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 modem-tunegit 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/modem-tune)<a href="https://agentmods.dev/skills/mishahanin/heading-os/modem-tune"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/modem-tune/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/modem-tune"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/modem-tune.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 | $0.00151 | $0.02275 |
| Opus 5 | $0.00076 | $0.01137 |
| Sonnet 5 | $0.00030 | $0.00455 |
| Haiku 4.5 | $0.00015 | $0.00228 |
Grade A, and why
modem-tune 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 10d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modem Tune -- IMEI Reconfiguration
Automates changing the reported IMEI on either of two personal GL.iNet travel routers,
auto-detected from the live modem. The two are the GL-XE300 (Quectel EG25-G, gl_modem AT over SSH) and the GL-E5800 "Mudi 7" (Quectel RG650V-EU, ubus modem.CPU.AT over
SSH). All mechanics live in scripts/modem-tune.py. This skill is the conversational
wrapper that owns the device-confirm gate and the reset-confirm gate.
Spec: docs/superpowers/specs/2026-05-30-modem-tune-skill-design.md (data overlay: .heading-os-data/docs/superpowers/specs/2026-05-30-modem-tune-skill-design.md).
Device + procedure reference: outputs/operations/reference/gl-inet-mobile-router-imei-reconfig.md.
Modes
- Default / full rotation (
/modem-tune): detect -> confirm device -> status -> generate -> apply -> confirm reset -> reset -> verify. /modem-tune status: detect -> confirm device -> read the live IMEI(s), SIM, network, and signal. No change./modem-tune revert: detect -> confirm device -> restore the factory IMEI (fromconfig/modem.json), then confirm reset + reset + verify.
Every mode accepts an explicit --device {xe300,e5800}, which skips auto-detection.
Pre-flight
Both routers are reached over SSH with credentials from .env (MODEM_HOST,
MODEM_USER, MODEM_SSH_PASSWORD -- unchanged, shared across devices). No VPN
pre-flight applies here. These are local authenticated devices, not public web
services. config/modem.json is now per-device, one entry per router: transport,
host, TAC, factory IMEI. An unconfigured device exits cleanly (exit 2) on generate,
apply and revert, but not on detect or status.
If MODEM_SSH_PASSWORD is missing the engine exits with a clear error; tell the CEO to
add the MODEM_* block to .env and stop.
Phase 0 -- Detect (always run first)
Run python3 scripts/modem-tune.py detect (or detect --device <xe300|e5800> if the
CEO already named the device). Read-only; identifies the connected modem from its
live model string.
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.
- 10d ago First seen · 177 lines · 151 tokens per session scan A 4a46830d7fa5
modem-tune is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 151 tokens to every session and 2,275 once invoked, about $0.0008 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
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
findmy
Track Apple devices/AirTags via FindMy.app on macOS.
openhue
Control Philips Hue lights, scenes, rooms via OpenHue CLI.
actual-setup
Set up Actual Computer (actual.inc) inference in Hermes.
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.