What is yocto-project?

A guide for making changes in Yocto Project, OpenEmbedded, and Poky codebases. Yocto Project is a toolkit for building custom Linux systems for embedded devices.

It helps create or modify layers, package recipes, system images, SDKs, board support, machine and distribution settings, kernels, and development-tool workflows.

It reduces version-specific mistakes by checking the project's release, existing metadata, and official documentation before changes.

yocto-project — Skill for Codex by prashantdivate

Install

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.

Any agent

npx skills add prashantdivate/awesome-yocto-ai-agent-skills --skill yocto-project

Clone the repo

git clone --depth 1 https://github.com/prashantdivate/awesome-yocto-ai-agent-skills

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-project/github.svg)](https://agentmods.dev/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-project)

Your own site

<a href="https://agentmods.dev/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-project"><img src="https://agentmods.dev/badge/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-project/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-project"><img src="https://agentmods.dev/badge/skills/prashantdivate/awesome-yocto-ai-agent-skills/yocto-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 809 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00117	$0.00809
Opus 5.5	$0.00047	$0.00324
Sonnet 5.5	$0.00023	$0.00162
Haiku 4.5	$0.00012	$0.00081

Measured 2mo ago against content hash fd58cccbca63, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

yocto-project 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/yocto_doc_router.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

yocto-project/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Yocto Project

Core Workflow

Identify the target release before giving commands or editing metadata. Inspect branch names, conf/layer.conf, LAYERSERIES_COMPAT, bblayers.conf, README, kas*.yml, poky/meta/conf/distro/include/yocto-uninative.inc, or release tags.
Prefer the workspace's own metadata over generic examples. Search existing layers for the same pattern before inventing a new recipe, image feature, class, override, or machine setting.
Check official docs for version-sensitive behavior. Use yocto_doc_router.py with a topic name for a quick URL map, then open the relevant docs.
Make the smallest layer-local change that fits Yocto conventions. Avoid editing poky/ or upstream layers unless the user explicitly asks for an upstream patch.
Validate with BitBake-native tools whenever available: bitbake-layers, bitbake -e, bitbake -c listtasks, bitbake -c cleansstate, devtool, oe-pkgdata-util, or the existing project build wrapper.

Source Priority

Use official sources first:

Local workspace metadata and build configuration.
Yocto Project docs: https://docs.yoctoproject.org/
BitBake manual: https://docs.yoctoproject.org/bitbake/
Yocto source: https://git.yoctoproject.org/
OpenEmbedded source: https://git.openembedded.org/
OpenEmbedded Layer Index: https://layers.openembedded.org/

If the user asks for "latest", "current", "supported", "LTS", package versions, release notes, migration rules, or security status, verify online before answering.

Task Routing

For recipe syntax, tasks, overrides, fetchers, signatures, or .bbappend mechanics, use $bitbake-metadata as the primary skill and return here for Yocto workflow context.
For layers, images, SDKs, BSPs, distro/machine policy, build setup, package selection, or migration planning, stay in this skill.
For kernel recipe and device-tree work, inspect existing machine and kernel metadata first, then read the kernel development sections from the official docs.

Read the full file on GitHub · 49 lines

Files

What ships with it

4 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.

Changes

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 · 49 lines · 117 tokens per session scan A fd58cccbca63

Subscribe to this mod's changes

yocto-project is a skill published in the GitHub repository prashantdivate/awesome-yocto-ai-agent-skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 117 tokens to every session and 809 once invoked, about $0.0005 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 2026-08-31.

DevOps and cloud Hardware and IoT agent-skills ai-agents ai-coding-assistant bitbake bsp build-system

yocto-project next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
yocto-projectprashantdivate/awesome-yocto-ai-agent-skills	Skill	4	4mo ago	MIT	A	117	Codex
eidezhinkgit/embeddedskills	Skill	785	18d ago	MIT	A	151	Claude Code
workflowzhinkgit/embeddedskills	Skill	785	18d ago	MIT	A	88	Claude Code
lov-migrate-camera-medialovstudio/skills	Skill	72	3d ago	MIT	A	86	Claude Code
robot-perceptionarpitg1304/robotics-agent-skills	Skill	393	2mo ago	Apache-2.0	A	181	Claude Code, Codex
robotics-software-principlesarpitg1304/robotics-agent-skills	Skill	393	2mo ago	Apache-2.0	A	140	Claude Code, Codex
robotics-design-patternsarpitg1304/robotics-agent-skills	Skill	393	2mo ago	Apache-2.0	A	120	Claude Code, Codex