Multi-agent workflow orchestration: 9 commands (fix, turbo-fix, fix-pipeline, tournament, mega-swarm, deep-think, batch-implement, red-blue-review, baryon-mode) + 2 skills (eight-gates, hades).
npx claudepluginhub ancplua/ancplua-claude-plugins --plugin exodiaIF .NET warnings need extermination THEN use this. One-shot Noble Phantasm: snapshots reality (Rider MCP + NuGet MCP), 8 aspects burst at T0, headless/reckless, cross-repo. Full MCP access.
IF implementing multiple similar items THEN use this. Pattern extraction->parallel implement (1 agent per item)->consistency review->verify. Endpoints, tests, migrations, fixes.
IF complex problem needing multi-perspective analysis THEN use this. 5 agents, 3 phases: understand->synthesize->recommend. No implementation. For competing implementations -> tournament.
IF fixing audit findings THEN use this. 7 agents, 4 gated phases: analyze->design->implement->verify. For ad-hoc bugs -> fix. For P0 -> turbo-fix.
IF bug fix needed THEN use this. 4 gated phases, 8 agents (standard) or 16 (maximum). For P0 critical → turbo-fix. From audit findings → fix-pipeline.
IF codebase audit or release readiness check THEN use this. 6-12 agents scan in parallel. Full(12), quick(6), focused(8). Feed findings into fix-pipeline.
IF adversarial security/quality review needed THEN use this. Red team attacks, Blue team defends, Red re-attacks. Scored. Release recommendation. For broad audit -> mega-swarm.
IF multiple valid approaches THEN use this. N agents compete, judge picks winner by penalty scoring. For trade-offs without competition -> deep-think.
IF P0 critical bug THEN use this. 13 agents, 4 phases, maximum parallelism. For P1-P3 → use fix. From audit → fix-pipeline.
IF maximum disciplined orchestration needed THEN use this. 8 progressive gates — each unlocks more capability only if the workflow stays honest, testable, and resumable. Composes mega-swarm (MAP), fix pipeline (EXECUTE), hades (HAKAI).
IF cleanup/elimination needed THEN use this. IF zero suppressions THEN this. IF dead code THEN this. IF duplication THEN this. IF frontend design audit THEN --goggles. Smart-Hades: Smart ID, deletion permit, audit ledger. 4 teammates per phase.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, and 11+ AI coding assistants.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Claude + Google Stitch workflow toolkit with MCP integration (prompt authoring, screen generation, design extraction)