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 headscale-routinggit 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/headscale-routing)<a href="https://agentmods.dev/skills/magnus919/agent-skills/headscale-routing"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/headscale-routing/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/headscale-routing"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/headscale-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 49 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 51 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 55 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 | $0.00047 | $0.01189 |
| Opus 5 | $0.00023 | $0.00594 |
| Sonnet 5 | $0.00009 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
headscale-routing 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 9d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
headscale-routing
Overview
Subnet routers extend a tailnet to non-Tailscale devices (printers, NAS boxes, IoT devices) by advertising the local LAN subnet routes through a gateway node. Exit nodes route all non-tailnet internet traffic through a home server, providing privacy on untrusted networks (coffee shop Wi-Fi, hotel networks, etc.).
Headscale manages route approval centrally — routes must be advertised by the gateway node and then approved on the Headscale server before they become active.
Subnet Router Setup
- On the gateway node, advertise the LAN subnet:
tailscale up --advertise-routes=192.168.1.0/24 - On the Headscale server, approve the route:
headscale routes approve -r <route-id> - On client nodes that need to reach the subnet, enable route acceptance:
tailscale up --accept-routes
Exit Node Setup
- On the exit node, advertise it as an exit node:
tailscale up --advertise-exit-node - On the Headscale server, approve the exit node route.
- On the client, select the exit node:
tailscale set --exit-node=<node-name>
Auto-Approvers
Configure Headscale ACL policy to auto-approve routes from trusted nodes:
{
"autoApprovers": {
"routes": {
"192.168.0.0/16": ["tag:gateway"]
},
"exitNode": ["tag:gateway"]
}
}
Nodes carrying tag:gateway will have their advertised routes or exit-node status
approved automatically without manual intervention.
Via Filtering
Use grants.via in ACL policies to restrict cross-subnet access:
{
"grants": [
{
"src": ["tag:monitoring"],
"dst": ["tag:servers"],
"app": ["prometheus"],
"via": ["192.168.10.0/24"]
}
]
}
This ensures traffic from monitoring nodes to servers is routed through the specified subnet, enabling firewall policies on the gateway to inspect or filter traffic.
SNAT on Subnet Routers
By default, Headscale enables Source NAT (SNAT) on subnet router traffic. This means traffic originating from tailnet clients destined for the advertised subnet appears to come from the gateway node's IP. To disable SNAT:
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.
- 9d ago First seen · 161 lines · 47 tokens per session scan A 6aaf3e548621
headscale-routing is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,189 once invoked, about $0.0002 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
routine
Manage CocoRoutine Snowflake task scheduling. Usage: $routine list, $routine schedule --cadence , $routine disable , $routine delete .
terraform-expert
Expert-level Terraform infrastructure as code, modules, state management, and production best practices. Use when the user mentions infrastructure as code, devops, or automation, or when the task involves Terraform Basics, Resource Management, Modules, or State Management.
floom
Create, run, and manage Floom AI workers — cloud automations that run on a schedule or a trigger and report back. Reach for this whenever the user wants something to happen repeatedly or in the background rather than a one-off script: a recurring task, "every day / every hour / every week", "schedule this", "run it on…
bridge-health
Quick health check on the bridge daemon (CEO machine + any exec mirrors). Surfaces heartbeat staleness, version drift, active sessions, and the Phase 1 to Phase 2 adoption gate metrics. Use when the dashboard feels stale, the sync-pill is red, the daemon may have crashed, or before a /push-updates that changes daemon…
control-plane-ops
Operar o control-plane local-first do agents-lab com board canônico, long-runs bounded, handoff/checkpoint, rollout/rollback e espelhos externos sem perder governança.
gandi
Gère les domaines, DNS et emails via l'API Gandi v5. Permet de lister les domaines, consulter/modifier les enregistrements DNS, gérer les boîtes mail et configurer les redirections.