Borrowing it
Nothing to install: this file belongs to aspectrr/deer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aspectrr/deer/main/AGENTS.mdgit clone --depth 1 https://github.com/aspectrr/deerWrote 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.
[](https://agentmods.dev/instructions/aspectrr/deer/agents-md)<a href="https://agentmods.dev/instructions/aspectrr/deer/agents-md"><img src="https://agentmods.dev/badge/instructions/aspectrr/deer/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.
<a href="https://agentmods.dev/instructions/aspectrr/deer/agents-md"><img src="https://agentmods.dev/badge/instructions/aspectrr/deer/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00526 | $0.00526 |
| Opus 5.5 | $0.00210 | $0.00210 |
| Sonnet 5.5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
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 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.
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.gofiles - 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
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 · 95 lines · 526 tokens per session scan A 0f5aa76bcd98
deer AGENTS.md is an instructions file published in the GitHub repository aspectrr/deer (406 stars, last pushed 6mo ago), licensed MIT. It adds 526 tokens to every session, about $0.0021 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.
deer AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deer AGENTS.mdaspectrr/deer | Instructions file | 406 | 6mo ago | MIT | A | 526 | 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 | yesterday | 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 |