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-smfgit 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-smf)<a href="https://agentmods.dev/skills/ksachdeva/zephyr-rtos-ai/zephyr-smf"><img src="https://agentmods.dev/badge/skills/ksachdeva/zephyr-rtos-ai/zephyr-smf/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-smf"><img src="https://agentmods.dev/badge/skills/ksachdeva/zephyr-rtos-ai/zephyr-smf.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 | $0.00080 | $0.01357 |
| Opus 5 | $0.00040 | $0.00678 |
| Sonnet 5 | $0.00016 | $0.00271 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
zephyr-smf 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zephyr State Machine Framework (SMF)
Overview
SMF is an application-agnostic framework for integrating state machines into Zephyr applications. Enable with CONFIG_SMF=y.
Core Concepts
State Structure
Every state has three optional actions:
- Entry: Executes when entering the state
- Run: Executes on each
smf_run_state()call - Exit: Executes when leaving the state
// User object MUST have smf_ctx as FIRST member
struct s_object {
struct smf_ctx ctx; // MUST be first
/* application-specific data */
};
State Definition
enum app_state { STATE_IDLE, STATE_ACTIVE, STATE_ERROR };
static const struct smf_state app_states[] = {
[STATE_IDLE] = SMF_CREATE_STATE(idle_entry, idle_run, idle_exit, NULL, NULL),
[STATE_ACTIVE] = SMF_CREATE_STATE(active_entry, active_run, NULL, NULL, NULL),
[STATE_ERROR] = SMF_CREATE_STATE(NULL, error_run, error_exit, NULL, NULL),
};
SMF_CREATE_STATE parameters: (entry, run, exit, parent, initial)
- Set unused actions to
NULL parent: For hierarchical states (requiresCONFIG_SMF_ANCESTOR_SUPPORT)initial: Initial child state (requiresCONFIG_SMF_INITIAL_TRANSITION)
Action Signatures
// Entry and exit actions
static void state_entry(void *o) { /* ... */ }
static void state_exit(void *o) { /* ... */ }
// Run action - returns event handling result
static enum smf_state_result state_run(void *o) {
struct s_object *s = (struct s_object *)o;
// Process events, trigger transitions
return SMF_EVENT_HANDLED; // or SMF_EVENT_PROPAGATE for HSM
}
Workflow
1. Determine State Machine Type
| Type | Use Case | Kconfig |
|---|---|---|
| Flat | Simple sequential states, no nesting | CONFIG_SMF=y |
| Hierarchical (HSM) | Shared behavior, nested states | Add CONFIG_SMF_ANCESTOR_SUPPORT=y |
| HSM + Initial Transitions | Auto-transition to child states | Add CONFIG_SMF_INITIAL_TRANSITION=y |
Step 1a: For flat state machines, proceed to step 2.
What ships with it
3 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.
- 10d ago First seen · 149 lines · 80 tokens per session scan A ec6e90e5f609
zephyr-smf is a skill published in the GitHub repository ksachdeva/zephyr-rtos-ai (23 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,357 once invoked, about $0.0004 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
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
raspberry-pi-pico2
Use when developing with Raspberry Pi Pico 2 or the Pi Debug Probe.
gap
Program robots with GaP (graph-as-policy) — compile natural-language tasks into typed, verified robot skill graphs and run them on simulators or real robots. Use when the user mentions GaP or graph-as-policy, robot manipulation, robot skills, robot tools or capabilities, skill registries, open-robot-skills, LIBERO or…
piper-tts-training
Train custom TTS voices for Piper (ONNX format) using fine-tuning or from-scratch approaches. Use when creating new synthetic voices, fine-tuning existing Piper checkpoints, preparing audio datasets for TTS training, or deploying voice models to devices like Raspberry Pi or Home Assistant. Covers dataset preparation…
web-components
Architecture and coding rules for single-page applications using web components, BCE layering, lit-html templating, unidirectional Redux-style state management (reduction.js, standards-based), and standards-based client-side routing (Navigation API + URLPattern). Web standards and web platform first, minimal external…
sbce
Spec-driven BCE workflow where one capability spec equals one business component (same name) and the spec is the boundary contract. Invoked as /sbce new|apply (or by intent), it drives declare → converge; the stack's own test loop is the oracle for "done". new accepts a BC name or a natural-language feature…