snosi AGENTS.md

snosi AGENTS.md is an instructions file for Codex, OpenCode from frostyard/snosi. It costs 23,390 tokens per session, scanned D, original, MIT.

A repository guide for snosi, a system that builds unchangeable Debian-based operating-system images and add-on layers. It documents the project layout, configuration, outputs, and build commands.

In plain words
What is it for?
Use it when working on snosi's desktop or server images, system add-ons, build setup, or deployment-related code.
Why use it?
It gives a coding agent the project context needed to build or change the right image and understand how local builds match automated builds.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/frostyard/snosi/agents-md
Clone the repo
git clone --depth 1 https://github.com/frostyard/snosi

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.

agentmods badge for snosi AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/frostyard/snosi/agents-md.svg)](https://agentmods.dev/instructions/frostyard/snosi/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/frostyard/snosi/agents-md"><img src="https://agentmods.dev/badge/instructions/frostyard/snosi/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 23,390 This file is loaded in full into every session.
When invoked 23,390 The same file — it is already loaded in full.
Security scan D 3 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.23390 $0.23390
Opus 5 $0.11695 $0.11695
Sonnet 5 $0.04678 $0.04678
Haiku 4.5 $0.02339 $0.02339

Measured yesterday against content hash 8ad02c340258, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

snosi AGENTS.md scanned grade D with 3 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 yesterday.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Requires: just, git, python3, root/sudo access. mkosi itself is auto-bootstrapped: the Justfile fetches systemd/mkosi into a repo-local, gitignored `.mkosi/` checkout at the exact commit pinned by the `systemd/mkosi@<sha

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

1. Captured to `/usr/share/factory/etc` during build (via `mkosi.finalize`) — capture ONLY the specific paths the sysext's tmpfiles rules reference, never all of `/etc` (the buildroot `/etc` is the merged base view; a fu

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Three stager hardening rules, all root-caused live in the first QEMU run of `test/native-ab-updateux-test.sh`:** (1) capture `check-new` STDOUT ONLY — its progress lines ("Discovering installed instances…") are stderr
AGENTS.md · 729 lines

How it starts

The opening of the file, as written. The whole thing — 729 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

snosi is a bootable container image build system using mkosi to produce Debian Trixie-based immutable OS images and system extensions (sysexts). Images are deployed via bootc/systemd-boot with atomic updates.

Outputs: 2 OCI desktop images (snow, snowfield), 1 OCI server image (cayo), and 27 sysext overlay images (1password, 1password-cli, azurevpn, bitwarden, chatgpt, claude-desktop, code-server, coder, debdev, dev, docker, edge, github-copilot, incus, k3s, lemonade, localsend, moonlight, nix, obsidian, paseo, pilothouse, podman, sunshine, tailscale, voxtype, vscode).

Build Commands

Requires: just, git, python3, root/sudo access. mkosi itself is auto-bootstrapped: the Justfile fetches systemd/mkosi into a repo-local, gitignored .mkosi/ checkout at the exact commit pinned by the systemd/mkosi@<sha> action in .github/workflows/build.yml (read at runtime — no drift between local and CI), and runs .mkosi/bin/mkosi from there. Delete .mkosi/ to discard it; override with just mkosi=/usr/bin/mkosi <target> to use a system install.

just                    # List targets
just sysexts            # Build base + all 27 sysexts
just snow               # Build snow desktop image
just snowfield          # Build snowfield (Surface kernel)
just cayo               # Build cayo server image
just clean              # Remove build artifacts
just test-install       # Run bootc install test
just run-qemu           # Run image in QEMU

All just targets run mkosi clean first (clean build every time).

Optional bcvk testing: bcvk is a local convenience for exercising the OCI bootc images and does not replace just test-install or its CI workflow. OCI profiles include bubblewrap because bcvk runs bwrap from the target image; virtiofsd already ships in base. bcvk 0.18 requires an explicit host-side podman pull before bcvk libvirt run (--pull=never). OCI bootc profiles use SecureBoot=no and do not build or enroll the native A/B MOK signing chain, so they do not currently boot under bcvk's enrolled-key Secure Boot firmware. Use --firmware uefi-insecure only for bcvk install-mechanics testing. Do not represent this as Secure Boot validation or change the established bootc installation/testing path because of it.

Read the full file on GitHub · 729 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.

  1. yesterday Changed · +51 lines · +1,276 tokens per session 8ad02c340258
  2. 5d ago First seen · 678 lines · 22,114 tokens per session scan D 45af7683cf23

Subscribe to this mod's changes

snosi AGENTS.md is an instructions file published in the GitHub repository frostyard/snosi (24 stars, last pushed yesterday), licensed MIT. It adds 23,390 tokens to every session, about $0.1169 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,719 tokens