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 ksachdeva/zephyr-rtos-ai --skill zephyr-power-managementgit clone --depth 1 https://github.com/ksachdeva/zephyr-rtos-aiWrote 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/ksachdeva/zephyr-rtos-ai/zephyr-power-management)<a href="https://agentmods.dev/skills/ksachdeva/zephyr-rtos-ai/zephyr-power-management"><img src="https://agentmods.dev/badge/skills/ksachdeva/zephyr-rtos-ai/zephyr-power-management/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/ksachdeva/zephyr-rtos-ai/zephyr-power-management"><img src="https://agentmods.dev/badge/skills/ksachdeva/zephyr-rtos-ai/zephyr-power-management.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 | $0.00059 | $0.02578 |
| Opus 5.5 | $0.00024 | $0.01031 |
| Sonnet 5.5 | $0.00012 | $0.00516 |
| Haiku 4.5 | $0.00006 | $0.00258 |
Grade A, and why
zephyr-power-management 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 2mo 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zephyr Power Management
Overview
Use this skill when the goal is to reduce power without breaking responsiveness. Power management in Zephyr is usually a combination of:
- system PM through the idle-thread and policy path
- device runtime PM for individual peripherals
- correctly configured wake sources
- measurement to confirm the real current draw
Power management crosses several Zephyr areas. When needed, also read:
- ../zephyr-kconfig/SKILL.md for
prj.conf, symbol dependencies, and menuconfig debugging - ../zephyr-devicetree/SKILL.md for wake-capable pins, interrupts, and board wiring
- ../zephyr-gpio/SKILL.md for GPIO wake interrupts
- ../zephyr-isr/SKILL.md for ISR-safe wake handling
- ../zephyr-threading/SKILL.md for blocking thread design, workqueues, and scheduler behavior
- ../zephyr-kernel-synchronization/SKILL.md for semaphores, events, mutexes, and wait-based coordination
- ../zephyr-device-drivers/SKILL.md for driver PM callbacks and
PM_DEVICE_*integration
Workflow
1. Choose the PM level
Decide what should sleep:
- System PM: Use when the whole application is mostly idle and should enter low-power states automatically when no runnable work remains.
- Device runtime PM: Use when only specific peripherals should suspend while the rest of the system stays active.
- Both: Common in battery-powered products. Runtime PM trims peripheral waste while system PM handles deep idle periods.
Use the application behavior to choose the depth:
- frequent wakeups and tight latency budget: prefer lighter states
- long idle windows and interrupt-driven wakeups: allow deeper states
- thermal pressure or burst workloads: combine reduced activity with PM constraints and scheduling discipline
2. Enable the right Kconfig symbols
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.
- 2mo ago First seen · 291 lines · 59 tokens per session scan A 6c5564a247d5
zephyr-power-management is a skill published in the GitHub repository ksachdeva/zephyr-rtos-ai (23 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,578 once invoked, about $0.0002 per session on Opus 5.5. 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.
zephyr-power-management compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zephyr-power-managementksachdeva/zephyr-rtos-ai | Skill | 23 | 5mo ago | Apache-2.0 | A | 59 | Claude Code, Codex |
| home-assistantsammcj/agentic-coding | Skill | 169 | yesterday | Apache-2.0 | A | 57 | Claude Code |
| raspberry-pi-pico2sammcj/agentic-coding | Skill | 169 | yesterday | Apache-2.0 | A | 24 | Claude Code |
| gapgraph-robots/graph-as-policy | Skill | 183 | 6d ago | Apache-2.0 | A | 195 | Claude Code |
| piper-tts-trainingsammcj/agentic-coding | Skill | 169 | yesterday | Apache-2.0 | A | 79 | Claude Code, Codex |
| sbceAdamBien/airails | Skill | 63 | 3d ago | MIT | A | 215 | Claude Code |
| web-componentsAdamBien/airails | Skill | 63 | 3d ago | MIT | A | 160 | Claude Code |