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 skills/lyhcode/agent-skills/tailscale-clinpx skills add lyhcode/agent-skills --skill tailscale-cligit clone --depth 1 https://github.com/lyhcode/agent-skillsWhat 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 | $0.00084 | $0.02119 |
| Opus 5 | $0.00042 | $0.01059 |
| Sonnet 5 | $0.00017 | $0.00424 |
| Haiku 4.5 | $0.00008 | $0.00212 |
Grade A, and why
tailscale-cli 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tailscale CLI Assistant
Help users manage Tailscale VPN using the tailscale CLI.
Prerequisites
- Tailscale installed on the device
- Verify setup:
tailscale status
CLI Path by Platform
IMPORTANT: The CLI path differs by platform and installation method.
macOS (App Store)
The CLI is bundled inside the app. Use the full path or create an alias:
# Direct execution
/Applications/Tailscale.app/Contents/MacOS/Tailscale <command>
# Recommended: add alias to ~/.zshrc or ~/.bashrc
alias tailscale="/Applications/Tailscale.app/Contents/MacOS/Tailscale"
macOS (Standalone variant)
Install CLI integration from the client: Settings > CLI integration > Install Now.
This installs a launcher to /usr/local/bin/tailscale.
Linux / Windows
The tailscale binary is in $PATH by default:
tailscale <command>
Force CLI mode (macOS)
If the app intercepts the command, set:
export TAILSCALE_BE_CLI=1
Core Commands
Connect & Authenticate
tailscale up # Connect to Tailscale
tailscale up --auth-key=<key> # Auto-authenticate with auth key
tailscale up --force-reauth # Force re-authentication
tailscale down # Disconnect
tailscale login # Log in (add device to tailnet)
tailscale logout # Log out (expire session)
tailscale switch <account> # Switch account (fast user switching)
tailscale switch --list # List available accounts
Status & Info
tailscale status # Show connected devices
tailscale status --json # JSON output (detailed)
tailscale status --json | jq '.Peer[] | {Name: .HostName, IP: .TailscaleIPs[0]}'
tailscale ip # Show this device's Tailscale IPs
tailscale ip -4 # IPv4 only (100.x.y.z)
tailscale ip -6 # IPv6 only
tailscale ip <hostname> # Get IP of another device
tailscale whois <ip> # Look up device/user by IP
tailscale whois --json <ip> # JSON output
tailscale version # Print version
tailscale netcheck # Network connectivity report
What ships with it
1 file 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.
- yesterday First seen · 281 lines · 84 tokens per session scan A 20cfb346663a
tailscale-cli is a skill published in the GitHub repository lyhcode/agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 2,119 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…