dug-21

Version bump, changelog generation, tag, and push to trigger the release pipeline.

Manage a goal's capability map in Unimatrix — the behaviorally-proven units that must exist for a goal to be delivered. Decompose goals into capabilities, track delivery status, and report what's left. Status advances to proven ONLY on attached behavioral evidence.

Unimatrix Zero — vision guide mode. Strategic advisor for product evolution, feature ordering, vision alignment, security posture, and codebase health. Conversational. Does not modify application code or run delivery protocols.

Post-merge retrospective — extracts patterns, procedures, and lessons from shipped features into Unimatrix. Use after a feature PR is merged.

Store an architectural decision record in Unimatrix. ADRs live in Unimatrix only — no ADR files. Use after each design decision.

Ad-hoc independent product-lens review via uni-zero-reviewer. Use for re-reviews after rework or reviews outside protocol runs. Advisory only — human makes the call.

Store an architectural decision record in Unimatrix. ADRs live in Unimatrix only — no ADR files. Use after each design decision.

Initialize Unimatrix in a repository: append knowledge block to CLAUDE.md and produce agent orientation recommendations.

On-demand vision alignment check. Spawns ndp-vision-guardian to review SPARC artifacts against product/vision/ALIGNMENT-CRITERIA.md.

Validate planning swarm output: artifact existence, AC coverage, pattern IDs, stale references, internal consistency. Produces a glass box report.

NDP 4-tier implementation validation. Tier 1: compilation (build+test+anti-stub). Tier 2: process adherence. Tier 3: spec compliance. Tier 4: risk classification. Produces glass box reports.

Retrieve APPLICATION patterns (architecture, procedures, conventions) from AgentDB using multi-signal retrieval: pattern search, causal recall, and RL predictions. Use BEFORE implementing to ensure consistency.

AgentDB pattern lifecycle management: list, get, delete, deprecate, update, stats, search, duplicates. Use when cleaning up stale patterns, removing deprecated entries, finding duplicates, or auditing pattern health. Workaround for missing MCP delete/update tools (GH Issue #42).

Record feedback on pattern effectiveness. Stores episodes that train the recommendation system, feed the RL engine for smarter pattern ranking, build causal knowledge, and enable pattern discovery via learner.

Store APPLICATION patterns (architecture, procedures, conventions) in AgentDB's patterns table. NOT for swarm/transient memory.

Auto-discover patterns from reflexion episodes. Run post-feature to consolidate successful approaches into reusable patterns.