vp-beads

Use this agent when the user closes a sprint, finishes a batch of commits, runs `bd close`, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a `bd close` command has just run or the user is asking what to do next after a stretch of development work. Do NOT trigger during active development or mid-sprint issue work.

Manage the beads backlog for this project. Use when the user wants to review or triage open issues, reprioritize the backlog, identify obsolete issues to close, investigate a topic to inform future work, create new issues from research findings, or enrich an existing issue with external context. Trigger phrases: 'groom', 'triage', 'backlog review', 'reprioritize', 'stale issues', 'what should we close', 'too many issues', 'backlog health', 'investigate for backlog', 'research and create issues', 'add context to issue', 'enrich issue', 'plan the work for', 'break down into issues', 'start the sprint', 'plan the sprint', 'plan next sprint', 'what should we work on', 'find duplicates', 'dedup backlog', 'near-duplicates', or any request to audit, prune, or research work tracked in beads.

Audit the `bd remember` store and recommend which entries to prune, so each one earns its per-session `bd prime` injection cost. Read-only: it proposes a triage table plus the exact `bd forget` / migration commands; you run them. Use when `bd remember` entries have accumulated, feel stale, redundant, or conflicting, or when session-startup token cost from injected memories is high. Trigger phrases: 'harden memories', 'audit bd remember', 'prune bd remember', 'bd remember bloat', 'bd remember audit', 'trim bd remember', or '/harden-memories'. NOT for Claude Code auto-memory (`/dream` / Auto Dream files), NOT for Basic Memory graph hygiene (use vp-knowledge's memory-defrag / memory-lifecycle skills), and NOT for beads issues or the backlog (use /backlog-groomer).

Run a sprint retrospective for this project. Use when the user says 'retrospective', 'retro', 'close out the sprint', 'what went well', 'generate retro', or wants to generate a RETRO-NN.md file. Reads UPSTREAM-*.md files, recent git history, and conversation context to pre-populate the retrospective. Do NOT use for read-only sprint summaries — use the sprint-review agent for that.

Bilateral SYNERGY/UPSTREAM reconciliation across sibling projects. Use when the user wants to sync sibling SYNERGY/UPSTREAM files, compare both sides to surface drift, find reciprocation gaps (entries here but not there, or vice versa), flag stale-aligned rows, detect status drift across sides, surface friction the sibling tracks ABOUT this project (their UPSTREAM-<this-project>.md), or apply a reciprocation batch with --auto-reciprocate. Workflow 3 covers two UPSTREAM pairing modes: shared third-party dependencies AND reciprocal sibling-friction pairs (UPSTREAM-<sibling>.md here ↔ UPSTREAM-<this-project>.md there). NOT for logging entries on this side (use /synergy-tracker workflow 1 (Log a synergy entry)) — sibling-sync compares both sides without writing by default. NOT for upstream → project drift (use /vendor-sync); sibling-sync handles peer-to-peer drift between sibling vp-* projects. Trigger phrases: 'sibling sync', 'compare siblings', 'sync sibling', 'reconcile siblings', 'reciprocation gap', 'sync drift', 'bilateral sync', 'sync SYNERGY', 'sync UPSTREAM both ways', 'auto-reciprocate', 'check sibling drift', 'peer-to-peer drift', 'cross-project drift', 'sibling reconciliation', 'sibling has friction about us', 'what does the sibling say about us', 'reconcile sibling-tracked friction', 'reciprocal upstream friction', 'friction filed against this project', 'sibling follow-up', 'act on sibling drift', 'after sibling-sync', 'follow-up actions', 'what to do about sibling findings'.

Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint, partition work into file-disjoint waves, map file contention across open issues, run a post-wave quality gate with review agents, manage agent backpressure, run a parallel research wave, or coordinate multiple concurrent agents on a shared codebase. Works with or without beads: sources waves from the beads backlog, from a ROADMAP.md, or from a manually supplied work list. Trigger phrases: 'swarm sprint', 'wave plan', 'launch wave', 'execute wave', 'post-wave gate', 'contention map', 'research wave', 'parallel agents', 'multi-agent sprint', 'agent wave', 'swarm orchestration', 'swarm from ROADMAP', 'wave plan without beads', 'swarm with manual list'.

3 hooks across 3 events