What is RMF-Block AGENTS.md?

A repository-specific instruction guide for coding agents working on the RMF-Block project. It covers the project structure, development workflow, and coding principles.

It helps agents understand the RMF-Block codebase, follow its software design workflow, and write code according to the project's stated principles.

It gives an agent the project context and working rules it needs before changing code. This helps avoid applying assumptions from unrelated Next.js projects.

How CBNU-TeamH/RMF-Block configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to CBNU-TeamH/RMF-Block. 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/CBNU-TeamH/RMF-Block/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/CBNU-TeamH/RMF-Block

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/cbnu-teamh/rmf-block/agents-md/github.svg)](https://agentmods.dev/instructions/cbnu-teamh/rmf-block/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/cbnu-teamh/rmf-block/agents-md"><img src="https://agentmods.dev/badge/instructions/cbnu-teamh/rmf-block/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/cbnu-teamh/rmf-block/agents-md"><img src="https://agentmods.dev/badge/instructions/cbnu-teamh/rmf-block/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,767 This file is loaded in full into every session.

When invoked 2,767 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	$0.02767	$0.02767
Opus 5.5	$0.01107	$0.01107
Sonnet 5.5	$0.00553	$0.00553
Haiku 4.5	$0.00277	$0.00277

Measured 23d ago against content hash e2fb8765faca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

RMF-Block 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 23d 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 · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

The single entry point for this repository. Every AI agent and teammate reads this before starting work. Tool-neutral (Claude / Cursor / Copilot alike). CLAUDE.md only imports this file — a tool that edits "the project's memory file" by name will target CLAUDE.md and miss the content that actually lives here, so check that assumption before adopting one that writes to it.

0. This is NOT the Next.js you know

This version (16.2.12) has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ before writing any code. Heed deprecation notices.

1. Project overview

What: a LAN-based real-time document collaboration system. Full requirements: docs/SRS-en.md — the English copy agents read; docs/SRS-ko.md is the canonical text the team agrees on.
Who: CBNU Team H capstone project.
Current stage: this repository holds both the docs and the code — Next.js + TypeScript, single package, pnpm.
Stack: why Yorkie and not Yjs/Automerge, why Next's App Router and not a React SPA with its own backend, and the smaller choices around them — docs/adr/003-stack-choices.md.
Architecture: real-time sync runs on self-hosted Yorkie (CRDT), which also owns document persistence (on MongoDB — the app never connects to it) and version history; the app/WS server is one Next.js custom server (REST + WebSocket) keeping its own state as JSON under .data/. Sessions stay in memory, so restarting the container is the revoke path. See docs/design/architecture.md, docs/design/api.md, docs/adr/002-persistence-on-yorkie-mongo.md, docs/SRS-ko.md §2.3.2.

2. How we work (SDD workflow)

Read the full file on GitHub · 108 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.

23d ago Changed · +6 tokens per session e2fb8765faca
25d ago Changed · +1 lines · +49 tokens per session a262e70e745f
27d ago Changed · +1 lines · +68 tokens per session 12a52e1cf21e
29d ago Changed · -11 lines · -34 tokens per session e49a3af04e73
1mo ago Changed · +3 lines · +111 tokens per session 15e9c6e9858e
1mo ago Changed · -3 lines · -167 tokens per session e860520a105a
1mo ago Changed · -1 lines · -31 tokens per session 8841b44edca9
1mo ago Changed · +28 tokens per session df341b25bc66
1mo ago Changed · +57 tokens per session 0e40e37f6348
1mo ago First seen · 118 lines · 2,680 tokens per session scan A 9059391d572b

Subscribe to this mod's changes

RMF-Block AGENTS.md is an instructions file published in the GitHub repository CBNU-TeamH/RMF-Block (3 stars, last pushed 9d ago), licensed MIT. It adds 2,767 tokens to every session, about $0.0111 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 2026-08-31.

RMF-Block AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
RMF-Block AGENTS.mdCBNU-TeamH/RMF-Block	Instructions file	3	9d ago	MIT	A	2,767	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

RMF-Block: Instructions file for Codex