PRD: org-agent Cognitive Core & Configuration

0. Core Mandates

The `org-agent` project MUST adhere to these foundational mandates:

Mandate 1: Strict Homoiconic Memory. All documentation, planning, and system logic MUST be authored in Org-mode (.org) and Common Lisp. Markdown (.md) and JSON are strictly prohibited for internal use.
Mandate 2: Minimalist Microkernel. The core daemon MUST remain minimalist, handling only the cognitive loop, the persistent Object-Store, and the communication protocol. All domain-specific features and LLM provider logic MUST be implemented as hot-reloadable Skills living in the user's Memex.

The `org-agent` must transition from a monolithic prototype to a generalized neurosymbolic kernel.

The daemon MUST implement a 4-stage pipeline: Perceive -> Think -> Decide -> Act.
System 1 (Neural) MUST be restricted to the 'Think' stage.
System 2 (Symbolic) MUST have absolute authority in the 'Decide' stage to block or modify neural proposals.
The I/O protocol (OACP) MUST be encapsulated in 'Perceive' and 'Act'.

All secrets (API keys) and environment-specific settings (ports, paths) MUST live in a `.env` file.
The system MUST automatically load `.env` upon system initialization.
Secrets MUST NOT be hardcoded or checked into source control.

TODO Daemon starts and loads LLM_API_KEY from .env.
TODO `cognitive-loop` successfully routes a `:buffer-update` event through all 4 stages.
TODO System 2 (`decide`) successfully blocks an `:eval` request containing "shell-command".