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/numtide/llm-agents.nix/agents-mdgit clone --depth 1 https://github.com/numtide/llm-agents.nixWrote 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/numtide/llm-agents.nix/agents-md)<a href="https://agentmods.dev/instructions/numtide/llm-agents.nix/agents-md"><img src="https://agentmods.dev/badge/instructions/numtide/llm-agents.nix/agents-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 | $0.02747 | $0.02747 |
| Opus 5 | $0.01373 | $0.01373 |
| Sonnet 5 | $0.00549 | $0.00549 |
| Haiku 4.5 | $0.00275 | $0.00275 |
Grade B, and why
llm-agents.nix AGENTS.md scanned grade B with 2 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 4d 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.
echo "experimental-features = nix-command flakes" | sudo tee -a /etc/nix/nix.conf Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
githubId = 123456; # Get from: curl -s https://api.github.com/users/username | jq -r '.id' How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
- Root:
flake.nix,flake.lock,devshell.nix,README.md. - Packages live under
packages/<tool>/withpackage.nix, optionalupdate.py, and lockfiles when needed. - Formatting config:
packages/formatter/treefmt.nix. - Utilities and docs:
scripts/,docs/,.github/.
Build, Test, and Development Commands
- Enter dev shell:
nix develop. - Build a package:
nix build --accept-flake-config .#<package>(e.g.,nix build .#claude-code). - Run without installing:
nix run .#<package> -- --help. - Repo checks (builds + lints):
nix flake check. - Format everything:
nix fmt. - Regenerate README package section:
./scripts/generate-package-docs.nu.
Coding Style & Naming Conventions
- Indentation: 2 spaces; avoid tabs.
- Nix: small, composable derivations; prefer
buildNpmPackage/rustPlatform.buildRustPackage/stdenv.mkDerivationas in existing packages. - File layout per package:
package.nix(definition),update.py(optional custom updater),nix-update-args(optional nix-update flags).package.nixis called from a scope that contains all in-repo packages and helpers (buildNpmPackage,wrapBuddy,formatelf,versionCheckHomeHook,bun2nixLib,platformSource,flake, ...), so declaring one of these names as a function argument is enough. - Tools via treefmt: nixfmt, deadnix, shfmt, shellcheck, mdformat, yamlfmt, taplo. Always run
nix fmtbefore committing.
Updating Packages
Prefer nix-update over custom update scripts. Most packages can be updated with:
nix run nixpkgs#nix-update -- --flake <package>
For this to work, package.nix must have version/hash attributes inline (not loaded from JSON):
buildGoModule rec {
pname = "example";
version = "1.0.0"; # nix-update finds and updates this
src = fetchFromGitHub {
owner = "owner";
repo = "repo";
rev = "v${version}";
hash = "sha256-..."; # nix-update updates this
};
subPackages = [ "." ]; # for go find the relevant packages containing the binary
vendorHash = "sha256-..."; # nix-update updates this too
}
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.
- 4d ago First seen · 265 lines · 2,747 tokens per session scan B e6567ab73555
llm-agents.nix AGENTS.md is an instructions file published in the GitHub repository numtide/llm-agents.nix (1,869 stars, last pushed 2d ago), licensed MIT. It adds 2,747 tokens to every session, about $0.0137 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.