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/runtimed/intheloop/agents-mdgit clone --depth 1 https://github.com/runtimed/intheloopWrote 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/runtimed/intheloop/agents-md)<a href="https://agentmods.dev/instructions/runtimed/intheloop/agents-md"><img src="https://agentmods.dev/badge/instructions/runtimed/intheloop/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 | $0.02960 | $0.02960 |
| Opus 5 | $0.01480 | $0.01480 |
| Sonnet 5 | $0.00592 | $0.00592 |
| Haiku 4.5 | $0.00296 | $0.00296 |
Grade A, and why
intheloop 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 3d 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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Development Context
This document provides essential context for AI assistants working on the In the Loop project.
Current work state and development priorities. What works, what's experimental, what needs improvement. Last updated: October 2025.
Development Workflow: The user typically runs the integrated development server (pnpm dev) which handles both frontend and backend. For checking work, run type checks first, followed by lints, tests, and UI builds. The iframe outputs server runs separately (pnpm dev:iframe).
Project Overview
In the Loop is a real-time collaborative notebook system built on event-sourced architecture using LiveStore. It supports multiple runtime paradigms: external runtime agents via @runt JSR packages, and in-browser runtime agents for HTML and Python (Pyodide) that execute directly in the web client.
Current Status: A working system deployed at https://app.runt.run. Features real-time collaboration, persistent execution outputs, and integrated AI capabilities. The system is stable for experimentation and real usage while actively developed.
Architecture
Monorepo Structure
In the Loop is organized as a monorepo with four core packages and a unified web application:
- Packages (
packages/): Core libraries published to npm/JSR for runtime agent development - Web Client (
src/): React-based notebook interface with integrated backend - Backend (
backend/): Cloudflare Worker serving API and sync functionality - Runtime Agents: External (via @runt JSR packages) and in-browser (HTML/Python) execution
Core Packages
@runtimed/schema: LiveStore schema definitions with full type inference across packages@runtimed/agent-core: Runtime agent framework with artifact storage and observability@runtimed/ai-core: Multi-provider AI integration (OpenAI, Ollama, Groq) with tool calling@runtimed/pyodide-runtime: In-browser Python runtime with scientific computing stack
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.
- 3d ago First seen · 346 lines · 2,960 tokens per session scan A a2f8db6eb3f1
intheloop AGENTS.md is an instructions file published in the GitHub repository runtimed/intheloop (54 stars, last pushed 6mo ago), licensed BSD-3-Clause. It adds 2,960 tokens to every session, about $0.0148 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 2026-08-30.
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.