OGAM: Instructions file for Codex

AGENTS.md

OGAM AGENTS.md is an instructions file for Codex, OpenCode from off-grid-ai/OGAM. It costs 31 tokens per session, scanned A, original, MIT.

A pointer telling agents to read the repository's single rules.md file before working on the Off-grid AI project.

In plain words
What is it for?
Use it as the starting point for any change in the project, then follow the referenced repository rules.
Why use it?
It keeps the project's instructions in one authoritative place, including rules for architecture, testing, device checks, and pull requests.

Instructions file for CodexOpenCode

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

This is off-grid-ai/OGAM's own configuration. It tells Codex and OpenCode how to work on OGAM 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 OGAM configures →

About the project

Off Grid AI is an offline AI application for phones and Macs that can chat, process speech, understand images, generate images, and run language models on the device. It is intended for people who want local AI use without an account, API key, or data leaving their device.

off-grid-ai/OGAM · 3,333 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to off-grid-ai/OGAM. 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/off-grid-ai/OGAM/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/off-grid-ai/OGAM

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 OGAM AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/off-grid-ai/ogam/agents-md/github.svg)](https://agentmods.dev/instructions/off-grid-ai/ogam/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/off-grid-ai/ogam/agents-md"><img src="https://agentmods.dev/badge/instructions/off-grid-ai/ogam/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 OGAM AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/off-grid-ai/ogam/agents-md"><img src="https://agentmods.dev/badge/instructions/off-grid-ai/ogam/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 This file is loaded in full into every session.
When invoked 31 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 $0.00031 $0.00031
Opus 5.5 $0.00012 $0.00012
Sonnet 5.5 $0.00006 $0.00006
Haiku 4.5 $0.00003 $0.00003

Measured 1mo ago against content hash 090a9689d0d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

OGAM 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 1mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 4 lines

What it actually says

Mobile instructions

Read rules.md and the workspace engineering contract.

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. 1mo ago Changed · -7 lines · -101 tokens per session 090a9689d0d4
  2. 2mo ago First seen · 11 lines · 132 tokens per session scan A c0aeabfbbc73

Subscribe to this mod's changes

OGAM AGENTS.md is an instructions file published in the GitHub repository off-grid-ai/OGAM (3,333 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session, about $0.0001 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 2026-08-30.

Related

OGAM AGENTS.md compared with instructions from other repositories

OGAM AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
OGAM AGENTS.mdoff-grid-ai/OGAMInstructions file3.3kyesterdayMITA31Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode