Your first mission

1. 01

   Set up once: sign in, connect agents, start MUON

   After installing, run one command. It verifies your GitHub identity (MUON stays locked until you do), registers MUON with the coding agents you choose, and starts the local brain and runner. In the app, the first-run wizard does the same.

   muon setup

   muon doctor afterwards prints a short verdict: brain, runner, ready agents, and one next step for anything that needs attention.

2. 02

   Connect a vendor

   MUON checks Claude Code, Codex, Cursor, OpenCode and Kiro separately for installed vs. authenticated, and gives one concrete next action for whichever is missing. You never hand MUON a token — you log in to the vendor's own CLI, and MUON only observes readiness. Re-check any time with:

   muon onboard

3. 03

   Pick a workspace

   Run MUON from the folder you want the crew to work in, or choose it in the app. Memory, blast-radius and every path in the run are scoped to it.

4. 04

   Run a mission chat

   Type what you want done into the chat. MUON's orchestrator plans the work, dispatches it to the fleet, and reports back — the gates stay yours. No task in mind? MUON can seed a tiny, safe sample so you can watch the whole loop.

   muon quickstart                 # seed + dispatch a safe sample task
   muon chat --workspace <dir>     # or start a real mission yourself

5. 05

   Watch the crew

   Open the desktop's Crew Topology tab (⌘K → “Open crew topology”) to see who is doing what: one node per vendor lane, subagents nested under their parent, and peer edges only where two jobs actually exchanged an addressed message.

   muon crew roles --chat <id>     # who holds which role, and why
   muon crew coord --chat <id>     # peer messages, file claims, conflicts
   muon dispatch status            # active jobs across the fleet

   Peer messages render as explicit “Agent text · untrusted” — another agent's words are evidence, never an instruction, and never something that can approve or dispatch on its own.

6. 06

   See the pre-edit view

   Before an agent edits a target, MUON fuses its code blast-radius with the human-confirmed memory anchored to it — prior decisions, contested proposals, and live cross-agent activity on the same target.

   muon context <file-or-symbol> # any symbol, file or module path

   Trusted decisions show their full text. Contested proposals show existence-only until you explicitly ask to read them — an unvetted note can never reach an agent as if it were settled fact.

7. 07

   Approve, review, merge

   When an agent needs to cross a boundary — an edit outside the expected surface, a network call, a merge — MUON files a gate and waits. A merge gate is graph-certified when possible: MUON reviews the diff itself and either certifies it or marks specific files REVIEW BLIND for a human read.

   muon approve list
   muon approve review --approval-id <id>     # artifact digest + blind files
   muon approve resolve --approval-id <id> --status approved

The desktop sidebar's full-auto panel turns red when armed — that color is deliberate: it is disabling a gate, and MUON wants that visible at a glance, not buried in settings.

• Off (default): every approval waits for you.
• Armed, all lanes: approvals resolve automatically. Egress and blocked merge reviews still ask.
• Armed, a subset of lanes: checked lanes approve automatically; everything else still asks. A request MUON cannot attribute to a lane is never covered by a partial selection.