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 magnus919/agent-skills --skill tailnet-policygit clone --depth 1 https://github.com/magnus919/agent-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/magnus919/agent-skills/tailnet-policy)<a href="https://agentmods.dev/skills/magnus919/agent-skills/tailnet-policy"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/tailnet-policy/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/magnus919/agent-skills/tailnet-policy"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/tailnet-policy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 21 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 182 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 186 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 196 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 287 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00060 | $0.02183 |
| Opus 5 | $0.00030 | $0.01092 |
| Sonnet 5 | $0.00012 | $0.00437 |
| Haiku 4.5 | $0.00006 | $0.00218 |
Grade A, and why
tailnet-policy 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 8d 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tailnet-policy
Overview
Headscale uses Tailscale-compatible policy files written in huJSON (Human JSON — standard JSON with trailing commas and // comments). Policy files control:
- ACLs (deprecated legacy syntax) —
{action, users, ports}rules - Grants (modern syntax) —
{src, dst, ip, proto, via}rules - Tags — Node identity tags (
tag:dev,tag:prod) - TagOwners — Which users/groups can apply which tags
- AutoApprovers — Auto-approval for subnet routers and exit nodes
- Tailscale SSH — SSH access rules via
ssh.usersandssh.action
ACLs vs Grants
| Feature | ACLs (legacy) | Grants (modern) |
|---|---|---|
| Format | {action: "accept", users: [...], ports: [...]} |
{src: [...], dst: [...], ip: [...], proto: "tcp"} |
| Port filtering | Embedded in ports: ["*:*"] |
Separate ip field for ports |
| Protocol filtering | Not supported | proto field (tcp, udp, icmp) |
| Destination routing | Not supported | via field for relay/exit nodes |
| Status | Deprecated by Tailscale | Current recommended syntax |
Use Grants wherever possible. The migrate-acls-to-grants.py script can convert legacy ACL files automatically.
Policy Location
The policy file path is configured in Headscale's config.yaml:
policy:
path: /etc/headscale/policy.hujson
After modifying the policy file, reload it on the Headscale server:
# Reload via SIGHUP
kill -HUP $(pgrep headscale)
# Or use the convenience script
./skills/tailnet-policy/reload-headscale-policy.sh
Writing Policy
Allow-All (default-open)
{
// Grants that allow all traffic
"grants": [
{
"src": ["autogroup:member"],
"dst": ["autogroup:member"],
"ip": ["*:*"]
}
],
// Tag ownership
"tagOwners": {
"tag:dev": ["autogroup:admin"],
"tag:prod": ["autogroup:admin"]
}
}
Deny-All (default-closed)
{
"grants": [
// Only allow ICMP (ping) between all members
{
"src": ["autogroup:member"],
"dst": ["autogroup:member"],
"ip": ["*"],
"proto": "icmp"
}
],
// Specific grants added per-service
"tagOwners": {
"tag:monitor": ["autogroup:admin"]
}
}
What ships with it
5 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.
- 8d ago First seen · 297 lines · 60 tokens per session scan A e10e7af1440d
tailnet-policy is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 2,183 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…