blake-simpson

Apply a Codex-only Belmont planning handoff packet after a plan-mode product-plan or tech-plan interview; write only the explicit .belmont files named in the packet without asking new planning questions.

Interactive planning session - create PRD and PROGRESS files for a feature

Technical planning session - create detailed implementation spec from PRD

Claude Code only. Drive a single feature to completion by self-pacing /belmont:implement → verify → next → status until no pending milestones remain.

Auto debug loop — investigate, fix, verify using agent-dispatched pipeline

Manual debug loop with deep Belmont context and in-place spec reconciliation — user-verified fix + correct the specs that let the bug exist

Implement the next pending milestone from the PRD using the agent pipeline

Run verification and code review on completed tasks

Scaffold a new Verona connector under ~/.verona/user/connectors/<id>/ — its own directory, manifest, source, build output. Loaded by the daemon at startup and on `verona reload`. Use when the user wants to add support for a new external system (Discord, Telegram, email, GitHub webhooks, QuickBooks, etc.).

Scaffold a new Verona agent in the user-agents dir (default ~/.verona/agents/<name>/) with SOUL.md, tasks/, memory/INDEX.md, and a valid agent.toml. Use when the user wants to create a new agent.

Add a new task to an existing Verona agent. Updates agent.toml and creates tasks/<id>.md. Use when the user wants to extend an existing agent with another scheduled or on_message task.

Report Verona's current health — daemon state, registered agents, scheduled jobs, recent invocations, costs. Use when the user asks 'how's Verona doing' or 'what did the agents do last night'.

Refine an agent's SOUL.md (the personality file) toward OpenClaw-style specificity. Use when the user feels an agent's tone is bland, generic, or off — or when starting from scratch.