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 larsboes/Axon --skill piholegit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/pihole)<a href="https://agentmods.dev/skills/larsboes/axon/pihole"><img src="https://agentmods.dev/badge/skills/larsboes/axon/pihole/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/larsboes/axon/pihole"><img src="https://agentmods.dev/badge/skills/larsboes/axon/pihole.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00139 | $0.01152 |
| Opus 5 | $0.00069 | $0.00576 |
| Sonnet 5 | $0.00028 | $0.00230 |
| Haiku 4.5 | $0.00014 | $0.00115 |
Grade A, and why
pihole scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pihole
Drive the home Pi-hole over its v6 REST API (/api/..., auth via X-FTL-SID). Pi-hole logs
every DNS query, so it answers "what does this device talk to on the internet" — per-device egress,
the payoff after isolating IoT onto its own VLAN. Pure Python 3 stdlib, no deps: python3 on the
host is enough.
Setup (once)
- In the overlay config (non-secret): set
PIHOLE_HOST(base URL/host of the Pi-hole; scheme +:portoptional) in<overlay>/config/home-assistant.vars(override its root with$AXON_HOME_ROOT). The tool fails cleanly, naming a missing/TODO-key, until it's filled in. - In Bitwarden (secret only): an item
home-assistant/pihole(override with$PIHOLE_BW_ITEM) with the custom fieldPIHOLE_PASSWORD(the admin/API password). Provision via Axonsetup-secret.sh. The item may not exist yet — the tool fails cleanly, naming the missing field, until it does. - Point
bwat the vault once:bw config server <vault-url>. - On the network: the Fritz!Box DHCP DNS must point at the Pi for whole-house coverage, and
Pi-hole must run in
network_mode: hostso per-client source IPs survive (Docker NAT would hide them and break per-device egress).
Run
Unlock Bitwarden interactively, then call (the tool reads $BW_SESSION, never the master password):
export BW_SESSION=$(bw unlock --raw)
scripts/pihole status # overview + blocking state
scripts/pihole egress <device-ip> # what one device phones home to
scripts/pihole top-domains 20
scripts/pihole top-clients
scripts/pihole block-off 300 # pause blocking 5 min
scripts/pihole block-on
scripts/pihole deny telemetry.example.com
scripts/pihole allow updates.example.com
scripts/pihole --help (or <command> --help) lists every command and its args.
Egress allow-listing (turn isolation into containment)
After isolating an IoT device, lock it to only its needed vendor domains: review egress <ip>,
then deny everything else (or build a per-device allowlist in the UI). A compromised camera then
can't exfiltrate or pivot — DNS for anything but its vendor is refused.
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.
- 8d ago First seen · 79 lines · 139 tokens per session scan A e16bdb1532e8
pihole is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 1,152 once invoked, about $0.0007 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
eng-runbook
A one-page engineering runbook: a practical guide for operating a software service. It includes alerts, dashboards, procedures, on-call information, and an incident checklist.
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
compute-env-setup
Prepare reproducible setup instructions and validate a user-managed named software environment on an Open Science SSH Compute Host, including direct SSH and Slurm hosts. Use when a remote job needs packages, modules, cache variables, or a repeatable activation that the host does not already provide.
Tencent Cloud Infra
A command-line guide for managing Tencent Cloud services, including servers, networks, domains, certificates, storage, permissions, and monitoring. Tencent Cloud is a cloud provider, and tccli is its command-line tool.
terraform-ops
Infrastructure-as-Code operations: plan, apply, import, state management, module development, and drift detection using Terraform CLI.
cloud-migration
Cloud migration strategy and execution: assessment frameworks, migration patterns, database migration, network cutover, and multi-cloud planning.