What is mullion-ts AGENTS.md?

Repository instructions for Mullion, a TypeScript library for managing the information given to language models. It is organised as a pnpm workspaces and Turborepo monorepo, meaning one repository contains several related packages and applications.

Developing the core library, ESLint plugin, and AI SDK; running demos and integration tests; formatting, linting, building, and managing package versions.

It shows where the packages, demos, tests, documentation, shared settings, and task lists live, and identifies the commands used to build and check changes.

How mullionlabs/mullion-ts configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to mullionlabs/mullion-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mullionlabs/mullion-ts/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/mullionlabs/mullion-ts

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mullionlabs/mullion-ts/agents-md/github.svg)](https://agentmods.dev/instructions/mullionlabs/mullion-ts/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/mullionlabs/mullion-ts/agents-md"><img src="https://agentmods.dev/badge/instructions/mullionlabs/mullion-ts/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mullionlabs/mullion-ts/agents-md"><img src="https://agentmods.dev/badge/instructions/mullionlabs/mullion-ts/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 898 This file is loaded in full into every session.

When invoked 898 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00898	$0.00898
Opus 5.5	$0.00359	$0.00359
Sonnet 5.5	$0.00180	$0.00180
Haiku 4.5	$0.00090	$0.00090

Measured 2mo ago against content hash a9f78014037c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mullion-ts 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.

AGENTS.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Overview

Mullion is a TypeScript library for type-safe LLM context management. This is a pnpm workspaces + Turborepo monorepo using Changesets for versioning, tsup for builds, Vitest for tests, ESLint 9 (flat config) + TypeScript ESLint v8 for linting, and Prettier for formatting. Husky + lint-staged enforce pre-commit checks.

Project Structure & Module Organization

Core packages live under packages/:

packages/core for @mullion/core
packages/eslint-plugin for @mullion/eslint-plugin
packages/ai-sdk for @mullion/ai-sdk

Apps and examples:

apps/ for demo apps
tests/integration/ for real-provider integration tests
examples/ for minimal usage examples
docs/ for guides, reference, design docs, and contributing notes

Shared configs sit at the repo root (tsconfig.base.json, turbo.json, eslint.config.mjs, commitlint.config.mjs, pnpm-workspace.yaml). Root README.md is intentionally marketing + orientation.
This docs/ folder is the technical source of truth.

Task Management (TODO)

Follow the modular TODO workflow:

Read TODO/README.md
Read TODO/ACTIVE.md
Read the relevant file in TODO/tasks/
Update progress in the task file and TODO/ACTIVE.md as work completes

Build, Test, and Development Commands

Use pnpm from the repo root:

pnpm install installs workspace dependencies.
pnpm build builds all packages via Turborepo.
pnpm dev runs package dev tasks (where defined).
pnpm test runs all tests; pnpm test:watch watches.
pnpm lint runs ESLint across packages.
pnpm typecheck runs TypeScript checks.
pnpm format / pnpm format:check run Prettier.
pnpm clean runs package clean tasks and removes root node_modules.
pnpm clean:node_modules removes all node_modules folders.

For a single package:

pnpm --filter @mullion/core build
pnpm --filter <package> test

Coding Style & Naming Conventions

TypeScript strict mode is expected. Prefer interface for object shapes and import type for type-only imports. Avoid any; use unknown and narrow types. Use kebab-case for filenames, PascalCase for types, camelCase for functions, and UPPER_SNAKE_CASE for constants. Formatting is enforced with Prettier; linting with ESLint and lint-staged via Husky.

Read the full file on GitHub · 76 lines

Changes

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 · 76 lines · 898 tokens per session scan A a9f78014037c

Subscribe to this mod's changes

mullion-ts AGENTS.md is an instructions file published in the GitHub repository mullionlabs/mullion-ts (20 stars, last pushed 3mo ago), licensed MIT. It adds 898 tokens to every session, about $0.0036 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.

Languages TypeScript

mullion-ts AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mullion-ts AGENTS.mdmullionlabs/mullion-ts	Instructions file	20	3mo ago	MIT	A	898	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mullion-ts: Instructions file for Codex