> ## Documentation Index
> Fetch the complete documentation index at: https://docs.murmur.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Personas

> Reusable templates that define how an agent behaves — system prompt, model, allowed tools, default tasks, and turn limits applied at spawn time.

An **agent persona** is a reusable template for how an [agent](/concepts/agents) 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

| Field             | Purpose                                                        | Example                                          |
| ----------------- | -------------------------------------------------------------- | ------------------------------------------------ |
| `name`            | DNS-label identifier within the tenant                         | `programmer`                                     |
| `description`     | One-line summary shown in the spawn UI                         | "Mythical programmer obsessed with code quality" |
| `prompt` (body)   | The system prompt — instructions, voice, principles            | (markdown prose)                                 |
| `model`           | Override the default model                                     | `claude-opus-4-7`                                |
| `tools`           | Allowlist of Claude Code tools the agent may use               | `Bash, Edit, Read, Grep`                         |
| `disallowedTools` | Tools the agent may not use                                    | `NotebookEdit`                                   |
| `maxTurns`        | Maximum number of turns before the agent stops                 | `50`                                             |
| `tasks`           | Default checklist items with optional activation conditions    | (see [reference](/catalog/agent-persona))        |
| `followups`       | Per-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](/concepts/events) 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](/catalog/agent-persona#follow-up-overrides) for the format.

## Built-in personas

Murmur ships platform-managed personas that exist in every tenant:

| Persona                          | Optimized for                                  |
| -------------------------------- | ---------------------------------------------- |
| `programmer`                     | Implementation, code review, simplification    |
| `architect`                      | Design docs, proposals, package boundaries     |
| `designer`                       | UX, visual polish, dashboard work              |
| `researcher`                     | Investigation, fact-checking, root-cause       |
| `tester`                         | Test strategy, flake fixing, integration tests |
| `frontend`                       | React/TypeScript SPA work                      |
| [`director`](/concepts/director) | Spawning + coordinating other agents           |

Use them via the `--agent` flag on [`murmur spawn`](/cli/spawn), or select them in the dashboard's spawn dialog.

## Authoring your own

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

## Lifecycle

The [agent](/concepts/agents) 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.

***

| Type      | Page                                    |
| --------- | --------------------------------------- |
| Reference | [agent-persona](/catalog/agent-persona) |
| Reference | [`murmur spawn --agent`](/cli/spawn)    |
| Reference | [`murmur set agent-persona`](/cli/set)  |
| Concept   | [Agents](/concepts/agents)              |