By evgenygurin
Risk-first crypto market research — 16 MCP tools (market data, analytics, catalog + observability), 4 resources + 1 URI template, 2 prompts, Supabase-backed cache, realtime cache invalidation, provenance tracking, and auditable reasoning.
Run composite analytics snapshot (VWAP + support/resistance + volatility) for a symbol.
Smoke-test the plugin — echo + read cryptozavr://venue_health.
Stream OHLCV history across a time window — pages through chunks and returns a SessionExplainer envelope.
Fetch OHLCV candles (open/high/low/close/volume) for a symbol + timeframe.
Multi-tool research collage — ticker + OHLCV (1h, 24 candles) + order book + recent trades for a symbol.
Use when the user asks a crypto-research question that needs multiple tool calls (ticker + OHLCV, comparison, trend analysis, liquidity check). This skill explains the research loop, when to call which tool, and how to structure findings.
Use when you've just received output from a cryptozavr MCP tool (ticker, OHLCV, orderbook, trades) and need to read it correctly. Covers field meanings, staleness flags, reason_codes, and common pitfalls.
Use at the end of a cryptozavr research session (or when the user asks "wrap up" / "what did we do"). Produces a disciplined 3-bullet summary — artifacts produced, decisions made, what's next — so the next session starts warm.
Use when the user brings a declarative trading strategy (StrategySpec payload, a saved strategy id, or a plain-language "review my strategy" request). This skill runs the validate → explain → backtest → compare/stress → save loop against the Phase-2 MCP tools and packages the findings in a Claude-friendly order.
Use when a cryptozavr tool returns degraded/stale data, times out, or reports an upstream failure (KuCoin/CoinGecko). Walks through the L2 infrastructure chain, inspects provider metrics, and pinpoints whether the issue is rate limiting, transport, provider downtime, or cache staleness.
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Risk-first crypto market research plugin for Claude Code, OpenAI Codex, OpenCode, Cursor, and Gemini CLI. 16 MCP tools over KuCoin and CoinGecko with Supabase-backed cache, realtime cache invalidation, observability, provenance tracking, and auditable reasoning.
MCP tools (16)
Market data (5)
get_ticker(venue, symbol, force_refresh) — last / bid / ask / 24h statsget_ohlcv(venue, symbol, timeframe, limit, force_refresh) — OHLCV candles (1m..1w)get_order_book(venue, symbol, depth, force_refresh) — bids / asks / spread_bps; KuCoin depth snaps to {20, 100}get_trades(venue, symbol, limit, force_refresh) — recent trade ticksresolve_symbol(user_input, venue) — fuzzy symbol resolutionAnalytics (4) + history (1)
compute_vwap(...) — VWAP + bars_used + confidenceidentify_support_resistance(...) — swing-pivot S/R + pivots_found + cluster meansvolatility_regime(...) — ATR-based classifier (calm/normal/high/extreme)analyze_snapshot(...) — composite VWAP + S/R + volatility with one OHLCV fetchfetch_ohlcv_history(...) — streaming history with paginator:clipped_to_window guaranteeCatalog (5, structuredContent — no escape)
list_venues, list_symbols(venue), list_trending, list_categories, get_venue_healthPlus echo for smoke.
MCP resources (4 + 1 URI-template)
cryptozavr://venues, cryptozavr://symbols/{venue}, cryptozavr://trending, cryptozavr://categories, cryptozavr://venue_healthMCP prompts (2, cross-client portable)
research_symbol(venue, symbol) — 4-tool parallel research templaterisk_check(venue, symbol) — data-quality pre-decision checkSlash commands (8)
/cryptozavr:ticker, /cryptozavr:ohlcv, /cryptozavr:research, /cryptozavr:resolve, /cryptozavr:trending, /cryptozavr:analyze, /cryptozavr:history, /cryptozavr:healthSubagent
crypto-researcher — multi-step market research specialist (calm, explainable, no advice)Skills (4)
crypto-research — when-to-invoke + tool-selection matrixinterpreting-market-data — field-by-field legend + red flagsvenue-debug — walk the 5-layer L2 chain to pinpoint failurespost-session-reflection — disciplined 3-bullet wrap-up (produced / decided / next)SessionStart hook — prints a plugin-loaded banner with command cheat-sheet and venue health pointer.
Every response carries
reason_codes audit trail (5-handler chain: venue → symbol → cache → provider; plus paginator:clipped_to_window for streamed history)staleness + cache_hit — so you always know if data is freshstructuredContent in the MCP response (no escaped JSON strings)Pick your platform:
Copy .env.example → .env and fill:
SUPABASE_URL — your Supabase project URLSUPABASE_SERVICE_ROLE_KEY — from Dashboard → API Keys → service_roleSUPABASE_DB_URL — PostgreSQL connection string (session pooler, port 5432)The cryptozavr MCP server needs Python 3.12 + uv. Install with:
uv sync --all-extras
data, quality, reasoning.See docs/superpowers/specs/2026-04-21-cryptozavr-mvp-design.md for the full MVP design.
npx claudepluginhub evgenygurin/cryptozavr --plugin cryptozavrIntelligent project memory management for Claude Code using Mem0. Automatically captures and persists decisions, patterns, and context across sessions.
Bridge to Codegen AI agent platform — delegate tasks, monitor agents, review output, debug failures, and manage PRs via cloud agents
Intelligent prompt optimization with R2R semantic search integration. Enriches vague prompts using knowledge base search, codebase analysis, and research-based clarifying questions
Codex-as-Manager autopilot for Claude Code: OpenAI Codex (gpt-5.4/5.5) decomposes goals, reviews diffs, and directs the loop; Claude Code implements. Works with ChatGPT subscription via codex login (no OPENAI_API_KEY required).
DJ techno music library management — 20 MCP dispatchers (6 entity CRUD + 3 provider + 2 compute + sync + 2 admin + 6 UI Prefab Apps) + 27 resources + 6 prompts + 6 handlers. FastMCP v3 bounded-contexts architecture.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.