ReflexioDeveloper Docs
Menu
GitHubWebsitellms.txt
CLI

reflexio agent-playbooks / reflexio user-playbooks

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

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 (pending → approved / 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

Terminal
reflexio agent-playbooks list [OPTIONS]
PropTypeDefaultDescription
--limit?int20Maximum number of playbooks to return.
--playbook-name?strnoneFilter by playbook category name.
--agent-version?strnoneFilter by agent version.
--playbook-status?strnoneFilter by approval status: "pending", "approved", or "rejected".
Terminal
reflexio agent-playbooks search "<query>" [OPTIONS]
PropTypeDefaultDescription
QUERY?str (positional)—Semantic search query. Required.
--limit?int10Maximum number of results.
--agent-version?strnoneFilter by agent version.
--playbook-status?strnoneFilter by approval status: "pending", "approved", or "rejected".

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.

Terminal
reflexio agent-playbooks add --content "<text>" --agent-version <v> [OPTIONS]
PropTypeDefaultDescription
--content?str—Playbook content text. Required.
--agent-version?str—Agent version this playbook applies to. Required.
--playbook-name?str"agent_corrections"Playbook category name.
--playbook-status?str"pending"Initial approval status: "pending", "approved", or "rejected".
--trigger?strnoneWhen this playbook applies (structured data).
--instruction?strnoneWhat to do (DO).
--pitfall?strnoneWhat not to do (DON'T).
--rationale?strnoneWhy this playbook matters.

update

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

Terminal
reflexio agent-playbooks update --id <int> [--content "<text>"] [--playbook-name <name>]
PropTypeDefaultDescription
--id?int—Agent playbook ID to update. Required.
--content?strunchangedNew content text.
--playbook-name?strunchangedNew playbook category name.

To update trigger or rationale, 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.

Terminal
reflexio agent-playbooks update-status --id <int> --status <pending|approved|rejected>
PropTypeDefaultDescription
--id?int—Agent playbook ID. Required.
--status?str—New approval status: "pending", "approved", or "rejected". Required.

delete

Terminal
reflexio agent-playbooks delete --id <id>
PropTypeDefaultDescription
--id?str—Agent playbook ID to delete. Required.

delete-all

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

Terminal
reflexio agent-playbooks delete-all [--yes]
PropTypeDefaultDescription
--yes / -y?flagfalseSkip the interactive confirmation prompt.

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.

Terminal
reflexio agent-playbooks aggregate [OPTIONS]
PropTypeDefaultDescription
--agent-version?strallAgent version to aggregate. Omit to aggregate all versions.
--playbook-name?strfirst configuredPlaybook category to aggregate.
--wait?flagfalseBlock until aggregation completes.

regenerate

Re-run playbook generation for a specific agent version.

Terminal
reflexio agent-playbooks regenerate --agent-version <v> [--wait]
PropTypeDefaultDescription
--agent-version?str—Agent version to regenerate. Required.
--wait?flagfalseBlock until regeneration completes.

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

Terminal
reflexio user-playbooks list [OPTIONS]
PropTypeDefaultDescription
--user-id?strnoneFilter by user ID.
--limit?int20Maximum number of playbooks to return.
--playbook-name?strnoneFilter by playbook category name.
--agent-version?strnoneFilter by agent version.
--status?strnoneLifecycle status: "current", "pending", or "archived".

search

Terminal
reflexio user-playbooks search "<query>" [OPTIONS]
PropTypeDefaultDescription
QUERY?str (positional)—Semantic search query. Required.
--limit?int10Maximum number of results.
--agent-version?strnoneFilter by agent version.

add

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

Terminal
reflexio user-playbooks add --content "<text>" [OPTIONS]
PropTypeDefaultDescription
--content?str—Playbook content text. Required.
--playbook-name?str"agent_corrections"Playbook category name.
--trigger?strnoneWhen this playbook applies.
--instruction?strnoneWhat to do (DO).
--pitfall?strnoneWhat not to do (DON'T).
--rationale?strnoneWhy this playbook matters.

update

Terminal
reflexio user-playbooks update --id <int> [--content "<text>"] [--playbook-name <name>]
PropTypeDefaultDescription
--id?int—User playbook ID to update. Required.
--content?strunchangedNew content text.
--playbook-name?strunchangedNew playbook category name.

delete

Terminal
reflexio user-playbooks delete --id <id>
PropTypeDefaultDescription
--id?str—User playbook ID to delete. Required.

delete-all

Terminal
reflexio user-playbooks delete-all [--yes]
PropTypeDefaultDescription
--yes / -y?flagfalseSkip the interactive confirmation prompt.

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.