Borrowing it
Nothing to install: this file belongs to vonzelle-vzt/vzt-ssh-phone. 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/vonzelle-vzt/vzt-ssh-phone/main/AGENTS.mdgit clone --depth 1 https://github.com/vonzelle-vzt/vzt-ssh-phoneWrote 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/vonzelle-vzt/vzt-ssh-phone/agents-md)<a href="https://agentmods.dev/instructions/vonzelle-vzt/vzt-ssh-phone/agents-md"><img src="https://agentmods.dev/badge/instructions/vonzelle-vzt/vzt-ssh-phone/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/vonzelle-vzt/vzt-ssh-phone/agents-md"><img src="https://agentmods.dev/badge/instructions/vonzelle-vzt/vzt-ssh-phone/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 | $0.01340 | $0.01340 |
| Opus 5 | $0.00670 | $0.00670 |
| Sonnet 5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade C, and why
vzt-ssh-phone AGENTS.md scanned grade C with 1 finding 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 12d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- Mac/Linux: `ssh-keygen -t ed25519` then `cat ~/.ssh/id_ed25519.pub`. How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — agent takeover playbook for vzt-ssh-phone
Audience: an AI coding agent (Claude Code, OpenAI Codex, Gemini CLI, etc.) running in a terminal on the user's Windows PC. This file tells you how to take over and set up remote phone→PC SSH for the user with the least possible effort on their part — drive it yourself, headless, and only hand back the few steps a human physically must do.
Goal
Get the user able to ssh <user>@<tailscale-ip> from their phone and run a CLI (you). Install the SSH server + Tailscale + (optionally) the AI CLIs, authorize the user's device key, and verify — bundling everything so the user interacts the absolute minimum.
The 3 things only a human can do (everything else is yours)
- Approve the UAC elevation prompt (once). It renders on the secure desktop — no software can click it.
- Sign into Tailscale in the browser window that opens (once).
- Sign into each AI CLI in the browser the first time (once, locally) — first-run auth opens on the PC, not the phone.
Plan around these: do everything else automatically, and tell the user clearly when each click is needed.
Procedure
1. Get the repo
If not already present, clone or download it, then cd into it:
git clone https://github.com/vonzelle-vzt/vzt-ssh-phone
cd vzt-ssh-phone
2. Get the user's device public key (recommended)
Ask the user to generate a key on the device they'll connect from and paste the public line:
- Phone SSH app (Termius/Blink): Generate Key → ED25519 → copy public key.
- Mac/Linux:
ssh-keygen -t ed25519thencat ~/.ssh/id_ed25519.pub.
Never ask for a private key. If they can't do this yet, run the install without -PublicKey and authorize the key later (re-run with -PublicKey).
3. Launch the installer ELEVATED and headless, with a status file you poll
Pick an absolute status path (the elevated child runs from system32, so relative paths won't resolve). Choose the CLI(s) to install — typically include the one you are.
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.
- 12d ago First seen · 77 lines · 1,340 tokens per session scan C 74a2bfab794e
vzt-ssh-phone AGENTS.md is an instructions file published in the GitHub repository vonzelle-vzt/vzt-ssh-phone (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,340 tokens to every session, about $0.0067 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
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.
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.
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.
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).
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 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).