sovereign-plugins

Interview-based project scaffolding — generates CLAUDE.md, ROADMAP, .gitignore, and .env.example from decisions, not templates

Claude Code infrastructure and agent team setup — rules, hooks, memory system, routing, and agent installation in one guided flow

Define what is IN, what is OUT, and exit criteria before implementation. Quick mode (3 questions) or Full mode (layered spec with ADR)

Declare the editable zone — everything outside is frozen. Prevents scope creep during implementation

Agent discipline engine — locks the goal, enforces PLAN-DO-VERIFY-FINALIZE-OUTPUT loop, detects 11 success masquerading patterns

Mandatory pre-push pipeline — secrets scan (12 patterns), build/test gate, lint, parallel AI code review. Blocks push on Critical/High findings

Session opener — loads handoff from last session, reviews lessons learned, runs health check, outputs ready signal with priority action

Session closer — saves context before compact. Handoff file, memory updates, lesson extraction, reflexion

Scan existing project across 4 dimensions: Infrastructure, Security, Quality, Harness. Returns scored gaps ordered by severity

12Q quantified code review — 4-axis scoring (Security/Stability/Robustness/Operability), severity anchors, deployment verdict, factuality gate. Works as standalone prompt in any LLM

13-section AI collaboration audit — analyzes actual work patterns to generate behavioral profile, blind spots, and growth direction

One-shot perspective reset — 1 reframing question + 3 quick checks (scope drift, side effects, better approach) in under 10 lines. Use anytime during work