What is meta-qcom AGENTS.md?

A build guide for meta-qcom, a Yocto/OpenEmbedded layer that adds Qualcomm hardware support to embedded Linux. It describes the required container checks, shared build caches, and routine quality tests.

Use it to prepare the build environment, run containerized builds, review patches, test the layer, and check it for compatibility with the Yocto build system.

It makes builds more reproducible and catches layer, patch, and hardware-integration problems before changes reach review.

How qualcomm-linux/meta-qcom configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to qualcomm-linux/meta-qcom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/qualcomm-linux/meta-qcom/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/qualcomm-linux/meta-qcom

Made for: Codex, OpenCode.

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/instructions/qualcomm-linux/meta-qcom/agents-md/github.svg)](https://agentmods.dev/instructions/qualcomm-linux/meta-qcom/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/qualcomm-linux/meta-qcom/agents-md"><img src="https://agentmods.dev/badge/instructions/qualcomm-linux/meta-qcom/agents-md/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/instructions/qualcomm-linux/meta-qcom/agents-md"><img src="https://agentmods.dev/badge/instructions/qualcomm-linux/meta-qcom/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,068 This file is loaded in full into every session.

When invoked 2,068 The same file — it is already loaded in full.

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	$0.02068	$0.02068
Opus 5.5	$0.00827	$0.00827
Sonnet 5.5	$0.00414	$0.00414
Haiku 4.5	$0.00207	$0.00207

Measured 1mo ago against content hash bd681748cf37, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meta-qcom AGENTS.md 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 1mo 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.

AGENTS.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide for meta-qcom

This file guides automation agents to run builds / checks the same way CI does:

use kas-container (isolated from host),
keep DL_DIR and SSTATE_DIR outside the repo so caches are shared,
run yocto-patchreview and oe-selftest routinely, and run yocto-check-layer before opening/updating a PR, via the CI helper scripts.

Project Overview

meta-qcom is an OpenEmbedded / Yocto Project hardware enablement layer for Qualcomm based platforms.

Agent skills

Reusable agent skills for the qualcomm-linux projects are maintained in qcom-linux-skills, in the SKILL.md format understood by Claude Code, Codex, Cursor and similar agents. Several of them cover the workflows described in this file, such as qcom-yocto-build-image (build images with kas-container), qcom-yocto-pre-pr-checks (the CI-parity checks from section 4), qcom-yocto-update-base-lock (refresh ci/base.lock.yml), and qcom-flash-qdl / qcom-boot-validate (flash and boot-test a board). Install them with the repository's install.sh and prefer an existing skill over re-deriving the workflow; improvements go back to that catalog.

1) Prerequisites

kas-container available on PATH, or set KAS_CONTAINER=/abs/path/to/kas-container (from kas-container).
Container runtime access (Docker/Podman backend used by kas-container).
Work directories outside the repository for build outputs and shared caches.

Container runtime smoke test

kas-container uses Docker when it is installed and falls back to Podman otherwise (set KAS_CONTAINER_ENGINE to override), so check the engine it will pick:

docker run --rm hello-world    # or, on a Podman-only host: podman run --rm hello-world

Notes:

Do not use sudo unless the host setup explicitly requires it.
Do not create or modify user groups as part of this workflow.

Read the full file on GitHub · 211 lines

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.

1mo ago Changed · +4 lines · +212 tokens per session bd681748cf37
1mo ago Changed · +54 lines · +639 tokens per session 52d739cde4de
2mo ago First seen · 153 lines · 1,217 tokens per session scan A 31bb53cd3b8c

Subscribe to this mod's changes

meta-qcom AGENTS.md is an instructions file published in the GitHub repository qualcomm-linux/meta-qcom (174 stars, last pushed yesterday), licensed MIT. It adds 2,068 tokens to every session, about $0.0083 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.

Containers DevOps and cloud Hardware and IoT

meta-qcom AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
meta-qcom AGENTS.mdqualcomm-linux/meta-qcom	Instructions file	174	yesterday	MIT	A	2,068	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

meta-qcom: Instructions file for Codex