What is harbor AGENTS.md?

Project guidance for Harbor, a Docker-based toolkit for running and managing large-language-model services through a command-line tool and desktop app.

Use it to run containers, manage AI services, change service configurations, write CLI scripts, or work on the Tauri desktop application.

It distinguishes this project from Harbor, the unrelated container registry, and maps its services, configuration, scripts, tests, and command reference.

How av/harbor configures Codex and OpenCode

About the project

av/harbor is a command-line tool and companion app that uses Docker Compose to start a connected local stack of language-model backends, user interfaces, and supporting AI services. People use it to run services such as Ollama, llama.cpp, vLLM, Open WebUI, search, voice, and image-generation tools without configuring their connections manually, while the catalogue provides agent workflows for operating Harbor.

av/harbor · 3,263 stars · on GitHub · discord.gg

Reuse

Borrowing it

Nothing to install: this file belongs to av/harbor. 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/av/harbor/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/av/harbor

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/av/harbor/agents-md/github.svg)](https://agentmods.dev/instructions/av/harbor/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/av/harbor/agents-md"><img src="https://agentmods.dev/badge/instructions/av/harbor/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/av/harbor/agents-md"><img src="https://agentmods.dev/badge/instructions/av/harbor/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,997 This file is loaded in full into every session.

When invoked 1,997 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.

Model	Per session	Once invoked
Fable 5.1	$0.01997	$0.01997
Opus 5.5	$0.00799	$0.00799
Sonnet 5.5	$0.00399	$0.00399
Haiku 4.5	$0.00200	$0.00200

Measured 2mo ago against content hash 613e9c702a42, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

harbor 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 2mo 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 · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harbor Project

Harbor is a containerized LLM toolkit — a large Docker Compose project with a CLI and a Tauri app for managing AI services. Not to be confused with Harbor container registry which is a completely different unrelated project. This repository, Harbor, is the LLM toolkit.

Key Locations

harbor.sh — main CLI (too large to read in full; search for specific functions)
services/ — all service directories and compose files (e.g., services/ollama/, services/compose.ollama.yml)
compose.yml — base compose file, always included
app/ — Tauri GUI app
docs/ — service and user documentation
routines/ — CLI internals rewritten in Deno
.scripts/ — dev scripts in Deno/Bash, run via harbor dev <script>
tests/ — container-based test runner (suites, rows, orchestrator); see tests/README.md
.scripts/lint/ — bash-compat lint rules (HARBORxxx), fixtures, and 4-pass orchestrator
profiles/default.env — default config distributed to users
skills/harbor/SKILL.md — agent-facing CLI skill (shipped via npm for Claude Code discovery)

CLI Reference

harbor ps                        # list running containers
harbor ls                        # list all available services
harbor up <service>              # start service(s)
harbor down                      # stop and remove containers
harbor logs <service>            # ⚠️ TAILS BY DEFAULT (HANGS AGENT). Use docker logs <container> instead
harbor build <service>
harbor shell <service>           # interactive shell in container
harbor exec <service> <cmd>
harbor eject                     # output standalone Compose config for current selection
$(harbor cmd <service>)          # raw docker compose command for a service

harbor config get <KEY>
harbor config set <KEY> <VALUE>
harbor config update             # propagate profiles/default.env → .env
harbor config search <query>     # search config keys and values

Never edit .env directly — always use harbor config get/set.

Read the full file on GitHub · 167 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.

2mo ago First seen · 167 lines · 1,997 tokens per session scan A 613e9c702a42

Subscribe to this mod's changes

harbor AGENTS.md is an instructions file published in the GitHub repository av/harbor (3,263 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,997 tokens to every session, about $0.0080 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.

Containers DevOps and cloud LLM ai cli docker docker-compose tools

harbor AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
harbor AGENTS.mdav/harbor	Instructions file	3.3k	6d ago	Apache-2.0	A	1,997	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

harbor: Instructions file for Codex