Reflexio Docs
CLI Reference

playbooks

Manage user playbooks and agent playbooks — CRUD, aggregation, approval.

reflexio agent-playbooks / reflexio user-playbooks

Two related command groups manage the playbook system:

  • user-playbooks — rules extracted from individual interactions, scoped per request.
  • agent-playbooks — aggregated, agent-level rules produced by clustering user playbooks. Supports an approval workflow (pendingapproved / rejected).

The typical lifecycle: publish interactions → extractors emit user playbooks → agent-playbooks aggregate clusters them into agent playbooks → review and approve.


reflexio agent-playbooks

list

reflexio agent-playbooks list [OPTIONS]

Prop

Type

reflexio agent-playbooks search "<query>" [OPTIONS]

Prop

Type

add

Add an agent playbook directly, bypassing the aggregation pipeline. Useful for seeding rules without first producing sample user playbooks for the aggregator to cluster.

reflexio agent-playbooks add --content "<text>" --agent-version <v> [OPTIONS]

Prop

Type

update

Update editable fields on an existing agent playbook. Pass at least one of --content / --playbook-name.

reflexio agent-playbooks update --id <int> [--content "<text>"] [--playbook-name <name>]

Prop

Type

To update trigger, rationale, or blocking_issue, use the Python client's update_agent_playbook() / update_user_playbook() methods — each field is updated independently.

update-status

Dedicated approval-workflow command. Prefer this over update for status changes — the server has a single-purpose endpoint that writes a smaller change log.

reflexio agent-playbooks update-status --id <int> --status <pending|approved|rejected>

Prop

Type

delete

reflexio agent-playbooks delete --id <id>

Prop

Type

delete-all

Delete every agent playbook (scoped to agent playbooks only — user playbooks are untouched).

reflexio agent-playbooks delete-all [--yes]

Prop

Type

aggregate

Cluster similar user playbooks into agent playbooks. Without --agent-version, discovers every agent version that has user playbooks and aggregates each one separately. --playbook-name defaults to the first playbook name configured on the server.

reflexio agent-playbooks aggregate [OPTIONS]

Prop

Type

regenerate

Re-run playbook generation for a specific agent version.

reflexio agent-playbooks regenerate --agent-version <v> [--wait]

Prop

Type


reflexio user-playbooks

Same shape as agent-playbooks for list / search / add / update / delete / delete-all, but operates on the pre-aggregation user playbook layer and has no approval workflow.

list

reflexio user-playbooks list [OPTIONS]

Prop

Type

search

reflexio user-playbooks search "<query>" [OPTIONS]

Prop

Type

add

Manually add a user playbook entry. Fills in the structured data block directly rather than running it through extraction.

reflexio user-playbooks add --content "<text>" [OPTIONS]

Prop

Type

update

reflexio user-playbooks update --id <int> [--content "<text>"] [--playbook-name <name>]

Prop

Type

delete

reflexio user-playbooks delete --id <id>

Prop

Type

delete-all

reflexio user-playbooks delete-all [--yes]

Prop

Type

user-playbooks delete-all and agent-playbooks delete-all are independent — each wipes only its own layer. Run both if you want a clean slate.