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/isaac-sim/isaacautomator/agents-mdgit clone --depth 1 https://github.com/isaac-sim/IsaacAutomatorWrote 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/isaac-sim/isaacautomator/agents-md)<a href="https://agentmods.dev/instructions/isaac-sim/isaacautomator/agents-md"><img src="https://agentmods.dev/badge/instructions/isaac-sim/isaacautomator/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 | $0.00941 | $0.00941 |
| Opus 5 | $0.00470 | $0.00470 |
| Sonnet 5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
IsaacAutomator 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 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Isaac Automator - Agent Instructions
This repository is Isaac Automator: a command-line tool that deploys Isaac Sim, Isaac Lab, and Isaac Lab Arena to public clouds (AWS, GCP, Azure, Alibaba Cloud) as ready-to-use GPU Isaac Workstations (a remote desktop cloud VM with the Isaac apps installed, plus start/stop/destroy lifecycle and data transfer).
If you are an AI agent working with this repository, first decide your role:
- Operating Isaac Automator - you want to use the tool: deploy a workstation, connect to it, run a
demo, stop/start it, and tear it down. Read
ai/automator.agent.mdand follow the procedures inai/skills/. That is the entry point for operator agents. Start there. - Developing Isaac Automator - you want to change the tool itself (its Python CLI, Terraform, or
Ansible). See
README.mdandCONTRIBUTING.md. The operator docs are not for editing source.
Operator quickstart (the short version)
The full procedures are in ai/skills/; this is the orientation.
- Prerequisite: Docker running, cloud credentials available, then
./buildonce. - Everything runs in a container. The top-level scripts (
./deploy-aws,./start,./novnc, ...) wrap commands that run inside theisaac_automatorDocker image. Run them from the repo root. - Deploy:
./deploy-<cloud>with options; e.g. install Isaac Lab and a demo in one shot. Seeai/skills/deploy-workstation.skill.md. - Connect:
./novnc <name>(2D desktop), NoMachine (live 3D viewport), or./ssh <name>(shell). Seeai/skills/connect-workstation.skill.md. - Control cost / clean up:
./stop <name>,./start <name>, and./destroy <name> --yes. Seeai/skills/manage-lifecycle.skill.md.
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 · 56 lines · 941 tokens per session scan A 9513127c110c
IsaacAutomator AGENTS.md is an instructions file published in the GitHub repository isaac-sim/IsaacAutomator (261 stars, last pushed yesterday), licensed Apache-2.0. It adds 941 tokens to every session, about $0.0047 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 instructions, from other repositories
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.
awesome-kubernetes GEMINI.md
Instructions for nubenetes/awesome-kubernetes, covering 🧠 core mandates, 🛠️ structural evolution & navigation, 📊 mermaid diagram best practices, 🛡️ repository policies & branch protection and 📝 readme synchronization & maintenance protocols.
aurora AGENTS.md
AGENTS.md instructions for Arvo-AI/aurora, covering aurora - agent guidelines, commands, docker deployments, architecture and secrets management (vault).
_b00t_ GEMINI.md
Gemini CLI instructions for elasticdotventures/_b00t_, a project described as: 🥾 b00t: state of the art agentic harness tooling & dynamic context initialization.
_b00t_ CLAUDE.md
Claude Code instructions for elasticdotventures/_b00t_, a project described as: 🥾 b00t: state of the art agentic harness tooling & dynamic context initialization.
aurora CLAUDE.md
Claude Code instructions for Arvo-AI/aurora, a project described as: Aurora — Open source AI-powered agentic incident management & root cause analysis for SREs. LangGraph agents investigate across AWS, Azure, GCP, Kubernetes. Integrates with PagerDuty, Datadog, Grafana, Slack and More. Apache 2.0.