thunder-cli AGENTS.md

Instructions for Thunder Compute, a cloud service that provides rented GPU computers for AI and machine-learning workloads. They cover its command-line tool, remote MCP server, setup, development, and release notes.

In plain words
What is it for?
It is for creating and managing GPU instances, running commands and background jobs, transferring files, checking GPU availability and prices, connecting by SSH, and handling related account settings.
Why use it?
They explain how a coding agent can manage remote GPU computers and run commands without installing the service locally. They also document authentication, instance access, files, networking, and billing.

Instructions file for CodexOpenCode

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 instructions/thunder-compute/thunder-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/Thunder-Compute/thunder-cli

Made for: Codex, OpenCode.

Per session 747 This file is loaded in full into every session.
When invoked 747 The same file — it is already loaded in full.
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 $0.00747 $0.00747
Opus 5 $0.00374 $0.00374
Sonnet 5 $0.00149 $0.00149
Haiku 4.5 $0.00075 $0.00075

Measured 2d ago against content hash a2f98bb947f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

thunder-cli AGENTS.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 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.

AGENTS.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Thunder Compute CLI

tnr is the CLI for Thunder Compute, a cloud GPU platform for AI/ML workloads.

MCP Server

Thunder Compute provides a remote MCP server that lets AI coding agents manage GPU instances directly — no local install required.

Connect it:

Agent Setup
Claude Code /mcp add --transport http https://www.thundercompute.com/mcp
Cursor Add to .cursor/mcp.json (see config below)
Windsurf Add to MCP settings (see config below)
Other agents POST to endpoint with OAuth 2.0
{
  "mcpServers": {
    "thunder-compute": {
      "type": "http",
      "url": "https://www.thundercompute.com/mcp"
    }
  }
}

No API tokens needed — authenticates via OAuth in the browser.

37 tools: instance management, command execution and background jobs, file reads, GPU specs/pricing/availability, snapshots, SSH keys, port forwarding, billing, and API tokens.

Full MCP documentation

CLI Quick Reference

tnr login            # Authenticate with Thunder Compute
tnr create           # Create a GPU instance
tnr status           # List instances with status
tnr connect <id>     # SSH into an instance
tnr scp <src> <dst>  # Transfer files
tnr delete <id>      # Delete an instance
tnr port <id> <port> # Forward a port

Instance IDs are integers. Add --json for scripted/non-interactive usage.

Release Notes

Every pull request that changes cli/** must add a Changie fragment under cli/changes/unreleased/. The generated release-preparation pull request is the only exception because it consumes all pending fragments.

Use the fragment kind that matches the shipped user impact. Changie derives the SemVer bump automatically:

  • Fixed, Changed, or Security: patch
  • Added or Deprecated: minor
  • Breaking or Removed: major
  • Internal: no release bump

Example:

cd cli
changie new --kind Fixed \
  --body "Preserve the login link when the terminal is resized."

Read the full file on GitHub · 98 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 · 98 lines · 747 tokens per session scan A a2f98bb947f0

Subscribe to this mod's changes

thunder-cli AGENTS.md is an instructions file published in the GitHub repository Thunder-Compute/thunder-cli (34 stars, last pushed 1mo ago), licensed MIT. It adds 747 tokens to every session, about $0.0037 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 instructions, from other repositories

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 · 5,182 tokens

buildNext

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

next.js 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

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

spec-kit 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.

github/spec-kit · 7,040 tokens

langchain 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 · 4,345 tokens