ObsidianArc: Instructions file for Codex

AGENTS.md

ObsidianArc AGENTS.md is an instructions file for Codex, OpenCode from OnyxAxisOwO/ObsidianArc. It costs 8,030 tokens per session, scanned A, original, MIT.

Repository instructions for Obsidian Arc, an AI chat application, covering direct implementation and deployment practices. They distinguish Arc from a separate chat system and require identifying the correct hosted instance before deployment.

In plain words
What is it for?
They are for guiding code changes and deployments of Arc, including checking the instance, hosting setup, deployment record, and relevant services.
Why use it?
They prevent changes or deployments from being made to the wrong service, host, container, or data store.

Instructions file for CodexOpenCode

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

This is OnyxAxisOwO/ObsidianArc's own configuration. It tells Codex and OpenCode how to work on ObsidianArc 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 ObsidianArc configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/onyxaxis/Documents/GitHub/AxisAI.

Reuse

Borrowing it

Nothing to install: this file belongs to OnyxAxisOwO/ObsidianArc. 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/OnyxAxisOwO/ObsidianArc/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/OnyxAxisOwO/ObsidianArc

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 ObsidianArc AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/onyxaxisowo/obsidianarc/agents-md/github.svg)](https://agentmods.dev/instructions/onyxaxisowo/obsidianarc/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/onyxaxisowo/obsidianarc/agents-md"><img src="https://agentmods.dev/badge/instructions/onyxaxisowo/obsidianarc/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 ObsidianArc AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/onyxaxisowo/obsidianarc/agents-md"><img src="https://agentmods.dev/badge/instructions/onyxaxisowo/obsidianarc/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,030 This file is loaded in full into every session.
When invoked 8,030 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.08030 $0.08030
Opus 5.5 $0.03212 $0.03212
Sonnet 5.5 $0.01606 $0.01606
Haiku 4.5 $0.00803 $0.00803

Measured yesterday against content hash 25fc108487a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ObsidianArc 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 yesterday.

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 · 585 lines

How it starts

The opening of the file, as written. The whole thing — 585 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working on Obsidian Arc

Keep implementation and deployment direct

The owner prefers the smallest direct solution. Do not add speculative fallbacks, automatic backups, rollback frameworks, repeated validation, extra safety tests or defensive branches without a concrete observed need or an explicit request. Fix actual failures at their cause. Routine UI deployments reuse the checks already completed for that source and do not run unrelated core, plugin, race or safety suites. Do not expand the work into reliability infrastructure or a general cleanup.

Deployment identity

Chat and Arc are separate systems. Chat is the independent chat software; Arc is the AI chat application. Never treat their services, containers, ports, data, or deployment directories as interchangeable.

When the user asks to deploy Arc, first identify the instance and verify its current hosting against that instance repository's AGENTS.md, latest deployment record and live version. Do not assume every instance uses Docker. For a Docker deployment, use the Arc Compose project (/data/obsidian-arc on that host) and operate only the obsidian-arc-server container and its PostgreSQL companion. Build it on the local machine with make deploy DEPLOY_HOST=…, not on the server: the server's own docker compose up --build compiles the frontend and the binary there, which is minutes on that host and seconds here. make deploy ships a cross-compiled binary and replaces the server container alone.

Axis AI's production instance runs plugins that are not in this repository. They live in ../AxisAI (/Users/onyxaxis/Documents/GitHub/AxisAI), which lays them over this tree and calls this Makefile. Build and deploy from that instance repository using its current deployment procedure; its native deployment must not be replaced by this repository's Docker deploy target. For Docker instances, run make deploy DEPLOY_HOST=… there. Deploying from here ships the core alone, which switches those features off under the people using them; scripts/deploy.sh refuses when the running server carries a plugin the build does not, and DROP_PLUGINS=1 is for the day one is meant to go.

Read the full file on GitHub · 585 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. yesterday First seen · 585 lines · 8,030 tokens per session scan A 25fc108487a2

Subscribe to this mod's changes

ObsidianArc AGENTS.md is an instructions file published in the GitHub repository OnyxAxisOwO/ObsidianArc (691 stars, last pushed yesterday), licensed MIT. It adds 8,030 tokens to every session, about $0.0321 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 2026-11-07.

Related

ObsidianArc AGENTS.md compared with instructions from other repositories

ObsidianArc AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ObsidianArc AGENTS.mdOnyxAxisOwO/ObsidianArcInstructions file691yesterdayMITA8,030Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot