belmont

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

Write an Amazon-style Working Backwards document (PR/FAQ). Use when the user mentions 'Working Backwards', 'PR/FAQ', 'PRFAQ', 'press release and FAQ', or wants to define a product vision before detailed planning.

Implement just the next single pending task using the implementation agent

Debug router — choose between auto (agent-verified, narrow code fix) and manual (user-verified, deep spec context, in-place spec reconciliation)

Reduce input token bloat by archiving completed features, removing stale milestone files, trimming notes, and auditing convention files (CLAUDE.md, AGENTS.md).

Review alignment between planning documents (PR/FAQ, PRDs, Tech Plans) and the codebase. Use when you want to detect drift, resolve conflicts, or ensure plans match reality.

Show current status of belmont tasks and milestones

Reset belmont state files (PRD, PROGRESS, TECH_PLAN) to start fresh

Save learnings and discoveries to NOTES.md for persistence across sessions