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 mishahanin/heading-os --skill mullvadgit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/mishahanin/heading-os/mullvad)<a href="https://agentmods.dev/skills/mishahanin/heading-os/mullvad"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/mullvad/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/mishahanin/heading-os/mullvad"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/mullvad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 19 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00199 | $0.02108 |
| Opus 5 | $0.00100 | $0.01054 |
| Sonnet 5 | $0.00040 | $0.00422 |
| Haiku 4.5 | $0.00020 | $0.00211 |
Grade A, and why
mullvad 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 6d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mullvad — Fastest Relay Benchmark & Connect
Finds the 3 fastest Mullvad WireGuard relays from this host (by median ICMP latency) and connects to whichever one the user selects. Reuses scripts/mullvad-fastest.py for the benchmark; uses the Mullvad CLI for tunnel control.
Phase 0 — Preflight
Run these checks in order. Bail early with a clear message if any fails.
- CLI present:
mullvad --version. If not found → tell the user "Mullvad CLI is not installed. Get it from https://mullvad.net/download/vpn/" and stop. - Daemon reachable:
mullvad status. If the command errors or prints "Daemon unreachable" / "service not running" → tell the user "Mullvad daemon is not running. Start the Mullvad VPN service and retry." and stop. - Current connection state: parse the
mullvad statusoutput.- If output begins with
Connected→ capture the current relay hostname (lineRelay: <hostname>). - If output begins with
Disconnected→ no tunnel active.
- If output begins with
- Tunnel-bias warning (only if currently connected):
- Show one line:
Currently connected via <hostname>. Pings through the tunnel bias results. - Ask: "Disconnect, measure, and let you reconnect? (recommended) — [D]isconnect / [M]easure anyway / [C]ancel"
- On
D→ runmullvad disconnect, wait 2 s, continue. - On
M→ continue without disconnecting; note the bias in the final summary. - On
C→ stop.
- Show one line:
Phase 1 — Benchmark
Run: python scripts/mullvad-fastest.py --owned-only
- Default region is Europe + Middle East (matches the script default).
- Owned-only is the default - Misha only uses Mullvad-owned relays (provider 31173/Blix).
- The script saves full results to
outputs/operations/mullvad_fastest_YYYY-MM-DD.json. Read that file to get the sorted list — do not re-parse stdout.
If the script exits non-zero → surface the stderr and stop.
Phase 2 — Present Top 3
Read the saved JSON. Show the top 3 entries in a compact numbered table:
Top 3 fastest Mullvad relays from this host:
1) <hostname> <city>, <CC> <Gbps> Gbps <median> ms [DAITA]
2) <hostname> <city>, <CC> <Gbps> Gbps <median> ms
3) <hostname> <city>, <CC> <Gbps> Gbps <median> ms
Reply "connect 1", "connect 2", or "connect 3" to connect.
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.
- 6d ago Changed ab21b7f26e9d
- 9d ago First seen · 153 lines · 199 tokens per session scan A 92b1f018486f
mullvad is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed today), licensed Apache-2.0. It adds 199 tokens to every session and 2,108 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.