nixos-config: Instructions file for Claude Code

CLAUDE.md

nixos-config CLAUDE.md is an instructions file for Claude Code, Codex from FilipNowakowicz/nixos-config. It costs 3,140 tokens per session, scanned B, original, MIT.

Repository-specific instructions for maintaining a NixOS configuration based on a flake. NixOS is a Linux system configured with code, and a flake is a reproducible way to define that configuration and its development tools.

In plain words
What is it for?
Use them when editing, validating, deploying, or troubleshooting the FilipNowakowicz/nixos-config repository and its NixOS hosts.
Why use it?
They give an agent the repository's expected structure, deployment commands, validation checks, security guidance, and host-specific procedures before it changes configuration.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: PreToolUse hook event, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is FilipNowakowicz/nixos-config's own configuration. It tells Claude Code and Codex how to work on nixos-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nixos-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FilipNowakowicz/nixos-config. 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/FilipNowakowicz/nixos-config/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/FilipNowakowicz/nixos-config

Made for: Claude Code, 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.

agentmods badge for nixos-config CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/filipnowakowicz/nixos-config/claude-md/github.svg)](https://agentmods.dev/instructions/filipnowakowicz/nixos-config/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/filipnowakowicz/nixos-config/claude-md"><img src="https://agentmods.dev/badge/instructions/filipnowakowicz/nixos-config/claude-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.

agentmods 80×15 button for nixos-config CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/filipnowakowicz/nixos-config/claude-md"><img src="https://agentmods.dev/badge/instructions/filipnowakowicz/nixos-config/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,140 This file is loaded in full into every session.
When invoked 3,140 The same file — it is already loaded in full.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03140 $0.03140
Opus 5 $0.01570 $0.01570
Sonnet 5 $0.00628 $0.00628
Haiku 4.5 $0.00314 $0.00314

Measured 9d ago against content hash 19342fe5b319, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

nixos-config CLAUDE.md scanned grade B with 1 finding 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 9d 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.

Asks for rootmediumPrivilege escalation

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

Module topology, persistence model, and the agent-maintenance sudo allowlist
CLAUDE.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NixOS Flake Configuration

Personal NixOS flake for an endgame, reproducible setup. Prefer clean, idiomatic Nix over quick fixes. Suggest better approaches proactively. Explain why, not just what.

For repository overview and structure see README.md. For deeper context see docs/architecture.md, docs/operations.md, and docs/security.md. Host-local runbooks live under each host: hosts/main/CLAUDE.md, hosts/mac/CLAUDE.md, hosts/homeserver-gcp/CLAUDE.md, hosts/gcp-builder/CLAUDE.md, hosts/gcp-agent/CLAUDE.md.


Environment

  • Dev machine: NixOS (main).
  • Dev shell: nix develop — provides deploy-rs, nixos-anywhere, nixd, statix, deadnix, sops, ssh-to-age, vulnix, direnv, and the flake-managed pre-commit hook tooling.
  • Per-project shells: direnv enabled — use use flake in .envrc.
  • Git hooks: nix develop installs a commit-msg hook that strips Co-authored-by: trailers to keep history single-author.
  • Fresh /tmp/nix-* linked worktrees: a codex/* branch may already be checked out in another worktree (git worktree list), and .pre-commit-config.yaml is flake-generated so a worktree never entered via nix develop lacks it — commit there with --no-verify, but never use --no-verify to skip a real lint failure in the primary checkout.
  • Git is for version control only, not deployment.

Deploy Commands

  • main: nh os switch --hostname main . (alias: rebuild).
  • mac: deploy '.#mac' from main; local fallback nh os switch --hostname mac ..
  • homeserver-gcp: deploy '.#homeserver-gcp' for ongoing updates. scripts/deploy-gcp.sh is provisioning/reinstall only (Terraform apply + nixos-anywhere), not an ongoing-deploy alias. Note deploy-rs can appear silent/hung in non-interactive sessions; fall back to a manual closure deploy (nix build the system, nix copy the closure, then switch-to-configuration).
  • gcp-builder: deploy '.#gcp-builder' for ongoing updates (start the VM first; it is normally powered off). Provision once via hosts/gcp-builder/CLAUDE.md. It is an on-demand Nix remote builder, not a service host — main starts it transparently for heavy builds (see scripts/validate.sh) and it self-powers-off when idle.
  • gcp-agent: on-demand Claude Code agent host (issue-loop sessions, not a service host). Keeps narrow sudo, so there is no deploy-rs auto-activation — apply config changes by reprovisioning or manual activation. Provision once via hosts/gcp-agent/CLAUDE.md.
  • user@wsl: home-manager switch --flake .#user@wsl.

Read the full file on GitHub · 202 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. 9d ago First seen · 202 lines · 3,140 tokens per session scan B 19342fe5b319

Subscribe to this mod's changes

nixos-config CLAUDE.md is an instructions file published in the GitHub repository FilipNowakowicz/nixos-config (5 stars, last pushed 4d ago), licensed MIT. It adds 3,140 tokens to every session, about $0.0157 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 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 · 5,153 tokens

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

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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens