adr
01Command
Create or maintain Architecture Decision Records as agent-readable decision memory.
🦖Curated Cursor AI agent skills, slash commands, MCP configs, subagents & rules for full-stack dev — React 19, Next.js 16, Supabase, Tailwind v4, TypeScript
Command
Create or maintain Architecture Decision Records as agent-readable decision memory.
Command
Answer-engine / AEO & GEO citation-readiness audit — plan only, no edits until approved.
Command
Install mechanically-enforced architecture boundaries that fail CI on spaghetti imports.
Command
App Store / Play listing ASO audit — plan only, no metadata or screenshot edits until approved.
Command
Read-only audit of app-layer auth — route×gate matrix, getSession vs getUser, middleware-as-only-gate.
Command
Backup and disaster-recovery capability audit — plan only, no infra changes until approved.
Command
Drive a partially-executed plan to 100% coverage across the whole repo — enumerate, batch-execute, prove completeness.
Command
Capacitor native-layer security audit — plan only, no config edits until approved.
Command
Audit a codemod or bulk mechanical transform for behavior-preservation — report only.
Command
Create one conventional commit from an already-scoped change; never push.
Command
Close every plan-related deferral, implement the full closure set, and prove the result with fresh tests.
Command
LLM cost guardrails & quota-abuse audit — plan only, no limits added until approved.
Command
Hypothesis-driven debugging with runtime evidence — Sentry, Firecrawl, and Sequential Thinking, not guessing.
Command
Dependency provenance & slopsquatting audit — plan only, no install until approved.
Command
Documentation drift audit + sync plan — no rewrites until approved.
Command
Audit custom lint/ratchet doctrine for content correctness — report only.
Command
Error-handling & observability audit (Sentry + Langfuse) — plan only, no fixes until approved.
Command
Turn raw feedback (reports, Sentry, reviews, QA/audit findings) into deduplicated durable tickets and drive each to production-verified closure.
Command
Fetch a GitHub issue, find the relevant code, implement the fix, verify, and open a PR.
Command
Audit CI/CD gate logic — silent bypass, ratchet gaming, conflicting conditions — report only.
Command
Drive the whole repository to a verified-green baseline — typecheck, lint, tests, build — with authorized fixing of pre-existing debt.
Command
Relentless one-question-at-a-time interview to sharpen a plan or design before any code is written.
Command
Compact the current conversation into a handoff document for a fresh agent session.
Command
Inventory parked work into one living BACKLOG.md — regenerate and diff, do not implement.