From openarche
Inspects or updates validation stage for planned changes in current harness session, managing acceptance/regression checks, browser/observability evidence, blockers, and readiness.
How this command is triggered — by the user, by Claude, or both
Slash command
/openarche:validateThis command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
Use this command to inspect or update the validation stage for the current harness session. Required behavior: 1. Prefer the current session state in `.openarche/sessions/<task-id>/state.json`. Only create a separate note when the user explicitly asks for one. 2. Read the current `runbook.validation` section and keep its structure stable. 3. Use `runbook.validation` as the source of truth for: - acceptance checks - regression checks - browser validation state - observability validation state - blockers - readiness 4. If the user is attaching validation evidence, updat...
Use this command to inspect or update the validation stage for the current harness session.
Required behavior:
.openarche/sessions/<task-id>/state.json.
Only create a separate note when the user explicitly asks for one.runbook.validation section and keep its structure stable.runbook.validation as the source of truth for:
runbook.validation and store any file evidence under .openarche/sessions/<task-id>/evidence/ instead of inventing a parallel format.When presenting the validation work, organize it into:
npx claudepluginhub done-0/openarche --plugin openarche/validateVerifies session completeness and quality gates by running analysis script, checking 100% tasks, deliverables, tests, files, security; auto-fixes minor issues.
/verify-workValidates built features through conversational UAT, producing a phase-UAT.md report. Automatically diagnoses issues, plans fixes, and prepares for execution.
/validateRuns validation checks on implementation for a topic or plan-path, executing proof methods from validation plan and reporting pass/fail evidence.
/fire-4-verifyVerifies a completed phase by checking must-haves and running a 70-point quality validation checklist, then generates a detailed report and optionally routes to gap closure.
/verifyVerifies implementations or changes using parallel specialized agents with 0-10 grading, full reports across tests/security/quality, and improvement suggestions.
/validateRe-runs multi-agent verification on current code changes via the groundwork:validation-loop skill, without re-executing the original task.