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.

harbor AGENTS.md — Instructions file by av

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/av/harbor/agents-md

Clone the repo

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

Made for: Codex, OpenCode.

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. 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.

Model	Per session	Once invoked
Fable 5	$0.01997	$0.01997
Opus 5	$0.00999	$0.00999
Sonnet 5	$0.00399	$0.00399
Haiku 4.5	$0.00200	$0.00200

Measured 2d ago against content hash 613e9c702a42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

2d 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 (3,198 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,997 tokens to every session, about $0.0100 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 2026-08-30.

Data and AI DevOps and cloud LLM ai cli docker docker-compose tools

harbor AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Harbor Project

Key Locations

CLI Reference

What this file has done since we first saw it

Other instructions, from other repositories

branchbox CLAUDE.md

branchbox AGENTS.md

docker-mcp AGENTS.md

FamilyNido CLAUDE.md

wordpress-nginx-docker-compose CLAUDE.md

onramp copilot-instructions.md