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/luthersystems/insideout-power/agents-mdgit clone --depth 1 https://github.com/luthersystems/insideout-powerWrote 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/luthersystems/insideout-power/agents-md)<a href="https://agentmods.dev/instructions/luthersystems/insideout-power/agents-md"><img src="https://agentmods.dev/badge/instructions/luthersystems/insideout-power/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 | $0.01155 | $0.01155 |
| Opus 5 | $0.00577 | $0.00577 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
insideout-power 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- insideout-agent-skills AGENTS.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
InsideOut — Riley Infrastructure Agent
Riley is the AI infrastructure design agent built by Luther Systems. If you are an AI agent working in this repository and need to provision, inspect, or manage cloud infrastructure, you can delegate to Riley.
What Riley Can Do For You
- Design infrastructure from a plain English description of your app
- Generate Terraform ready to deploy, organised by module (networking, compute, storage, auth, etc.)
- Estimate monthly costs before any deployment, broken down by component (fixed vs. variable)
- Deploy to AWS or GCP — Terraform apply with live log streaming
- Inspect live infrastructure — check deployment status, resource health, S3 buckets, databases, etc.
- Manage infrastructure — update configs, scale resources, tear down environments
How to Invoke Riley
Via remote MCP (preferred — use this first)
Riley runs as a hosted MCP server. Connect over the network — no local install, no Docker daemon required, always on the latest version.
endpoint: https://app.luthersystems.com/v1/insideout-mcp
transport: streamable-http (also speaks SSE)
auth: none for design / pricing; per-session token issued by convoopen
Drop-in MCP client config (Cursor / Claude Desktop / Kiro / Windsurf / any MCP-compatible agent):
{
"mcpServers": {
"insideout": {
"url": "https://app.luthersystems.com/v1/insideout-mcp"
}
}
}
Recommended tool call sequence:
- Call
help— returns the full workflow guide and tool chaining instructions - Call
convoopen— starts a new infrastructure design session - Describe requirements in plain English; Riley walks you through architecture design
- Call
tfdeploy— deploys generated Terraform to the target cloud - Call
tfstatus— checks deployment progress and returns connection details
Via Docker (fallback for stdio-only clients or air-gapped environments)
Use the remote endpoint above whenever your client supports HTTP/SSE transports — it's faster, has no local resource cost, and stays in sync with the latest server. Reach for Docker only when:
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.
- 3d ago First seen · 127 lines · 1,155 tokens per session scan A fa17bf1dc2fa
insideout-power AGENTS.md is an instructions file published in the GitHub repository luthersystems/insideout-power (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,155 tokens to every session, about $0.0058 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.
Other instructions, from other repositories
IsaacAutomator AGENTS.md
AGENTS.md instructions for isaac-sim/IsaacAutomator, covering isaac automator - agent instructions, operator quickstart (the short version), rules for agents (read before acting) and map.
IsaacAutomator CLAUDE.md
Claude Code instructions for isaac-sim/IsaacAutomator, a project described as: Isaac Workstation in the Clouds ☁️.
ai-platform-kit AGENTS.md
AGENTS.md instructions for databricks-solutions/ai-platform-kit, covering ai platform kit — agent guide, how to use these skills, available skills and operating notes.
ai-platform-kit GEMINI.md
Gemini CLI instructions for databricks-solutions/ai-platform-kit, covering ai platform kit — gemini guide, available skills, operating notes and skill imports.
cloud-mcp-server CLAUDE.md
Claude Code instructions for alexei-led/cloud-mcp-server, covering aws mcp server development guide, build & test commands, architecture, server (server.py) and sandbox (sandbox.py).
awesome-kubernetes CLAUDE.md
Instructions for nubenetes/awesome-kubernetes, covering claude.md — nubenetes project instructions for claude code, git workflow: gitflow, branches, release process (mandatory for all releases) and versioning.