code-oz AGENTS.md

A pointer instruction file for Code-Oz that directs coding agents to read CLAUDE.md and the design roadmap. It keeps the main project guidance in one canonical location.

In plain words
What is it for?
Use it at the start of a Code-Oz task to find the project's orientation, fixed architecture rules, working conventions, and milestone plan.
Why use it?
It reduces the chance that agents follow outdated or duplicated instructions.

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/omerakben/code-oz/agents-md
Clone the repo
git clone --depth 1 https://github.com/omerakben/code-oz

Made for: Codex, OpenCode.

Per session 112 This file is loaded in full into every session.
When invoked 112 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 $0.00112 $0.00112
Opus 5 $0.00056 $0.00056
Sonnet 5 $0.00022 $0.00022
Haiku 4.5 $0.00011 $0.00011

Measured yesterday against content hash 4549bcdf9b6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-oz 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 · 8 lines

What it actually says

AGENTS.md — code-oz

This file is a pointer for Codex sessions. The canonical project orientation, non-negotiable rules, architecture locks, working conventions, and milestone cadence live in CLAUDE.md.

Read CLAUDE.md first. Then docs/design/ROADMAP.md for the milestone plan.

The two files are kept in sync by treating CLAUDE.md as the single source of truth: changes land there, and this file remains a one-line pointer to avoid drift.

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 · 8 lines · 112 tokens per session scan A 4549bcdf9b6f

Subscribe to this mod's changes

code-oz AGENTS.md is an instructions file published in the GitHub repository omerakben/code-oz (2 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session, about $0.0006 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