Borrowing it
Nothing to install: this file belongs to newtype-ai/nit. 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/newtype-ai/nit/main/AGENTS.mdgit clone --depth 1 https://github.com/newtype-ai/nitWrote 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/newtype-ai/nit/agents-md)<a href="https://agentmods.dev/instructions/newtype-ai/nit/agents-md"><img src="https://agentmods.dev/badge/instructions/newtype-ai/nit/agents-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.
<a href="https://agentmods.dev/instructions/newtype-ai/nit/agents-md"><img src="https://agentmods.dev/badge/instructions/newtype-ai/nit/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00650 | $0.00650 |
| Opus 5.5 | $0.00260 | $0.00260 |
| Sonnet 5.5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
nit AGENTS.md scanned grade A with 0 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 2mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/ contains the TypeScript source for the nit library and CLI. src/index.ts is the public API entry point, src/cli.ts wires command-line behavior, and focused modules such as identity.ts, objects.ts, remote.ts, tx.ts, and wallet.ts hold protocol logic. dist/ is generated build output and should not be edited. tests/local-regression.test.mjs contains local Node tests; tests/nit-e2e.sh exercises the live service. docs/ and root Markdown files hold product, protocol, and launch notes.
Build, Test, and Development Commands
Use Node.js 18+.
npm install # install dependencies
npm run build # build ESM output and .d.ts files with tsup
npm test # build and run local node:test regression tests
npm run release:check
bash tests/nit-e2e.sh
npm run release:check runs local tests, the live e2e script, and npm pack --dry-run. The e2e test builds first, creates a temporary nit repository, and exercises init, branch, push, verify, and replay flows against https://api.newtype-ai.org, so run it only when network access and live-server side effects are acceptable.
Coding Style & Naming Conventions
This project uses strict TypeScript, ESM imports, and Node built-ins where possible. Match the existing style: two-space indentation, semicolons, single quotes, named exports, and .js extensions in relative TypeScript imports that compile to ESM. Keep modules small and protocol-focused. Prefer descriptive function names such as loadAgentId, signMessage, or findNitDir; use kebab-case for CLI command names and file names.
Testing Guidelines
Use Node's built-in node:test runner for local tests. For changes to core behavior, add focused tests to tests/local-regression.test.mjs or extend tests/nit-e2e.sh with clear PASS/FAIL checks. Always run npm test before submitting. Run the e2e script for changes touching CLI commands, remote behavior, signatures, branch state, or serialization.
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.
- 2mo ago First seen · 38 lines · 650 tokens per session scan A 7b2c78fe509f
nit AGENTS.md is an instructions file published in the GitHub repository newtype-ai/nit (113 stars, last pushed 5mo ago), licensed MIT. It adds 650 tokens to every session, about $0.0026 per session on Opus 5.5. A static security scan graded it A with 0 findings. 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.