obsidian-second-brain: Instructions file for Codex

AGENTS.md

obsidian-second-brain AGENTS.md is an instructions file for Codex, OpenCode from khanxxy/obsidian-second-brain. It costs 1,829 tokens per session, scanned A, original, MIT.

A set of instructions for an AI agent working in an Obsidian second-brain vault, a folder of linked notes used to organize knowledge and projects. It defines how to onboard users, navigate the vault, and record context.

In plain words
What is it for?
It helps set up a first project, update the current-work list, and continue work across sessions. It is also used to manage handoffs, work logs, and personal notes.
Why use it?
It keeps important decisions and project context in the vault instead of leaving them only in a chat. It also gives the agent a fixed reading order and limits before editing files.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is khanxxy/obsidian-second-brain's own configuration. It tells Codex and OpenCode how to work on obsidian-second-brain 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 obsidian-second-brain configures →

Reuse

Borrowing it

Nothing to install: this file belongs to khanxxy/obsidian-second-brain. 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/khanxxy/obsidian-second-brain/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/khanxxy/obsidian-second-brain

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 obsidian-second-brain AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/khanxxy/obsidian-second-brain/agents-md.svg)](https://agentmods.dev/instructions/khanxxy/obsidian-second-brain/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/khanxxy/obsidian-second-brain/agents-md"><img src="https://agentmods.dev/badge/instructions/khanxxy/obsidian-second-brain/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,829 This file is loaded in full into every session.
When invoked 1,829 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 5.1 $0.01829 $0.01829
Opus 5 $0.00915 $0.00915
Sonnet 5 $0.00366 $0.00366
Haiku 4.5 $0.00183 $0.00183

Measured 2d ago against content hash f411fd4d42d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

obsidian-second-brain 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 · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Universal Agent Instructions

If you are an AI agent and this file was loaded automatically, follow it strictly.

Core idea: this vault is the source of truth. Do not let useful context stay only in chat.


New User Onboarding Protocol

If the user asks you to inspect, clone, set up, explain, or "check" this repo for the first time, do this before making edits:

  1. Read README.md, START-HERE.md, VAULT.md, and this AGENTS.md.
  2. Tell the user, in plain language, what this repo is:
    • an Obsidian Second Brain template
    • built for humans and AI agents
    • centered on NOW.md, project HANDOFF.md, and !1 Work Log/
    • designed to prevent context loss between sessions
  3. Tell the user the first practical steps:
    • open the folder as an Obsidian vault
    • fill in People/Me.md
    • create one project from Projects/.template/
    • add that project to NOW.md
    • start future sessions from NOW.md
  4. Ask for the user's first project name and one-sentence goal before creating or editing project files.
  5. After the user answers, help set up only that first project:
    • copy Projects/.template/ to Projects/<Project Name>/
    • fill Context.md from the user's answers
    • add the project to NOW.md
    • add an initial HANDOFF.md entry
    • create or update today's !1 Work Log/YYYY-MM-DD.md
  6. Offer skill installation only after the basic vault is understandable:
    • bash scripts/install-skill.sh

Do not silently fill the vault with fake content. Keep the first setup small and real.

Suggested first response:

This is an Obsidian Second Brain template for working with AI agents. The main workflow is: keep current state in NOW.md, keep project continuity in each project HANDOFF.md, and record sessions in !1 Work Log. I will first help you set up one real project. What should your first project be called, and what is its one-sentence goal?

Reading Order

At the start of a vault-related session, read in this order:

Read the full file on GitHub · 267 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. 2d ago Changed · +8 lines · +45 tokens per session f411fd4d42d1
  2. 6d ago First seen · 259 lines · 1,784 tokens per session scan A 201676804af9

Subscribe to this mod's changes

obsidian-second-brain AGENTS.md is an instructions file published in the GitHub repository khanxxy/obsidian-second-brain (2 stars, last pushed 5d ago), licensed MIT. It adds 1,829 tokens to every session, about $0.0091 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

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 · 5,182 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens