r3bl-open-core: Instructions file for Codex

AGENTS.md

r3bl-open-core AGENTS.md is an instructions file for Codex, OpenCode from r3bl-org/r3bl-open-core. It costs 8,514 tokens per session, scanned C, original, Apache-2.0.

Repository instructions that tell coding agents how to protect system files, preserve ownership, and run commands safely.

In plain words
What is it for?
Use them when an agent edits r3bl-open-core, especially for file operations, permissions, ownership, and command execution.
Why use it?
They reduce the risk of an agent damaging operating-system files or changing protected settings while working on the project.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions subagents; positional $N argument; mentions Claude Code.

This is r3bl-org/r3bl-open-core's own configuration. It tells Codex and OpenCode how to work on r3bl-open-core itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything r3bl-open-core configures →

Reuse

Borrowing it

Nothing to install: this file belongs to r3bl-org/r3bl-open-core. 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/r3bl-org/r3bl-open-core/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/r3bl-org/r3bl-open-core

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.

agentmods badge for r3bl-open-core AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/r3bl-org/r3bl-open-core/agents-md/github.svg)](https://agentmods.dev/instructions/r3bl-org/r3bl-open-core/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/r3bl-org/r3bl-open-core/agents-md"><img src="https://agentmods.dev/badge/instructions/r3bl-org/r3bl-open-core/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.

agentmods 80×15 button for r3bl-open-core AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/r3bl-org/r3bl-open-core/agents-md"><img src="https://agentmods.dev/badge/instructions/r3bl-org/r3bl-open-core/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,514 This file is loaded in full into every session.
When invoked 8,514 The same file — it is already loaded in full.
Security scan C 3 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08514 $0.08514
Opus 5 $0.04257 $0.04257
Sonnet 5 $0.01703 $0.01703
Haiku 4.5 $0.00851 $0.00851

Measured 3d ago against content hash d37c98b0ce32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

r3bl-open-core AGENTS.md scanned grade C with 3 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`sudo chown/chmod/rm` is forbidden.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reaches for credential filesmediumPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

# Option B: Use the local store (if ~/.git-credentials is set up)

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Recursive operations (`chown -R`, `chmod -R`, `rm -rf`) are STRICTLY PROHIBITED on the

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

AGENTS.md · 709 lines

How it starts

The opening of the file, as written. The whole thing — 709 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions for r3bl-open-core

AI Agent Security & System Integrity Mandates

To prevent catastrophic system failures, all AI agents (Gemini, Claude, etc.) MUST adhere to these strict guardrails. These mandates take absolute precedence over any "YOLO" mode or perceived "fixes."

1. Critical Directory Protection

Recursive operations (chown -R, chmod -R, rm -rf) are STRICTLY PROHIBITED on the following top-level system directories and their contents:

  • / (Root)
  • /usr (System binaries and libraries)
  • /etc (System configuration)
  • /bin, /sbin, /lib, /lib64 (Essential system paths)
  • /boot (Bootloader and kernels)
  • /var (Variable data, including system logs and databases)

2. Ownership & Integrity

  • Root Ownership: System directories and binaries MUST remain owned by root. The agent must NEVER suggest or execute a change of ownership for system-managed paths to a non-root user.
  • Privilege Escalation: Do not modify the setuid or setgid bits of any system binary (e.g., sudo, pkexec, mount) unless specifically instructed by the user to fix a verified corruption.

3. Execution Safety

  • Explicit Paths Only: All sudo commands involving recursive changes or deletions MUST use absolute paths. The use of wildcards (*) or relative paths (.) with sudo chown/chmod/rm is forbidden.
  • Verification First: Before suggesting a permissions fix, the agent must first verify the current state using ls -ld or stat.
  • Destructive Warning: Any command that modifies system-wide permissions or ownership must be explicitly flagged to the user with a explanation of the risks, even in YOLO mode.

Ask for clarification immediately on important choices or ambiguities. Take your time with changes: slow, steady, and careful work beats fast and careless.

Standard Workflow (Alignment -> Plan -> Execute)

To ensure safety and alignment, always start by clarifying the scope of work. Ask the user: "Are we starting:

Read the full file on GitHub · 709 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. 3d ago Changed · +27 lines · +434 tokens per session d37c98b0ce32
  2. 9d ago First seen · 682 lines · 8,080 tokens per session scan C e7fc81dbd4d3

Subscribe to this mod's changes

r3bl-open-core AGENTS.md is an instructions file published in the GitHub repository r3bl-org/r3bl-open-core (483 stars, last pushed 3d ago), licensed Apache-2.0. It adds 8,514 tokens to every session, about $0.0426 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reaches for credential files, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens