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 fritzgit 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/fritz)<a href="https://agentmods.dev/skills/larsboes/axon/fritz"><img src="https://agentmods.dev/badge/skills/larsboes/axon/fritz/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/fritz"><img src="https://agentmods.dev/badge/skills/larsboes/axon/fritz.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 | $0.00203 | $0.02296 |
| Opus 5 | $0.00102 | $0.01148 |
| Sonnet 5 | $0.00041 | $0.00459 |
| Haiku 4.5 | $0.00020 | $0.00230 |
Grade A, and why
fritz scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **The box lists its own valid usernames, unauthenticated:** `curl -s "http://<host>/login_sid.lua?version=2"` How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fritz
Read the Fritz!Box's own view of the network — cleaner and more complete than an ARP scan (real hostnames, connection type, active/inactive), and the only place the radio-level truth lives. Two transports in one tool:
- TR-064 (
fritzconnection) — the authoritative host table and guest-WLAN state. - AVM JSON API (
login_sid.lua+data.lua, stdlib only) — channel, width, DFS exposure, mesh topology, event log, subsystem load. A slow-WLAN diagnosis needs this one.
uv run handles the dep; the host needs uv (one binary). Read-only by contract — every
request is a GET or an xhr=1 fetch, and no subcommand may be added that writes configuration.
Setup (once)
- On the Fritz!Box: enable TR-064 (Heimnetz → Netzwerk → Netzwerkeinstellungen → "Zugriff für Apps erlauben"), and create a dedicated user (System → FRITZ!Box-Benutzer) with the "FRITZ!Box Einstellungen" right. Use that user, not the box password.
- In Bitwarden: an item named by
FRITZ_BW_ITEM(defaulthome-assistant/fritz) carrying the password — either as a custom fieldFRITZBOX_PASSWORDor in the item's own password slot. Provision via Axonsetup-secret.sh. - In the overlay config (
<overlay>/config/home-assistant.vars):FRITZBOX_HOST,FRITZBOX_USERNAME, and optionallyFRITZ_BW_ITEM. An env var of the same name wins per key. - Point
bwat the vault once:bw config server <vault-url>.
Run
Unlock Bitwarden interactively, then call (the tool reads $BW_SESSION, never the master password):
export BW_SESSION=$(bw unlock --raw)
# TR-064 — the authoritative host table
scripts/fritz devices # active hosts: ip / mac / interface / active / name
scripts/fritz devices --all -j # include inactive, JSON
scripts/fritz guest # guest-WLAN enabled?
# JSON API — what TR-064 cannot tell you
scripts/fritz overview # model, uptime, device count, unmeshed flag, subsystem load
scripts/fritz chan # active channel + width per band, and whether that sits in DFS
scripts/fritz mesh # which AP serves how many clients, and how it backhauls
scripts/fritz log -f wlan # timestamped radar / DFS / channel-change events
scripts/fritz wlan --detail # every WLAN client and its serving AP
scripts/fritz api <page> # raw data.lua page — the escape hatch
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 · 136 lines · 203 tokens per session scan A 8be66c72b64f
fritz is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 203 tokens to every session and 2,296 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
usecase-smart-home-brain
Coordinate smart-home actions across existing integrations with clear dry-run and safety confirmation.
ryu-local-model
Search, download, and serve a local GGUF model on a Ryu node via Core's models and engines REST surface. Covers catalog search and device-fit, installing a specific quantization, activating a model, and listing engines (the engine is derived from the model format). Use when a user wants to get a local model running on…
beryl-it-tech
🛠️ Device, system, and network diagnosis.
it-work-reviewer
🔍 Evidence audit for device repair claims.
gx3-existing-project-audit
Analyze an existing Mitsubishi GX Works3 .gx3 project with gx3-cli when the user asks what a ladder does, why a device turns on, or whether a project has risks.
eight-sleep
Unofficial Eight Sleep pod data for AI agents. Writes stay fail-closed. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Eight Sleep data or actions through an agent.