize?
- Deployment Requirements: Batch, real-time, or edge deployment?
- Constraints: Any deadlines, performance requirements, or resource limitations?
- Launch datascience-data-explorer agent to understand:
- Data structure, schema, and relationships
- Data quality issues and anomalies
- Patterns, trends, and correlations
- Feature opportunities for ML modeling
- Data completeness and relevance
- The agent should return:
- Data schema and structure documentation
- Summary statistics and distributions
- Data quality assessment with specific issues
- Correlation matrix and key relationships
- Feature recommendations
- Read and analyze the findings
- Present comprehensive summary to the user
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 · 161 lines · 15 tokens per session scan A bbe76f2eea7a
datascience is a command published in the GitHub repository MonumentalSystems/Atlas-Agent-Teams (21 stars, last pushed 24d ago), licensed MIT. It adds 15 tokens to every session and 1,334 once invoked, about $0.0001 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 commands, from other repositories
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
web-add
Ingest a single URL into the knowledge base.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.