session-start

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

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

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

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

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

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

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

12 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management. Works with Claude Code, Codex, and Cursor.

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

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