What is deer AGENTS.md?

A project instruction file for deer.sh, a system administration platform where AI agents configure infrastructure in isolated virtual machines and a human approves the work before production.

It helps develop and run the command-line tool, API server, web dashboard, virtual-machine management, Python SDK, and example infrastructure agents.

It describes the system’s architecture, local startup commands, testing rules, and the roles of its API, web interface, and Python software library. This reduces setup mistakes and helps agents test each part correctly.

deer AGENTS.md — Instructions file by aspectrr

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/aspectrr/deer/agents-md

Clone the repo

git clone --depth 1 https://github.com/aspectrr/deer

Made for: Codex, OpenCode.

Per session 526 This file is loaded in full into every session.

When invoked 526 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	$0.00526	$0.00526
Opus 5	$0.00263	$0.00263
Sonnet 5	$0.00105	$0.00105
Haiku 4.5	$0.00053	$0.00053

Measured 2d ago against content hash 0f5aa76bcd98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deer 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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

deer.sh

The AI Sys-Admin for Enterprise.

What This Is

deer.sh lets AI agents do infrastructure work (provision servers, configure services, set up networking) in isolated VM sandboxes. The agent works autonomously. A human reviews and approves before production.

Architecture

Agent Task -> Sandbox VM (autonomous) -> Human Approval -> Production

deer/ - Go CLI & API server. Manages VMs via libvirt/KVM.
web/ - React frontend. Monitor sandboxes, approve actions.
sdk/ - Python SDK. Build agents that talk to the API.
examples/ - Working agent implementations.

Quick Start

docker-compose up --build

# API:      http://localhost:8080
# Web UI:   http://localhost:5173

Project Rules

Testing Required

Every code change needs tests. No exceptions.

Go: *_test.go files
Python: test/test_client.py
Web: Component tests as needed

Building

Use docker-compose:

docker-compose up deer            # API server
docker-compose up web              # Frontend
docker-compose up postgres         # Database

Project-Specific Docs

@deer/AGENTS.md - API server details
@sdk/AGENTS.md - Python SDK details
@web/AGENTS.md - Frontend details
@examples/agent-example/AGENTS.md - Agent example

Service Ports

Service	Port	Purpose
deer	8080	REST API for VM management
web	5173	React UI
PostgreSQL	5432	State persistence

Key Commands

# Go services
cd deer && make test && make check

# Python SDK
cd sdk/deer-py && pytest

# Frontend
cd web && bun run lint && bun run build

macOS Setup

brew install libvirt socket_vmnet cdrtools
brew services start libvirt
./scripts/setup-ssh-ca.sh --dir .ssh-ca
./scripts/reset-libvirt-macos.sh

Environment Variables

LIBVIRT_URI=qemu:///system          # libvirt connection
DATABASE_URL=postgresql://...        # postgres connection
API_HTTP_ADDR=:8080                  # API listen address

Read the full file on GitHub · 95 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 · 95 lines · 526 tokens per session scan A 0f5aa76bcd98

Subscribe to this mod's changes

deer AGENTS.md is an instructions file published in the GitHub repository aspectrr/deer (404 stars, last pushed 4mo ago), licensed MIT. It adds 526 tokens to every session, about $0.0026 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.

Analytics and metrics Backend and APIs Planning ai aiagent elk elk-stack infrastructure

spiceai copilot-instructions.md

Copilot instructions for spiceai/spiceai, covering spice.ai agent instructions, data correctness — absolute top priority, evidence — no claim without a reproduction, build, test, lint (expensive — read first) and git & prs.

spiceai/spiceai · 7,971 tokens

spiceai AGENTS.md

AGENTS.md instructions for spiceai/spiceai, a project described as: Add a real-time analytics node to your operational database. Spice is a portable, accelerated SQL query, search, and LLM-inference engine in Rust for data-grounded AI apps and agents.

spiceai/spiceai · 6 tokens

deer AGENTS.md