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 beriberikix/zephyr-agent-skills --skill zephyr-foundationsgit clone --depth 1 https://github.com/beriberikix/zephyr-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/beriberikix/zephyr-agent-skills/zephyr-foundations)<a href="https://agentmods.dev/skills/beriberikix/zephyr-agent-skills/zephyr-foundations"><img src="https://agentmods.dev/badge/skills/beriberikix/zephyr-agent-skills/zephyr-foundations/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/beriberikix/zephyr-agent-skills/zephyr-foundations"><img src="https://agentmods.dev/badge/skills/beriberikix/zephyr-agent-skills/zephyr-foundations.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 | $0.00070 | $0.00697 |
| Opus 5 | $0.00035 | $0.00349 |
| Sonnet 5 | $0.00014 | $0.00139 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
zephyr-foundations 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 11d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zephyr Foundations
Mastering the bedrock of Zephyr is essential for writing efficient, robust, and idiomatic code.
Core Workflows
1. Idiomatic C Patterns
Zephyr uses specific macros to manage memory and hardware-software mapping.
- Reference: zephyr_macros.md
- Key Tools:
CONTAINER_OF,BIT(),GENMASK(),ARRAY_SIZE.
2. Real-Time Concurrency
Safe multi-threading and interrupt handling are critical for stability.
- Reference: concurrency.md
- Key Tools:
k_mutex,k_sem,k_spinlock,atomic_t, ISR safety rules.
3. Hardware Literacy (Devicetree)
Understanding how code interacts with the hardware description.
- Reference: devicetree_basics.md
- Key Tools: Nodes, properties, phandles, overlays, and advanced deletion.
4. Robust Error Handling
Preventing crashes through defensive programming.
- Reference: error_handling.md
- Key Tools:
errno.h,BUILD_ASSERT, validation patterns, return code checking.
Quick Start (Defensive Pattern)
int sensor_read_checked(const struct device *dev)
{
if (dev == NULL || !device_is_ready(dev)) {
return -ENODEV;
}
return 0;
}
Validation Checklist
- Shared bit-field logic uses Zephyr macros (
BIT,GENMASK) instead of raw literals. - Thread-shared state is protected with mutex/spinlock/atomic primitives.
- Error paths return standard negative
errnocodes. - Defensive guards exist for null pointers, bounds, and device readiness checks.
Automation Tools
- errno_return_check.py: Detect likely non-negative
errnoreturn statements in C/C++ code.
Examples & Templates
- template_driver.c: A complete skeleton showing how to combine DT macros, mutexes, and config-data separation.
Resources
What ships with it
7 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.
- 11d ago First seen · 68 lines · 70 tokens per session scan A 5c9ab1cedb0e
zephyr-foundations is a skill published in the GitHub repository beriberikix/zephyr-agent-skills (63 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 697 once invoked, about $0.0003 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
mobile-hardware-ble-nfc
BLE scanning/connecting/GATT operations with react-native-ble-plx, NFC tag reading/writing with react-native-nfc-manager, permissions, background mode, battery-efficient patterns.
mactop
Retrieve real-time hardware metrics from Apple Silicon Macs using mactop. Provides CPU, RAM, GPU, power, thermal, network, disk I/O, and Thunderbolt bus information. Use when the user wants system stats, hardware monitoring, or performance metrics on Apple Silicon Macs.
home-assistant-integration
Use this skill when creating, scaffolding, reviewing, or maintaining Python Home Assistant custom integrations, including work on customcomponents, manifests, config flows, options flows, config entries, platforms/entities, DataUpdateCoordinator, integration automation triggers, diagnostics, repairs…
home-assistant-card
Use when creating, reviewing, debugging, or maintaining Home Assistant custom Lovelace cards or card editors, including custom elements, Web Components, hass data, setConfig, getCardSize/getGridOptions, getConfigElement/getConfigForm, window.customCards, resource registration, HACS card packages, entity display…
zephyr-device-drivers
Comprehensive Zephyr device driver expertise covering driver model, device instances, initialization levels, power management, and bus-specific patterns (I2C, SPI, UART, GPIO). Use this skill when you need to: (1) Create custom device drivers from scratch, (2) Use existing driver APIs (GPIO, I2C, SPI, UART, ADC, PWM…
zephyr-i2c
Comprehensive Zephyr I2C subsystem expertise for Inter-Integrated Circuit bus communication. Use when: (1) Configuring I2C controllers or devices via devicetree or Kconfig, (2) Implementing synchronous I2C transfers with i2ctransfer/i2cread/i2cwrite, (3) Using register access helpers like…