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.
npx agentmods add instructions/dryvist/nix-ai/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/dryvist/nix-ai/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/dryvist/nix-ai/copilot-instructions.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 | $0.00477 | $0.00477 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade B, and why
nix-ai copilot-instructions.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo darwin-rebuild switch --flake "$HOME/git/nix-darwin/main" \ What it actually says
GitHub Copilot Instructions — nix-ai
Repository Purpose
nix-ai is an AI CLI ecosystem (Claude Code, Antigravity, Codex, Copilot, MCP
servers, MLX inference) delivered as Nix home-manager modules. It exports
modules consumed by nix-darwin; this repo holds the module definitions, not a
deployed system.
Critical Constraints
- Flakes-only. Never generate
nix-envor other imperative Nix commands. - Module args injection. Flake inputs reach modules via
_module.args, not function parameters. - No direct main commits. Always work on a feature branch in a worktree.
Validation
Static checks run on every change:
nix flake check # formatting, statix, deadnix, regression tests
nix fmt # auto-fix formatting
Runtime changes (plugins, hooks, settings, activations, MCP servers) also need a real rebuild and a fresh Claude Code session — static checks validate Nix evaluation, not runtime behavior:
sudo darwin-rebuild switch --flake "$HOME/git/nix-darwin/main" \
--override-input nix-ai "$HOME/git/nix-ai/<worktree>"
Conventions
- Scripts longer than a few lines live in
scripts/*.sh, never inline in.nix. - Never hardcode model IDs, endpoints, or version strings — read them from
vars/ai-stack.nix(the central registry). - Never put secrets in Nix expressions or
env:blocks; they end up in the world-readable Nix store. Use Doppler or the macOS Keychain.
Key Files
modules/default.nix— module entry pointmodules/mcp/catalog.nix— shared MCP server catalogmodules/mlx/— local Apple Silicon inference (vllm-mlx LaunchAgent)vars/ai-stack.nix— model/endpoint/version registrylib/checks/— per-domain regression tests
See CLAUDE.md and docs/architecture/
for the full architecture.
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.
- 6d ago First seen · 53 lines · 477 tokens per session scan B 6c536952bcfa
nix-ai copilot-instructions.md is an instructions file published in the GitHub repository dryvist/nix-ai (11 stars, last pushed today), licensed MIT. It adds 477 tokens to every session, about $0.0024 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
gortex CLAUDE.md
Claude Code instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
DevoxxGenieIDEAPlugin AGENTS.md
AGENTS.md instructions for devoxx/DevoxxGenieIDEAPlugin, covering agents.md, project overview, build & development commands, building and testing.
opencodex AGENTS.md
AGENTS.md instructions for lidge-jun/opencodex, covering agents.md, what this project is, repository layout, optional subsystems stay off the core path and the devlog directory.
DevoxxGenieIDEAPlugin GEMINI.md
Gemini CLI instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven…
optio CLAUDE.md
Instructions for jonwiggins/optio, covering claude.md, what is optio?, architecture, pod-per-repo with worktrees and worktree lifecycle.
calva-backseat-driver AGENTS.md
Instructions for BetterThanTomorrow/calva-backseat-driver, covering calva backseat driver - ai agent guide, essential architecture, action/effect system ("ex"), runtime state structure and datascript connections.