crewship persona

Manage PERSONA.md — the ~1.5 KB identity surface the orchestrator injects into every agent’s system prompt at session start. The CLI mirrors the agent persona API and the crew persona API. Two layers:

Agent layer — per-agent override. Wins outright when non-empty.
Crew default layer — workspace-shared baseline that every agent in the crew falls back to.

crewship persona <subcommand> [flags]

All commands operate on the active workspace (crewship workspace use) and resolve targets by slug, not ID, to match the rest of the CLI surface.

Subcommands

Command	Description
`view <agent-slug>`	Show the resolved persona — content plus which layer it came from.
`edit <agent-slug>`	Open `$EDITOR` to update the agent-layer override.
`reset <agent-slug>`	Drop the agent-layer file (crew default reappears).
`history <agent-slug>`	List the agent’s persona version log (newest first).
`suggest-from-inbox <audit-id>`	Operator-side approval of a pending agent persona proposal.
`crew <crew-slug>`	Sub-tree applying the same view/edit/reset/history verbs to the crew-default layer.

`crewship persona view`

crewship persona view <agent-slug>

Prints the resolved persona — agent-layer file if present, otherwise crew default, otherwise the per-role synthesised stub — along with the layer marker and byte count.

Layer:        agent       (842 / 1500 bytes)
From default: false
─────
# Engineer

Focus on backend services. Prefer async over sync...

From default is true only when neither agent nor crew has a file on disk and the response is the You are the {role}... synthesised text — useful when reviewing a freshly-onboarded crew.

`crewship persona edit`

crewship persona edit <agent-slug>
crewship persona edit <agent-slug> --no-editor < new-persona.md

Pulls the current agent-layer content, opens $EDITOR, and writes the saved buffer back via PUT /api/v1/agents/{id}/persona. Without an editor (CI, piped stdin) pass --no-editor and provide the new body on stdin.

Flag	Default	Effect
`--no-editor`	`false`	Skip `$EDITOR`; read the new content from stdin.

The server caps at 1500 bytes; the CLI rejects oversize buffers client-side before the round-trip.

`crewship persona reset`

crewship persona reset <agent-slug>

Removes the agent-layer file. The next view falls through to the crew default (or the synthesised stub when the crew has none).

`crewship persona history`

crewship persona history <agent-slug>
crewship persona history <agent-slug> --limit 5

Lists memory_versions rows for the agent’s PERSONA.md path, newest first. Server clamps --limit to 100. Use the printed sha256 with crewship memory show to read an older version’s content without restoring it.

`crewship persona suggest-from-inbox`

crewship persona suggest-from-inbox <audit-id>

When an agent’s POST /persona/suggest lands as an inbox proposal (because the crew’s autonomy is strict / guided / trusted), this is the operator’s approval path: redeem the inbox audit_id to apply the proposed content and write a memory_versions entry. Reject with the regular crewship approve --deny flow against the same inbox item.

`crewship persona crew`

crewship persona crew <crew-slug>              # default subcommand: view
crewship persona crew view <crew-slug>
crewship persona crew edit <crew-slug>
crewship persona crew reset <crew-slug>

Same verbs against the crew-default layer at /api/v1/crews/{crewId}/persona. There is no suggest equivalent — agents propose only into their own layer, and the operator authors crew defaults directly.

Documentation Index

​crewship persona

​Subcommands

​crewship persona view

​crewship persona edit

​crewship persona reset

​crewship persona history

​crewship persona suggest-from-inbox

​crewship persona crew

​See also