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/usetemi/skills/tailscalenpx skills add usetemi/skills --skill tailscalegit clone --depth 1 https://github.com/usetemi/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/usetemi/skills/tailscale)<a href="https://agentmods.dev/skills/usetemi/skills/tailscale"><img src="https://agentmods.dev/badge/skills/usetemi/skills/tailscale.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.01296 |
| Opus 5 | $0.00043 | $0.00648 |
| Sonnet 5 | $0.00017 | $0.00259 |
| Haiku 4.5 | $0.00009 | $0.00130 |
Grade A, and why
tailscale 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 4d 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.
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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tailscale Platform
Use this skill for any Tailscale work, from local development connectivity to production tailnet architecture and incident diagnostics.
Tailscale changes quickly. Ground version-sensitive advice in the local CLI and current official docs before making claims about flags, policy syntax, product limits, or Kubernetes CRDs.
First Steps
-
Infer posture from context.
- For personal tailnets, MVPs, local dev, demos, and scrappy startup work, give the fastest viable path first.
- For organizations, production, shared tailnets, sensitive systems, or compliance contexts, use secure-first defaults.
- If the context is unclear and the posture changes commands, exposure, key handling, or access policy, ask before changing state.
-
Inspect local project and system context before prescribing commands.
rg --files -g 'tailnet*.json' -g '*tailscale*' -g 'acl.hujson' -g 'policy.hujson' -g 'docker-compose*.yml' -g 'Dockerfile*' -g '.github/workflows/**' -g 'k8s/**' -g 'helm/**' command -v tailscale tailscale version tailscale --help tailscale <subcommand> --help -
Prefer read-only checks first unless the user explicitly asks to mutate local Tailscale state, tailnet policy, Kubernetes resources, or remote resources.
tailscale status tailscale status --json tailscale netcheck tailscale ping <peer> tailscale dns status tailscale serve status tailscale funnel status -
Use official Tailscale docs as the source of truth. Third-party posts can help discover issues, but do not encode them as facts unless confirmed by official docs or the current CLI.
Reference Routing
- Read
references/policy-security.mdfor grants vs ACLs, policy HuJSON, tags, groups, tests,sshTests, Tailscale SSH, device posture, app capabilities, FunnelnodeAttrs, and Tailnet Lock cautions. - Read
references/routing-connectors.mdfor subnet routers, exit nodes, app connectors, MagicDNS, split DNS, route injection, HA/failover, regional routing, DERP/direct diagnostics,tailscale netcheck,tailscale ping, andtailscale status. - Read
references/expose-services.mdfor Tailscale Serve, Funnel, Tailscale Services, TailVIPs, HTTPS certs, identity headers, app capabilities headers, service config files, drain/advertise flows, TCP/TLS forwarding, and public exposure gotchas. - Read
references/automation-containers.mdfor auth keys, OAuth clients, workload identity federation, ephemeral nodes, GitHub Actions, Docker, userspace networking, serverless patterns,tsnet, API usage, and GitOps policy workflows. - Read
references/kubernetes.mdfor the Tailscale Kubernetes Operator, tags/OAuth prerequisites, ingress, egress, API server proxy, Connector, ProxyGroup, ProxyClass, Recorder, subnet routers, app connectors, version compatibility, and CNI notes. - Read
references/production-diagnostics.mdfor production review checklists, least privilege, key expiry, device approval, logs, network flow logs, audit logs, webhooks/log streaming, update policy, incident diagnostics, and safe read-only commands.
What ships with it
6 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.
- 4d ago First seen · 121 lines · 86 tokens per session scan A e2cc49645ee4
tailscale is a skill published in the GitHub repository usetemi/skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,296 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
higgsfield-soul
Creates and manages reusable character profiles (Soul IDs) for consistent facial and stylistic identity across multiple image and video generations. Provides identity-vs-motion prompt separation, character sheet creation workflows, micro-expression direction, and Soul Cast AI actor configuration. Use when the user…
higgsfield-acting
Writes the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per character plus a per-scene rewrite of it, and a…
higgsfield
Use this skill whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Sora 2, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema…
higgsfield-camera
Use when the user asks about camera movements, shot types, or how to describe camera behavior in a Higgsfield prompt. Contains all named camera controls with descriptions, best use cases, and example prompt phrases.
higgsfield-troubleshoot
Use when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output.
higgsfield-models
Use when the user asks which model to use, wants to compare models, or needs guidance on selecting between Kling, Sora 2, Wan, Seedance, Veo 3, Minimax Hailuo, Soul, Nano Banana, or other Higgsfield engines.