Borrowing it
Nothing to install: this file belongs to MotherofallVPNs/MoaV. 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/MotherofallVPNs/MoaV/main/AGENTS.mdgit clone --depth 1 https://github.com/MotherofallVPNs/MoaVWrote 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/motherofallvpns/moav/agents-md)<a href="https://agentmods.dev/instructions/motherofallvpns/moav/agents-md"><img src="https://agentmods.dev/badge/instructions/motherofallvpns/moav/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/motherofallvpns/moav/agents-md"><img src="https://agentmods.dev/badge/instructions/motherofallvpns/moav/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 | $0.02869 | $0.02869 |
| Opus 5.5 | $0.01148 | $0.01148 |
| Sonnet 5.5 | $0.00574 | $0.00574 |
| Haiku 4.5 | $0.00287 | $0.00287 |
Grade C, and why
MoaV AGENTS.md scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://moav.sh/install.sh | bash # or: git clone … && ./moav.sh install Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://moav.sh/install.sh | bash # or: git clone … && ./moav.sh install How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — running & operating a MoaV server with an AI agent
This guide is mainly for an agent operating a MoaV server on the owner's behalf — installing it, adding users, checking health, reading logs, handing the owner their dashboards. If you are instead editing the code (fixing a bug, adding a protocol), jump to Developing MoaV and the dev docs.
Humans: start with README.md; public docs are at moav.sh/docs. A one-fetch index for agents is llms.txt.
Safety first. Set the server up over an SSH key, never a password, and never paste the owner's
ADMIN_PASSWORD, private keys, or a user's share-link into anything public (issues, PRs, pastebins). Treat everything understate/andoutputs/as secret. Don't run destructive commands (uninstall,user revoke,docker volume rm) without the owner's explicit go-ahead.
What MoaV is
A single-host, Docker-Compose, multi-protocol Internet-censorship-circumvention
stack. moav.sh is a bash dispatcher over lib/*.sh modules; it bootstraps
keys/certs, generates per-user bundles (configs, QR codes, a V2Ray
subscription), and runs 18+ transports plus an optional Prometheus/Grafana
monitoring stack. Protocol servers run as containers; provisioning and the CLI
are bash. The install lives in /opt/moav by default.
Install & run
Install the global moav command, then run the guided setup (asks for domain,
ACME email, admin password, then bootstraps keys/certs and starts the stack):
curl -fsSL https://moav.sh/install.sh | bash # or: git clone … && ./moav.sh install
moav # guided config + bootstrap + start
The moav.sh/install.sh one-liner installs the latest stable release. To
fresh-install the latest dev code instead (e.g. to test an unreleased fix),
fetch and run install.sh from the branch and tell it to clone that branch:
curl -fsSL https://raw.githubusercontent.com/MotherofallVPNs/MoaV/dev/install.sh | bash -s -- -b dev
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 · +41 tokens per session 2983751fc322
- 7d ago Changed · +8 lines · +170 tokens per session e80dd5c19283
- 1mo ago Changed · +7 tokens per session 155324afc212
- 2mo ago First seen · 165 lines · 2,651 tokens per session scan C 2eb9d1321f36
MoaV AGENTS.md is an instructions file published in the GitHub repository MotherofallVPNs/MoaV (453 stars, last pushed today), licensed MIT. It adds 2,869 tokens to every session, about $0.0115 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.