🛡️ The approval and policy layer for AI agents. Intercept risky actions before they run, block them, or approve them remotely.
Command Claude Code
Apply the approved improvements from the latest memory-self-review PROPOSAL. Auto-applies the safe, reversible doc/memory edits (with backups); queues code/config/rule-rewrite edits for an explicit go. Never commits or pushes.
Command Claude Code
Post-commit verification wave — dispatch gate-runner, drift-auditor, and security-reviewer in parallel over the pending changes, report only failures.
Command Claude Code
Recurring find-and-fix quality pass over the whole DashClaw app — browser smoke (frontend-verify) + code gates → triage → parallel worktree fixes → verify → ship. The goal prompt that drives the dashclaw-find-and-fix workflow.
Command Claude Code
Officially retire the published dashclaw/legacy Node SDK the safe way — deprecate now, delete at v5 — without breaking external npm consumers. Drives the legacy-sdk-deprecation-sweep workflow.
Command Claude Code
Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMORY.md health, and PROPOSE (never apply) CLAUDE.md/memory edits for human approval.