Loading complete AGENTS.md…
One Mac, seven agents, one rulebook.
This site explains how Isaac's AI coding agents are set up and how they work together. It is generated from the same files the agents read, so what you see here is what is actually configured, not a description that drifted.
The setup in plain English
What lives here. Several AI coding agents run on one Mac: Claude Code (Anthropic), Codex (OpenAI), Cursor, Grok (xAI), OpenCode (open source, running local and OpenRouter models), and Hermes (a scheduler and assistant), plus Argent, a tool for testing phone apps. Each is a separate product with its own settings folder. This site and the repository behind it hold the shared rulebook and a copy of each product's settings, so the whole arrangement can be understood, audited, and rebuilt on another machine.
One rulebook, three layers. Every agent reads the same three files before it does anything: the constitution (rules that never change per task), the runtime overlay (which model orchestrates, which does routine work, which reviews), and the machine-readable routing graph. When prose and graph disagree, the graph wins.
Who is the boss. A Claude model (Fable 5.1 or Opus 5) or Codex orchestrates: it plans, splits the work, hands pieces out, checks results, and reports. Routine implementation goes to fast workers. Review always crosses vendors: work written by Claude is reviewed by Codex, and work written by Codex is reviewed by Claude, because a reviewer from the same family shares the author's blind spots.
When Isaac names a helper, that is final. "Use Grok" or "send this to Codex" means exactly that provider. An agent may not quietly substitute one of its own subagents because it was easier.
What is never done without asking. Committing, pushing, opening a pull request, deploying, publishing, running a database migration, posting to social media, writing to the marketing database, or spending money on a large media generation. Plain release language ("push it live", "ship it", "commit and push") is one authorization for the full chain; nothing weaker counts and nothing carries over from an earlier message.
Everything is shared. All agents see the same tool servers, the same skill library, and the same safety guard on shell commands. A small lint runs at the start of each session and prints a line if any of that has drifted.
Experimental features are on. Every experimental feature in every agent is enabled, with a short, named list of exceptions. Codex's own in-app browser and Computer Use are deliberately on.
How it stays honest. Nothing here contains a password, token, cookie, or account. Every refresh runs two secret scanners and refuses to sync if either finds anything. A daily job refreshes the snapshot; committing and pushing remain a human decision.
Chapter 2
The agents
Seven runtimes with their own settings folders, and five apps that launch them and inherit everything. Each card says which models it runs, what its job is, how it reads the rulebook, and how its permissions and guard are set.
Hosts that inherit the setup
Model roles, from the routing graph
Named agent definitions
Files under claude-code/agents and codex/agents. The four Haiku dispatchers (grok, luna, cursor, codex) exist so a named external delegate is visible where the model looks for agents.
Chapter 3
The rulebook
Six files. Three are policy every agent loads; three are the executable graph, the tool catalog, and the skills policy they point at. Every one is readable here in full.
PRIMARY SOURCE OF TRUTH
Global agent constitution, every word
Source of truth. The complete ~/AGENTS.md as the agents read it. Rules appear exactly once; mechanics live in skills and load only when a task needs them.
Chapter 4
How work flows
In the order an orchestrator applies them. Every value below is read from the routing graph.
Ceremony scales to blast radius
The route a task takes
How a named delegate is actually reached
Chapter 5
The words that trigger things
What each phrase authorizes, how much ceremony it carries, and which file says so.
Chapter 6
Permissions, guard, gates
Permission posture per runtime
The guard, explained
Gated: recorded, then allowed
Hard-blocked: no in-agent override
Every hook, with its runtime bindings
Chapter 7
Tools (MCP)
One pinned catalog for every runtime. The default profile starts automatically; the others switch on for a task.
Profiles
Outside the shared catalog
Chapter 8
Browser automation
The chain, from an agent's request to a tab in Isaac's Chrome
The four transports
Invariants
Read the full design
Chapter 9
Experimental features
Chapter 10
Skills
One canonical copy of each skill in ~/.agents/skills. Claude, Codex, and Hermes link to it; Cursor, Grok, and OpenCode scan it. A skill's description is its trigger: every session sees the names and descriptions, and a skill's body loads only when a task matches (or Isaac names it). Isaac's private library of about 84 leaf skills is installed as nine category routers (ads, app-store, images, operations, prompting, seo, video, voice, website): a router fires on its subject and points the agent at exactly one leaf, read on demand, so the library costs about 1,000 tokens per session instead of 10,000.
—
Chapter 11
Backup, refresh, drift
How the live machine becomes this repository, how secrets are kept out, and how drift between the layers is caught.
Security controls on this site
Recent snapshots
What the repository holds
Chapter 12
Every file
Every safe tracked Markdown file and registered agent descriptor, readable in full.
—