Borrowing it
Nothing to install: this file belongs to n3wth/r3. 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/n3wth/r3/main/AGENTS.mdgit clone --depth 1 https://github.com/n3wth/r3Wrote 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/n3wth/r3/agents-md)<a href="https://agentmods.dev/instructions/n3wth/r3/agents-md"><img src="https://agentmods.dev/badge/instructions/n3wth/r3/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/n3wth/r3/agents-md"><img src="https://agentmods.dev/badge/instructions/n3wth/r3/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 | $0.01582 | $0.01582 |
| Opus 5 | $0.00791 | $0.00791 |
| Sonnet 5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
r3 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 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.
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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for r3 Project
Key Rules
- NO EMOJIS - Never use emojis in any context within this project
- Brand Name - Always use "r3" (lowercase)
- Current Year - Use 2025 in copyright notices
- Professional Tone - Maintain technical, clear communication
Project Structure
r3/
├── src/ # Core TypeScript source
│ ├── index.ts # Main entry point
│ ├── core/
│ │ └── memory-engine.ts # Central memory logic
│ ├── handlers/
│ │ └── tool-handlers.ts # MCP tool handler implementations
│ ├── lib/
│ │ ├── cache-manager.ts # Redis cache layer
│ │ ├── cache-manager-optimized.ts
│ │ ├── redis-manager.ts # Redis connection management
│ │ ├── vectra-memory.ts # Vectra vector store integration
│ │ ├── enhanced-vectra-memory.ts
│ │ ├── local-memory.ts # Local (non-Redis) memory fallback
│ │ ├── entity-extractor.ts # NLP entity extraction
│ │ ├── entity-extractor-spacy.ts
│ │ ├── spacy_bridge.py # Python/spaCy interop bridge
│ │ ├── pubsub-manager.ts # Redis pub/sub
│ │ └── errors.ts # Shared error types
│ ├── cli-ui/ # Interactive CLI UI components (Ink/React)
│ │ └── source/
│ │ ├── cli.tsx
│ │ ├── app.tsx
│ │ └── SimpleSpinner.tsx
│ ├── types/
│ │ ├── index.ts # Shared type definitions
│ │ ├── blessed.d.ts
│ │ └── terminal.d.ts
│ └── populate-demo-data.ts # Seed script for demo data
├── test/ # Test suite (requires Redis + MEM0_API_KEY)
│ ├── test-suite.js # Primary integration tests
│ ├── test-intelligence.js # Intelligence/recall tests
│ ├── test.js
│ └── run-tests.js
├── docs/ # Documentation
│ ├── CLI_USAGE.md
│ ├── CONTRIBUTING.md
│ ├── SECURITY.md
│ ├── TODO.md
│ └── validation-prompt.md
├── mcp-server/ # Standalone Python MCP server
│ ├── server.py
│ ├── requirements.txt
│ ├── Dockerfile
│ └── docker-compose.yml
├── r3call-cli/ # Ink-based CLI sub-package
│ └── source/
│ ├── cli.tsx
│ ├── app.tsx
│ ├── api.ts
│ └── SimpleSpinner.tsx
├── mac-menubar-app/ # macOS menu bar app (Swift)
│ └── main.swift
├── website/ # Docs site (Next.js, deployed to r3.n3wth.com)
│ ├── app/ # Next.js app router pages
│ ├── components/ # Shared React components
│ ├── content/docs/ # MDX documentation content
│ ├── lib/ # Utility modules
│ └── public/ # Static assets and fonts
├── assets/ # Brand assets (SVG logos)
├── data/ # Local runtime data (gitignored in prod)
│ ├── memories.db # SQLite memory store
│ └── vectra-index/ # Vectra vector index
├── .github/workflows/ # CI/CD workflows
│ ├── ci.yml # Lint and test on PR
│ ├── release.yml # Bump version and publish to npm
│ └── auto-release.yml
├── Dockerfile # Container image for the MCP server
├── index.d.ts # Public TypeScript declarations
├── package.json # Root package (npm publish target)
└── vercel.json # Vercel deployment config for website
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.
- 9d ago First seen · 175 lines · 1,582 tokens per session scan A eb9761bbd0f8
r3 AGENTS.md is an instructions file published in the GitHub repository n3wth/r3 (2 stars, last pushed 4d ago), licensed MIT. It adds 1,582 tokens to every session, about $0.0079 per session on Opus 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 2026-09-04.
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.
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 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).
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.
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.