Borrowing it
Nothing to install: this file belongs to dryvist/nix-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dryvist/nix-ai/develop/CLAUDE.mdgit clone --depth 1 https://github.com/dryvist/nix-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/instructions/dryvist/nix-ai/claude-md)<a href="https://agentmods.dev/instructions/dryvist/nix-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/dryvist/nix-ai/claude-md.svg" alt="Measured on agentmods" 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 | $0.01985 | $0.01985 |
| Opus 5 | $0.00992 | $0.00992 |
| Sonnet 5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade B, and why
nix-ai CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo darwin-rebuild switch --flake "$HOME/git/nix-darwin/main" \ How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nix-ai - AI Agent Instructions
AI CLI ecosystem for Claude, Antigravity, Codex, Copilot, and MCP servers via Nix home-manager modules.
Critical Constraints
- Flakes-only: Never use
nix-envor imperative Nix commands - Module args injection: All flake inputs reach modules via
_module.args, not function parameters - Worktrees required: Run
/refresh-repothen create a worktree before any work - No direct main commits: Always use feature branches
Validation
Static (every change):
nix fmt # Fix formatting
nix flake check # Packages, formatters, devShells
# Regression suite (lib/checks/) — REQUIRED on macOS, see below
nix eval --raw .#checks.x86_64-linux \
--apply 'cs: builtins.concatStringsSep "\n" (map (c: c.outPath) (builtins.attrValues cs))' \
>/dev/null
A bare nix flake check on a Mac runs none of lib/checks/. checks is
scoped to x86_64-linux (flake.nix), so on aarch64-darwin it omits them, prints
green for packages and formatters, and says nothing about the regression suite.
A module argument launchd.nix required and default.nix never passed survived
a green bare check and failed only at darwin-rebuild.
--all-systems surfaces the assertions but then tries to build Linux
derivations on darwin, exiting non-zero for that unrelated reason — so it cannot
be routine. The nix eval form above forces every check's outPath: every
assertion runs at evaluation time, nothing builds. Verified both ways — passes
on a healthy tree, fails on a deliberately broken one.
Workaround; PR #1819 is the structural fix. It builds checks for every
supported system, so a plain nix flake check runs the darwin assertions.
When it lands, replace the nix eval form above — noting --all-systems on a
Linux-only runner then tries to realise the darwin markers and fails.
Assertions only fire when something forces them, so a check that reads a few
attributes of a large structure proves nothing about the rest. Where a check
covers a nested tree (the launchd agents, for one) it should deepSeq it.
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.
- 2d ago Changed · -5 tokens per session 5a3298aaa23c
- 8d ago First seen · 161 lines · 1,990 tokens per session scan B 3b5eb2acbcff
nix-ai CLAUDE.md is an instructions file published in the GitHub repository dryvist/nix-ai (11 stars, last pushed yesterday), licensed MIT. It adds 1,985 tokens to every session, about $0.0099 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 2026-08-30.
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.
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.
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).
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).
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.
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.