union-mcp: Instructions file for Claude Code

CLAUDE.md

union-mcp CLAUDE.md is an instructions file for Claude Code from unionai-oss/union-mcp. It costs 1,841 tokens per session, scanned A, original, Apache-2.0.

Project instructions for using Union MCP v2 to run heavy computation or data-processing work on a remote Flyte cluster. Flyte is a system for coordinating repeatable workloads across remote machines.

In plain words
What is it for?
Use them for large parallel jobs, GPU work, large datasets, long-running calculations, model training, hyperparameter searches, and batch data processing.
Why use it?
They explain when a laptop may not have enough processing power, memory, graphics hardware, or runtime for the job.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is unionai-oss/union-mcp's own configuration. It tells Claude Code how to work on union-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything union-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to unionai-oss/union-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/unionai-oss/union-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/unionai-oss/union-mcp

Made for: Claude Code.

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 union-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/unionai-oss/union-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/unionai-oss/union-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/unionai-oss/union-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/unionai-oss/union-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for union-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/unionai-oss/union-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/unionai-oss/union-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,841 This file is loaded in full into every session.
When invoked 1,841 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01841 $0.01841
Opus 5 $0.00920 $0.00920
Sonnet 5 $0.00368 $0.00368
Haiku 4.5 $0.00184 $0.00184

Measured 9d ago against content hash 927a50b97876, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

union-mcp CLAUDE.md 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 9d 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.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Union MCP v2

This file contains rules for using the Union MCP v2 server to run compute- or io-intensive workloads on a remote Flyte cluster.

When to Use Union MCP v2

Explicit Requests

If the user explicitly asks to run a workload on Flyte or Union, use the Union MCP v2 server.

Implicit Compute Needs

If a task requires compute resources beyond what a consumer laptop can handle, proactively suggest and use the Union MCP v2 server. This includes:

  • Large-scale parallel processing: Tasks that benefit from fan-out patterns (e.g., processing millions of items)
  • GPU workloads: Deep learning inference, embeddings, model training
  • Memory-intensive tasks: Processing large datasets that exceed typical RAM (8-16GB)
  • Long-running computations: Tasks that would take more than a few minutes on a laptop
  • Hyperparameter optimization: Parallel training runs across parameter combinations
  • Batch data processing: ETL jobs, data transformations on large datasets

Examples of When to Use Flyte

  • "Compute the sum of squares for 1 million numbers" → Fan-out to parallel workers
  • "Embed this 100k document dataset" → GPU batch inference
  • "Train models with different hyperparameters" → Parallel hyperparameter search
  • "Process this 50GB CSV file" → Distributed data processing
  • "Generate embeddings using a transformer model" → GPU acceleration

Examples of When NOT to Use Flyte

  • Simple calculations that complete in seconds
  • Reading/writing small files
  • Basic API calls
  • Local development tasks
  • Quick data exploration on small datasets

Workflow for Running Flyte Scripts

Follow these steps when running a workload on Flyte:

Step 1: Search for Examples

Before writing a script, search for relevant examples:

  1. Search the local workspace for existing Flyte examples
  2. Use search_flyte_sdk_examples for bleeding-edge SDK features
  3. Use search_flyte_docs_examples for common use cases and patterns
  4. Use search_full_docs for Flyte documentation and API reference

Read the full file on GitHub · 213 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. 9d ago First seen · 213 lines · 1,841 tokens per session scan A 927a50b97876

Subscribe to this mod's changes

union-mcp CLAUDE.md is an instructions file published in the GitHub repository unionai-oss/union-mcp (7 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,841 tokens to every session, about $0.0092 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens