kaizen-agentic/docs/integrations/activity-definitions/weekly-optimization-review.md

id, name, enabled, owner, governance, status, trigger, context_sources

id	name	enabled	owner	governance	status	trigger	context_sources
kaizen-weekly-optimization-review	Weekly Kaizen Optimization Review	false	kaizen-agentic	custodian	proposed	type cron_expression timezone misfire_policy cron 0 10 * * 1 Europe/Berlin skip	type query params bind_to resolver discover_kaizen_scheduled_repos domain cadence custodian weekly context.scheduled_runs

Weekly Kaizen Optimization Review

Every Monday 10:00 Berlin time, opens an optimization-agent review task for each schedule-eligible repo whose .kaizen/schedule.yml enables the optimization agent. Chains the agent orientation with the existing metrics optimizer so the review is evidence-backed.

id: run-weekly-optimization
for_each: context.scheduled_runs
bind_as: r
condition: 'context.r.agent == "optimization" and context.r.enabled'
action:
  task_template: "Weekly optimization review: {context.r.repo}"
  description: |
    {context.r.prepare_command}
    kaizen-agentic metrics optimize          # refresh evidence
    Then load agents/agent-optimization.md, paste the prepared bundle plus the
    optimizer report, and act on recommendations. At session close:
    kaizen-agentic metrics record optimization --success --time <s> --quality <0-1>
  target_repo: context.r.repo
  priority: medium
  labels: ["kaizen", "agent-run", "optimization", "scheduled", "automated"]

CLI mapping: kaizen-agentic schedule prepare optimization then kaizen-agentic metrics optimize.

Complementarity: this generalizes the metrics-only weekly-metrics-optimize definition into a full agent run. Repos may run either; running both duplicates the optimizer step.

Activation: sync into activity-core via make sync-activity-definitions after the resolver is enabled; hold at enabled: false until smoke-tested.