onebrain AGENTS.md

Instructions for using OneBrain, a personal AI system built around a folder of Markdown notes, through its web interface and Codex CLI. It explains how Claude Code tool names correspond to Codex tools.

In plain words
What is it for?
Use it when working in a OneBrain vault, loading its project instructions, mapping tools, or dispatching additional agents.
Why use it?
It tells the agent which configuration and instruction files to read and how to translate commands between the two agent environments.

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/onebrain-ai/onebrain/agents-md
Clone the repo
git clone --depth 1 https://github.com/onebrain-ai/onebrain

Made for: Codex, OpenCode.

Per session 243 This file is loaded in full into every session.
When invoked 243 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 $0.00243 $0.00243
Opus 5 $0.00121 $0.00121
Sonnet 5 $0.00049 $0.00049
Haiku 4.5 $0.00024 $0.00024

Measured 2d ago against content hash 8e21b2aac3ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onebrain 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 2d 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 · 26 lines

What it actually says

OneBrain — Codex CLI

OneBrain is a personal AI OS built on a plain-Markdown vault — use its built-in web UI. INSTRUCTIONS.md is written using Claude Code tool names — the mapping below translates them to Codex CLI equivalents and explains how to dispatch sub-agents for skills that require parallel execution.

Load Order

  1. Tool mapping — translates Claude Code tool names to Codex CLI equivalents, and maps Agent dispatch to spawn_agent
  2. Shared agent instructions — vault structure, skills, session behavior, and personality

Tool Name Mapping

@.claude/plugins/onebrain/references/codex-tools.md

Read .claude/plugins/onebrain/references/codex-tools.md completely before using any OneBrain workflow. The @ line above is documentation, not a guarantee that the Codex host expands file imports.

Agent Instructions

@.claude/plugins/onebrain/INSTRUCTIONS.md

Then read .claude/plugins/onebrain/INSTRUCTIONS.md completely and apply its vault configuration and session rules. Do not rely on @file expansion alone.

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. 2d ago First seen · 26 lines · 243 tokens per session scan A 8e21b2aac3ac

Subscribe to this mod's changes

onebrain AGENTS.md is an instructions file published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 243 tokens to every session, about $0.0012 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.