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 skills add alivirgo/Major-AI-Skills --skill tailscalegit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/skills/alivirgo/major-ai-skills/tailscale)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/tailscale"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/tailscale/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/skills/alivirgo/major-ai-skills/tailscale"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/tailscale.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 | $0.00040 | $0.02357 |
| Opus 5.5 | $0.00016 | $0.00943 |
| Sonnet 5.5 | $0.00008 | $0.00471 |
| Haiku 4.5 | $0.00004 | $0.00236 |
Grade D, and why
tailscale scanned grade D with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo tee /etc/sysctl.d/99-tailscale.conf >/dev/null <<'EOF' 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://tailscale.com/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://tailscale.com/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tailscale Mesh VPN AI Skill Guide (Claude)
Overview & Engine Architecture
Tailscale is a coordination-plane + WireGuard data-plane mesh VPN. Nodes register with a control server (Tailscale SaaS or self-hosted Headscale), exchange keys and ACL policy, then encrypt traffic peer-to-peer. When UDP hole-punching fails (symmetric NAT, locked-down firewalls), encrypted packets fall back through DERP relays (or optional peer relays). Agents should treat route advertisement and admin approval as a double opt-in, treat MagicDNS as an OS DNS integration problem, and never invent auth keys or ACL principals.
┌─────────────────────────────────────────────────────────────┐
│ Tailscale mesh │
│ │
│ Control plane (coord + ACL + MagicDNS names) │
│ ├── Auth / tags / key expiry │
│ ├── autoApprovers for routes & exit nodes │
│ └── Policy: who may reach which tags / CIDRs │
│ │
│ Data plane (WireGuard) │
│ ├── Prefer direct UDP (often ListenPort ~41641) │
│ ├── Else DERP / peer-relay (encrypted WG still) │
│ └── Subnet router / exit node = forward + advertise │
└─────────────────────────────────────────────────────────────┘
When to use / when not to
Use when
- Joining laptops, CI runners, and cloud VMs into one private overlay without opening inbound WAN ports.
- Exposing a LAN that cannot run Tailscale via a subnet router.
- Debugging “slow VPN” (DERP relay) vs broken routes / ACL denials.
- Publishing internal HTTPS with Serve, or carefully exposing with Funnel.
Do not use when
- You need a self-managed, no-vendor WireGuard fabric with your own key distribution →
@wireguard. - You need classic site-to-site IPsec / vendor SD-WAN with existing enterprise gear only.
- Someone asks to paste live auth keys, OAuth client secrets, or full ACL with real employee emails into chat/Git → refuse; use env vars / secret stores (
@vault).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +64 lines · +14 tokens per session 0c1db4e0210b
- 1mo ago Changed · -18 tokens per session 96b680252d14
- 1mo ago First seen · 128 lines · 44 tokens per session scan D 0758a64c1c66
tailscale is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 2,357 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
deploying-tailscale-for-zero-trust-vpn
Deploy and configure Tailscale as a WireGuard-based zero trust mesh VPN with identity-aware access controls, ACLs, and exit nodes for secure peer-to-peer connectivity.
deploying-tailscale-for-zero-trust-vpn
Deploy and configure Tailscale as a WireGuard-based zero trust mesh VPN with identity-aware access controls, ACLs, and exit nodes for secure peer-to-peer connectivity.
accounting-software-selection
Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request. Use for choosing accounting software.
accounting-audit-system-builder
Routes an accounting or audit request to the right module skill, from software selection through monthly closing, asking only what is missing. Use for books of accounts or audit files.
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
aws-cost-cleanup
Automated cleanup of unused AWS resources to reduce costs.