Borrowing it
Nothing to install: this file belongs to pandysp/openclaw-infra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pandysp/openclaw-infra/main/AGENTS.mdgit clone --depth 1 https://github.com/pandysp/openclaw-infraWrote 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/pandysp/openclaw-infra/agents-md)<a href="https://agentmods.dev/instructions/pandysp/openclaw-infra/agents-md"><img src="https://agentmods.dev/badge/instructions/pandysp/openclaw-infra/agents-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.
<a href="https://agentmods.dev/instructions/pandysp/openclaw-infra/agents-md"><img src="https://agentmods.dev/badge/instructions/pandysp/openclaw-infra/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.08469 | $0.08469 |
| Opus 5.5 | $0.03388 | $0.03388 |
| Sonnet 5.5 | $0.01694 | $0.01694 |
| Haiku 4.5 | $0.00847 | $0.00847 |
Grade A, and why
openclaw-infra 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 yesterday.
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 — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw Infrastructure
AI assistant guide for deploying and managing OpenClaw on Hetzner Cloud with Tailscale.
What This Project Is
OpenClaw is a self-hosted AI Agent gateway deployed on a Hetzner VPS with zero-trust networking via Tailscale. All access is through Tailscale—no public ports exposed.
Repository
This repo is pandysp/openclaw-infra. Personal deployment config (Pulumi secrets, group_vars/openclaw.yml) stays gitignored or in Pulumi encrypted state.
Architecture
Your Machine (Tailscale) → Hetzner VPS → Gateway (systemd, localhost:18789) via Tailscale Serve. No public ports. Hetzner firewall + UFW block all inbound except Tailscale.
Security Model
| Layer | Measure |
|---|---|
| Network (infrastructure) | Hetzner cloud firewall blocks ALL inbound |
| Network (host) | UFW: deny incoming, allow only tailscale0 interface |
| Access | Tailscale-only (no public SSH, no public ports) |
| Process | Runs as the ubuntu user (passwordless sudo). Agent turns run Claude Code on the host, or in a per-agent container with openclaw_claude_cli_enabled: true; OpenClaw's own tools run sandboxed in Docker (details) |
| Auth | Tailscale identity + device pairing |
| Secrets | Pulumi encrypted config (never in git) |
| Gateway | Binds localhost only, proxied via Tailscale Serve |
For the full threat model, see docs/SECURITY.md.
Gateway runs via systemd (not Docker) as unprivileged user. Docker runs OpenClaw's sandboxed tools (openclaw-sandbox-custom:latest) and the isolated workspace Git jobs. Auth: Tailscale identity + device pairing; no token needed. Resolve pairing requests over Tailscale SSH; do not print token-bearing URLs.
Directory Structure
openclaw-infra/
├── AGENTS.md # This file - AI assistant guide
├── README.md # Human overview
├── package.json # Node.js dependencies
├── tsconfig.json # TypeScript config
│
├── pulumi/ # Hetzner server, firewall, cloud-init; triggers Ansible
│
├── ansible/
│ ├── playbook.yml # Main playbook
│ ├── group_vars/all.yml # Non-secret defaults (models, agent types, server templates)
│ ├── group_vars/openclaw.yml # Deployment-specific overrides (gitignored)
│ ├── group_vars/openclaw.yml.example # Template for openclaw.yml
│ ├── inventory/ # Inventory from authenticated provisioner inputs
│ └── roles/ # One role per tag, see Ansible Tags below
│
├── scripts/
│ ├── provision.sh # Ansible wrapper (reads secrets from Pulumi)
│ ├── verify.sh # Post-deployment checks
│ ├── tests/ # Unit tests: python3 -m unittest discover -s scripts/tests
│ └── ... # Setup, staging and check scripts; each starts with a usage comment
│
└── docs/ # Durable topic guides only; investigations, specs,
# evidence and handoffs belong in scratch
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.
- yesterday Changed · +2 lines · +40 tokens per session ba68a7475062
- 16d ago Changed · +48 tokens per session e1a8cb3a12d2
- 17d ago Changed · +29 lines · +404 tokens per session 7f87734e4226
- 18d ago Changed · +10 tokens per session bb5b254c7d4f
- 19d ago First seen · 547 lines · 7,967 tokens per session scan A a8fbda6688eb
openclaw-infra AGENTS.md is an instructions file published in the GitHub repository pandysp/openclaw-infra (22 stars, last pushed 2d ago), licensed MIT. It adds 8,469 tokens to every session, about $0.0339 per session on Opus 5.5. 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 2026-10-09.
Other instructions, from other repositories
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).