AgentLayerdocs
Agent · Harness

The agent is the harness

Layer 02. The agent that loads the context every session, and the rails around the model that make it safe to use.

What makes an agent effective inside a company is not which model answers. It is what the agent knows before it starts, what it is allowed to do, and what gets recorded when it acts. Those live in files around the model. The model is a setting.

The rails

RailWhat it doesPage
Operating manualAGENTS.md says how the agent works, what it may do, and how you like to work. Every host reads it at session start.The agent home
Permission railsAllow and deny lists, a sandboxed shell, secrets in a store the agent's own tools cannot read.Configuration
HooksSession start loads the context, session end captures it, a guard checks every shell command. Skills advise; hooks enforce.Hooks
Audit trailEvery session captured to a dated file, every task change threaded, the folder under git.Tasks
ObservabilityThe dashboard, the session radar, briefings and pulses.Daily rhythm
Host-neutralOne home works from Claude Code or Codex. What a host provides, and what a new one needs.Hosts

How a session runs

Launch from the home. The SessionStart hook loads the identity stack, the wiki index, active memory, the task board, today's date, and the tail of the last session. You type. Skills run when you invoke them; tools do I/O and return prompts for your own session to think with, so nothing bills a metered key. On exit the transcript is captured for the next compile. Your first session walks through one.

Work, not chats

Tasks are one markdown file each with frontmatter, a checklist, and a thread. Projects group them. Parallel work happens in worktrees so agents never collide on one repo. The architecture page shows how the host, the plugin, and the brain fit.

On this page