AgentLayer▸docs
Run it

Naming your agent

Your agent wakes up as Oppi. Call it whatever you like; the plugin stays agentlayer.

Two separate things:

Lives inChangeable
Display name: what it calls itself, what the dashboard showsIDENTITY.md → - **Name:**Freely, any time
Namespace: the agentlayer command prefix on every host, and the MCP server agent that prefixes tool names (mcp__plugin_agentlayer_agent__)The plugin manifestsOnly by forking

init asks for a name, an emoji, and an avatar up front. Oppi 🐙 is the default, with its own avatar; a different name starts without one. Everything downstream reads the answer: templates are written in that name, the session banner and TASKS.md header render it, skill output like the standup card and the briefings signs off with its emoji, and the compile prompts refer to it, so your compiled memory speaks about the agent you actually named.

A different name also picks its colors, a primary and an accent from four pairs that init draws in their own colors (Oppi's are orchid #B456A8 and mint #3BAA70). They sit on the Colors line of IDENTITY.md, beside the emoji, and the session banner, the dashboard and the cmux sidebar's agent chip draw the agent in them.

Why an octopus

Oppi, the AgentLayer octopus

Meet Oppi, or Ops to its friends, which is also what it's for. An octopus keeps eight arms busy at once, and each arm does some of its own thinking: about two-thirds of its neurons sit in the arms. Its central brain still holds it all together.

That's the agent: many jobs in flight, each handled with some independence, and one brain that remembers all of it. Octopuses are also among the cleverest animals around: they solve puzzles and use tools. Call your agent whatever you like; Oppi is just who shows up first.

Renaming an existing home

rename-agent does the migration. It runs only when you type the command and asks for permission even then, because it rewrites files across the whole brain.

ChangesStays
IDENTITY.md: the Name (the old one added to Formerly), the emoji, the colors, the avatarThe home folder, and every path that contains it
Markdown the agent reads now: SOUL.md, AGENTS.md, USER.md, .claude/CLAUDE.md, rules, knowledge, projectsDated records: reports/, knowledge/raw/, every archive/ folder
TASKS.md and the dashboard, regeneratedCode, HTML and anything else that isn't markdown; your custom skills, which it lists for you to edit

It shows a dry run first: every line it would change, with the words around each mention, and the mentions it leaves alone, such as a path like Documents-Agents-Oppi.git. Read the lines, not the count: a mention that means someone else ("Oppi, the AgentLayer octopus") is in the list, and you keep it before anything is written.

The home folder keeps its name. Session history, the brain's version history and the home's settings are all tied to that path, so moving it is a separate job you do by hand.

Dated records keep the name they were written under. The - **Formerly:** line in IDENTITY.md loads every session and is read when knowledge compiles, so the agent knows the old name in them means itself. A seed bundle drops that line, since the agent it seeds has no such history. To finish a half-done rename, run it again naming the old name: that is a fresh dry run, so pass your keeps again.

Renaming survives updates: the upgrade skill resolves the name from your IDENTITY.md before diffing templates.

Forking is a different decision

Change name in the plugin manifests (.claude-plugin/plugin.json, .codex-plugin/plugin.json) and you get your own command and tool namespace (/scout:<skill>, mcp__plugin_scout_agent__). Settings still read the same AGENT_* variables, whatever the fork is called. The price is merging from upstream on every release, forever. If you only want the agent to feel like yours, rename it and skip the fork.

On this page