core AGENTS.md

Repository instructions for AI coding agents, including which commands, tools, package versions, and workflow rules to follow.

In plain words
What is it for?
Use them when setting up the repository, running checks, working in Git worktrees, or choosing between Turbo, package scripts, and CI workflows.
Why use it?
They provide a local source of truth when documentation and automated checks differ, and help agents match the project’s development environment.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/module-federation/core/agents-md
Clone the repo
git clone --depth 1 https://github.com/module-federation/core

Made for: Codex, OpenCode.

Per session 2,034 This file is loaded in full into every session.
When invoked 2,034 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.02034 $0.02034
Opus 5 $0.01017 $0.01017
Sonnet 5 $0.00407 $0.00407
Haiku 4.5 $0.00203 $0.00203

Measured today against content hash ebf60337dd44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core 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 today.

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 · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

How AI coding agents should operate in this repository.

Important migration note (Turborepo): Nx orchestration has been removed from this repository. Prefer Turbo + package scripts for all build/test/lint workflows.

Scope and Precedence

  • Scope: this file applies to the full repository root.
  • Precedence: a deeper AGENTS.md overrides this file for its subtree.
  • This is an agent-operations document, not a contributor tutorial.

Source of Truth (in priority order)

  1. GitHub Actions workflows in .github/workflows/*.yml and .github/workflows/*.yaml
  2. Local CI parity runner in tools/scripts/ci-local.mjs
  3. Root scripts in package.json as wrappers/convenience entrypoints

If prose docs conflict with workflows (for example README.md or CONTRIBUTING.md), follow the workflow commands.

Environment Parity

  • Node.js: 24 (from .nvmrc and workflow setup)
  • pnpm: 10.28.0 (from package.json packageManager)
  • Package manager: pnpm only

Recommended setup for agents:

corepack enable
pnpm install --frozen-lockfile

Worktree safety rule:

  • In git worktree contexts, prefer running Turbo/package scripts directly (pnpm exec turbo ... / pnpm --filter ... run ...).

Worktree Mode (Required in Worktrees)

Use these rules whenever the checkout is a git worktree (typically git rev-parse --git-dir differs from git rev-parse --git-common-dir):

  1. Setup/install via:
corepack enable
pnpm install --frozen-lockfile
  1. Run workspace tasks via Turbo/package scripts:
pnpm exec turbo run <task>
pnpm --filter <package-name> run <script>

CI-Aligned Command Matrix

Use these as defaults unless the task explicitly requires something else.

Turbo Task Primer (How to Run Tasks)

  • List effective tasks:
pnpm exec turbo run build --dry=json
  • Run a task across the workspace:
pnpm exec turbo run <task>
  • Run a task for packages only:
pnpm exec turbo run <task> --filter=./packages/**

Read the full file on GitHub · 298 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.

  1. today First seen · 298 lines · 2,034 tokens per session scan A ebf60337dd44

Subscribe to this mod's changes

core AGENTS.md is an instructions file published in the GitHub repository module-federation/core (2,625 stars, last pushed yesterday), licensed MIT. It adds 2,034 tokens to every session, about $0.0102 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 2026-08-31.

Related

Other instructions, from other repositories