agentic-ai-homelab: Instructions file for Codex

AGENTS.md

agentic-ai-homelab AGENTS.md is an instructions file for Codex, OpenCode from chipi/agentic-ai-homelab. It costs 790 tokens per session, scanned A, original, MIT.

Repository-wide instructions for an agentic AI homelab codebase. AGENTS.md is a shared convention that several coding agents can read, while folder-specific files add narrower rules.

In plain words
What is it for?
It covers repository conventions, environment-file handling, scoped instructions, and how broader operator rules fit with this repository's rules.
Why use it?
It keeps coding rules consistent across different agent tools and prevents secrets such as .env files from being committed. It also directs agents to the right rules for each folder.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is chipi/agentic-ai-homelab's own configuration. It tells Codex and OpenCode how to work on agentic-ai-homelab 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 agentic-ai-homelab configures →

Reuse

Borrowing it

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

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 agentic-ai-homelab AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chipi/agentic-ai-homelab/agents-md.svg)](https://agentmods.dev/instructions/chipi/agentic-ai-homelab/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/chipi/agentic-ai-homelab/agents-md"><img src="https://agentmods.dev/badge/instructions/chipi/agentic-ai-homelab/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 790 This file is loaded in full into every session.
When invoked 790 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 $0.00790 $0.00790
Opus 5 $0.00395 $0.00395
Sonnet 5 $0.00158 $0.00158
Haiku 4.5 $0.00079 $0.00079

Measured 6d ago against content hash 02ae4fc36261, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agentic-ai-homelab 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 6d 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — agentic-ai-homelab (repo-scoped)

Repo-scoped rules for any agent working in this codebase. AGENTS.md is a convention multiple harnesses follow — Claude Code picks this up via CLAUDE.md, Cursor and Codex read it natively, and the operator's chosen harness (opencode) does too. This file is harness- agnostic; nothing in this repo depends on which harness you run.

This file captures conventions that apply repo-wide. Folder-specific rules live in scoped AGENTS.md files (see the table below) — this root file points to them and never duplicates them. The operator's broader cross-repo rules (collab style, safety floor, comm defaults) layer underneath — when those exist as a separate file (e.g. ~/.config/<harness>/AGENTS.md), this file builds on top, never duplicates or contradicts.

Repo-wide conventions

  • .env belongs in .gitignore, never in git. Always. Reasserted here because this repo has many compose stacks and the temptation to commit "just the example values" comes up regularly. Compose stacks read a repo-root or stack-local .env depending on the stack (see infra/AGENTS.md).

Scoped AGENTS.md in this repo

Folder-specific rules live next to the code they govern. More-specific folder wins (e.g. infra/dgx/ over infra/ over root).

Path Scope
docs/AGENTS.md Docs workflow — mkdocs strict gate, doc hygiene, NEXT_STEPS punch list, history arcs
infra/AGENTS.md Infra stacks — run composes in place, symlink operator scripts
infra/dgx/AGENTS.md DGX-host work, GPU mode coordination
infra/vllm/AGENTS.md Local vLLM stacks — ports, dummy key, GPU sizing
provider-bakeoff/AGENTS.md provider-bakeoff sub-project
bugfix-fleet/AGENTS.md autonomous bug-fix fleet MVP (RFC-0002) — Pi vs opencode bake-off

Read the full file on GitHub · 59 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. 6d ago First seen · 59 lines · 790 tokens per session scan A 02ae4fc36261

Subscribe to this mod's changes

agentic-ai-homelab AGENTS.md is an instructions file published in the GitHub repository chipi/agentic-ai-homelab (2 stars, last pushed 3d ago), licensed MIT. It adds 790 tokens to every session, about $0.0040 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

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

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

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

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

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