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 instructions/purduercac/globus-mcp/agents-mdgit clone --depth 1 https://github.com/PurdueRCAC/globus-mcpWrote 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/instructions/purduercac/globus-mcp/agents-md)<a href="https://agentmods.dev/instructions/purduercac/globus-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/purduercac/globus-mcp/agents-md.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 | $0.07783 | $0.07783 |
| Opus 5 | $0.03891 | $0.03891 |
| Sonnet 5 | $0.01557 | $0.01557 |
| Haiku 4.5 | $0.00778 | $0.00778 |
Grade A, and why
globus-mcp AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Never build a shell string; never pass `shell=True`.** `globus()` runs `subprocess.run([...])` How it starts
The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for coding agents (Claude Code and others) working in this repository.
CLAUDE.md is a symlink to this file — edit AGENTS.md, never a separate copy. (.claude
is likewise a symlink to .agents, so Claude Code discovers the factory skills and settings
through it.)
This document is the operating manual: the architecture, the load-bearing invariants, and the process rules an autonomous agent needs to make correct, safe changes here without rediscovering them each session. When something below disagrees with the code, the code is ground truth — fix this file.
Not to be confused with the agent-facing docs this server ships.
SERVER_INSTRUCTIONSinsrc/globus_mcp/server.pytells an MCP client how to use the Globus tools;README.mdtells a human the same. This file is about building the server. All three must stay consistent — see § "Agent-facing documentation is part of the code."
Project
globus-mcp is a FastMCP server that gives AI agents federated data transfer and remote code execution across research storage systems worldwide. It is a thin, opinionated wrapper over two upstream surfaces:
- Globus Transfer, driven by shelling out to the
globusCLI (src/globus_mcp/cli.py) — endpoints, filesystem ops, transfers, tasks. - Globus Compute, driven by the
globus-compute-sdk(src/globus_mcp/compute.py) — registering Python source and running it on remote HPC endpoints.
There is deliberately no persistent state, no database, and no long-lived scheduler: every tool
is a stateless call that translates agent intent into an upstream request and shapes the reply. The
value is in the translation layer — argument construction, error classification, consent recovery,
and the worker_init provisioning script — not in orchestration.
The blast radius is unusual for a package this small. 1,800 lines of Python sit in front of
petabyte-scale institutional storage and job execution on shared supercomputers. A wrong path in a
delete, a mis-provisioned environment on a login node, a corrupted protocol channel — these are
not local bugs. Read § "Verification without touching production" before you run anything.
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 · 454 lines · 7,783 tokens per session scan A 53d830309bbe
globus-mcp AGENTS.md is an instructions file published in the GitHub repository PurdueRCAC/globus-mcp (1 stars, last pushed 9d ago), licensed MIT. It adds 7,783 tokens to every session, about $0.0389 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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).