mirabilis AGENTS.md

mirabilis AGENTS.md is an instructions file for Codex, OpenCode from AlexShchuka/mirabilis. It costs 3,582 tokens per session, scanned A, original, MIT.

Project instructions for Mirabilis, a self-hosted development container that runs Claude Code with persistent memory and broad network access. They describe its security boundaries, storage, and network setup.

In plain words
What is it for?
Guiding changes to the development container, its persistent data, authentication path, and security behavior.
Why use it?
They explain which protections belong to the container and which belong to its control system.

Instructions file for CodexOpenCode

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/alexshchuka/mirabilis/agents-md
Clone the repo
git clone --depth 1 https://github.com/AlexShchuka/mirabilis

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 mirabilis AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alexshchuka/mirabilis/agents-md.svg)](https://agentmods.dev/instructions/alexshchuka/mirabilis/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/alexshchuka/mirabilis/agents-md"><img src="https://agentmods.dev/badge/instructions/alexshchuka/mirabilis/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,582 This file is loaded in full into every session.
When invoked 3,582 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03582 $0.03582
Opus 5 $0.01791 $0.01791
Sonnet 5 $0.00716 $0.00716
Haiku 4.5 $0.00358 $0.00358

Measured 5d ago against content hash b81156c3219e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mirabilis 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 5d 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 · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

mirabilis is a personal, open-source cross-platform dev container that runs Claude Code with full autonomy, the neuro-matrix harness preinstalled, persistent memory, and open egress. CLAUDE.md is a symlink to this file. Setup: README.md. Threat model: SECURITY.md.

Boundaries

  • The container is the security boundary. Inside it the agent has full freedom — root, sudo, any file. Behavioural limits (no push/force to main, no credential exfiltration) are the harness's job, not the sandbox's. Sandbox provisions; harness behaves (G2).
  • Work lives in /workspace, a named volume the sandbox owns. ~/.claude and ~/.config/gh are persistent volumes (memory, auth). /tmp and everything else is ephemeral.
  • Egress is open: the container reaches the network directly — no in-container allowlist. api.anthropic.com is reached via the chain: claude → headroom (:8787, observability + MCP) → host auth proxy (token injection) → Anthropic. The real Claude token never enters the sandbox — only a per-session key does. Stopping credential exfiltration is the harness's behavioural job. WebFetch/WebSearch go via the Anthropic API and always work. Deliberate additional egress edge: internal/engine/localllm POSTs to host.docker.internal:1234 (LM Studio default port) to offload prompts to a host-local model. This edge is intentional and hardcoded to http://host.docker.internal:1234/v1; it carries only prompt text, never the Claude token. If an egress allowlist is added in future, it must include host.docker.internal:1234.
  • Secrets: single source of truth per platform — keychain (macOS) / file 0600 (Linux/WSL). Entry name mirabilis-<key> (no doubled suffix). The Claude OAuth token stays on the host; only the per-session key reaches the container. The Telegram token is host-side; Telegram chat-id is written to .mirabilis/chat-id (not an env var).

Read the full file on GitHub · 174 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. 5d ago First seen · 174 lines · 3,582 tokens per session scan A b81156c3219e

Subscribe to this mod's changes

mirabilis AGENTS.md is an instructions file published in the GitHub repository AlexShchuka/mirabilis (5 stars, last pushed 3d ago), licensed MIT. It adds 3,582 tokens to every session, about $0.0179 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.