Skip to main content
An agent persona is a reusable template for how an agent should think and what tools it should use. It’s the difference between spawning “a Claude” and spawning “a code reviewer” or “an architect drafting a proposal” — same model underneath, different instructions, tool budgets, and behavior. Personas live in the catalog as the agent-persona kind. They are tenant-scoped, version-controlled, and authored in Markdown with YAML frontmatter or as structured YAML.

​
What a persona contains

FieldPurposeExample
nameDNS-label identifier within the tenantprogrammer
descriptionOne-line summary shown in the spawn UI”Mythical programmer obsessed with code quality”
prompt (body)The system prompt — instructions, voice, principles(markdown prose)
modelOverride the default modelclaude-opus-4-7
toolsAllowlist of Claude Code tools the agent may useBash, Edit, Read, Grep
disallowedToolsTools the agent may not useNotebookEdit
maxTurnsMaximum number of turns before the agent stops50
tasksDefault checklist items with optional activation conditions(see reference)
followupsPer-event-class overrides for follow-up instructions and tasks(see below)
The prompt is the heart of the persona. Write it as you would a senior engineer’s briefing: principles, conventions, what to avoid, what to prefer.

​
Follow-up instructions

When an event wakes an agent — a PR comment, a PR review, a CI result — the follow-up has two parts: the platform-formatted content (the facts of the event) and the instructions (what to do about them). A persona can tailor the instructions and the checklist tasks per event class through its followups map, so a payments reviewer can react to PR comments differently from a generalist while still receiving the same platform-formatted event. The content is always platform-formatted — personas shape only the response, never the event formatting. See the agent-persona reference for the format.

​
Built-in personas

Murmur ships platform-managed personas that exist in every tenant:
PersonaOptimized for
programmerImplementation, code review, simplification
architectDesign docs, proposals, package boundaries
designerUX, visual polish, dashboard work
researcherInvestigation, fact-checking, root-cause
testerTest strategy, flake fixing, integration tests
frontendReact/TypeScript SPA work
directorSpawning + coordinating other agents
Use them via the --agent flag on murmur spawn, or select them in the dashboard’s spawn dialog.

​
Authoring your own

Create personas with murmur set agent-persona — either piping a Markdown file with YAML frontmatter, or structured YAML. Both produce identical catalog records. See the agent-persona reference for all fields and formats.

​
Lifecycle

The agent inherits the persona’s tools, model, and system prompt at spawn time. Edits to personas affect future spawns only — running agents continue with the persona they were spawned with.
TypePage
Referenceagent-persona
Referencemurmur spawn --agent
Referencemurmur set agent-persona
ConceptAgents