findtorontoevents_antigravity.ca

The June-2026 EDITION of the money-ready program — executes the self-correcting MASTER LOOP (docs/MONEY_READY_MASTER_LOOP_2026-06.md) that converges toward 2-3 profitable asset classes even from 0/9. Use when the user says "/money-maker-ready-June112026edition", "run the master loop", "weekly money-ready cycle", or at the monthly edition review. Inherits data sources + hard rules from /money-maker-ready and /money-maker-readyv2. Aliases - mmr-june2026, master-loop, money-loop.

The July-2026 EDITION of the money-ready program. SUPERSEDES money-maker-ready-June112026edition. The June edition's structural bet (converge to 2-3 profitable asset classes by mining the crypto ledger) was EXHAUSTED and found no net-of-cost alpha; the ONE structural change this edition makes is to REORIENT the primary money-making track from crypto-ledger directional-edge-mining (measurement-broken, dead) to ETF TACTICAL ASSET ALLOCATION (the one validated find), while treating the crypto ledger as fix-before-mine. Use when the user says "/money-maker-ready-July112026edition", "run the master loop", "weekly money-ready cycle", or at the monthly edition review. Inherits data sources + hard rules from /money-maker-ready and /money-maker-readyv2. Aliases - mmr-july2026, master-loop, money-loop.

The June-2026 EDITION of the money-ready program — executes the self-correcting MASTER LOOP (docs/MONEY_READY_MASTER_LOOP_2026-06.md) that converges toward 2-3 profitable asset classes even from 0/9. Use when the user says "/money-maker-ready-June112026edition", "run the master loop", "weekly money-ready cycle", or at the monthly edition review. Inherits data sources + hard rules from /money-maker-ready and /money-maker-readyv2. Aliases - mmr-june2026, master-loop, money-loop.

Use when investigating the /audit dashboard for hidden edges, debugging why no per-asset-class picks are profitable, checking picks-now.html forward-tested performance, ai-tournament.html model leaderboard staleness, portfolio_history.html staleness, ai_leaderboard.html missing models, pick_funnel.html accuracy, research_index.html coverage, and "high-conviction" / "smart picks" / "best score" / "proven only" filter logic. Also for "why is the forward WR only 21%?" and "which filter combination surfaces a real edge?"

One-shot second opinions / parallel drafting via the LOCAL AI fleet — vLLM (:8000 Qwen2.5-14B), Ollama (:11434, 23 models incl. llama3.3:70b + deepseek-r1:32b), LiteLLM proxy (:4000, 15 cloud groups). Use when the user says "/consult-local", "ask the local fleet", "local second opinion", or when a quick sanity-check/draft shouldn't burn cloud quota. Zero-key, low-latency.

Look up database schema, table structure, or connection details for any of the 9 MySQL databases (ejaguiar1_stocks, ejaguiar1_backtests, ejaguiar1_sportsbet, ejaguiar1_favcreators, ejaguiar1_events, ejaguiar1_memecoin, ejaguiar1_tvmoviestrailers, ejaguiar1_news, ejaguiar1_deals). Triggers — `/db-schema`, "what tables are in X db", "schema for table Y", "how is the DB structured", "where is the schema", "DB connection details", "regenerate schema doc". Aliases — dbschema, db-schema, schema-lookup, db-lookup.

Ultimate statistical edge audit per asset class. Produces proven, real-money-grade filters for CRYPTO/EQUITY/COMMODITY/ETF/FOREX/BOND so that a quant or hedge fund manager would find the edge trustworthy. Extends money-maker-ready v1.1 with stronger success criteria, autonomous execution rules, and a weekly filter output. Use when the user says "/money-maker-readyv2", "prove the edge", "real money filters", or "ultimate statistical edge". Aliases - money-maker-readyv2, ultimate-edge, prove-edge.

Use when user wants to audit findtorontoevents.ca/audit (+ /audit/hyrotrader, ejaguiar1_stocks, ejaguiar1_backtests) for production-grade real-money readiness. Per-asset-class statistical-edge hunt with cross-source correlation, external-data integration suggestions, dashboard UI/filter audit, and ranked Best-Possible-Action recommendations. Triggers — `/money-maker-ready`, "is /audit ready for real money?", "find edge per asset class", "money maker audit", "edge hunt", "what's our best statistical edge?", "should we go live with X asset class?". Aliases — mmready, money-maker, edge-hunt, real-money-audit, edge-by-class.

Bridge between Claude's file-based memory system and the Obsidian vault. Reads, writes, and searches project knowledge stored in obsidian-notes/ as the long-form counterpart to the terse entries in ~/.claude/projects/.../memory/. Use when the user asks to "save to Obsidian", "look up in vault", "update the vault", or when a decision/finding deserves richer context than a memory entry allows. Aliases: obsidian-memory, vault-memory, save-to-vault.

Consult MiniMax M3 via Ollama Cloud (`minimax-m3:cloud`) for peer review and second-opinion analysis. Use when the user says `/consult-minimax`, "ask minimax", "minimax second opinion", or wants MiniMax's beautiful structured analysis on a finding, plan, or strategy claim.

Use when handed a SET of files to review/audit and you want to avoid reviewing the same content twice — finds byte-identical and near-identical (reformatted/lightly-edited) files so you review one representative per cluster. Triggers — "/dedup-files", "are these files duplicates", "check file hashes for dups", "which of these are the same", "dedup before review", "find duplicate reports/docs". Aliases — dedup, dup-check, dedup-review, file-dups.

Resolve a Windows path (or a whole pasted list of them) to the equivalent Linux file in this repo, verifying each exists on disk. Handles E:\findtorontoevents_antigravity.ca\... -> /home/eaguiar2015/findtorontoevents_antigravity.ca/..., maps .claude/.qwen worktree copies that only exist on Windows back to the main-tree file, fuzzy-matches by basename, and flags external paths (Program Files, AppData, other drives) that have no repo equivalent. Triggers - "/win-to-linux-path", "what's the linux path for E:\...", "convert these windows paths", "find the equivalent linux file(s)". Aliases - win2linux, winpath, w2l, windows-path.

Multi-model fan-out across Cloudflare Workers AI. Lists all available text-gen models (Llama 3.3 70B, GPT-OSS 120B, Nemotron 3 120B, Qwen 3, GLM 4.7, Mistral, Phi, Gemma, etc.) and fans a single prompt to N of them in parallel, then aggregates replies. Use when the user says "/consult-cloudflare-models", "/consult-cloudflaremodels", "ask cloudflare models", "cf fan-out", or wants triangulation across multiple CF-hosted models. Subcommands - list, search, run, fan-out.

Consult any text-generation model on Cloudflare Workers AI (37+ models from Meta, OpenAI, Qwen, Mistral, Google, NVIDIA, Z-AI, IBM, DeepSeek, Moonshot). Use when the user says "/consult-cloudflare", "/consult-cf", "ask cloudflare", "cf workers ai", or names a CF-hosted model (llama-3.3-70b, gpt-oss-120b, nemotron-3-120b, qwen3-30b, glm-4.7-flash, etc.). Subcommands - list, run, models, search.

Push the current session's transcript summary + open PRs + outstanding action items to the cross-PC protocol gateway so peer agents (Cursor, Hermes/WSL, Freebuff, Claude on laptop, etc.) can see what this instance just did. Then poll the broadcast + DM queues for any messages from those peers and surface them to the operator. Optionally revise + recommit work based on peer insights. Triggers — `/dropchat-multipc`, "drop chat to multi-pc", "broadcast session summary", "DROPCHATTOMULTIPC", "share with peers", "check peer inbox + sync". Aliases — dropchat, dctm, multipc-sync, peer-sync.

Fan a prompt to N AIs through the local LiteLLM rotating proxy (http://localhost:4000) via tools/freellm.py. Three modes — team (CombineTeam, ask N AIs the same question), debate (DebateTeam, multi-round structured debate), file (FileTeam, divide files across AIs). Outputs .MD files. Use when the user says "/consult-PROXY", "proxy swarm", "ask the proxy team", "debate via proxy", or wants a multi-AI second opinion routed through the local proxy instead of per-provider CLIs.

Distributed parallel implementation + review + test swarm across the whole free/paid AI key pool and cross-PC peers. Probes peers/providers for signs of life, assigns each action item (one file) to a live working model, has it implement + place the file, validates it, then runs a code-swarm review → testing plan → swarm-executed tests. Use when the user says "/ParallelSwarm", "parallel swarm", "distribute these implementations", "code swarm across AIs", "build these N files in parallel fast", or wants many action items implemented + reviewed + tested concurrently. Aliases - parallel-swarm, pswarm, distributed-swarm, code-swarm-distributed.

Check messages on the cross-PC protocol gateway — poll your peer inbox, drain the broadcast queue (peer_id=all), and tail the durable JSONL event log. Use when the user says "check cross-pc msgs", "any peer messages", "/cross-pc-checkmsg", "what's in the bus", or wants to inspect inbound traffic. Aliases - xpc-check, cross-pc-poll, checkmsg.

Quick health check of the local cross-PC protocol gateway — confirms /health, lists registered peers, queue depths, pending ACKs, LAN-discovered peers. Use when the user says "is the gateway up", "/cross-pc-health", "cross-pc status", or you need a pre-flight before sending. Aliases - xpc-health, cross-pc-status.

Send a message over the cross-PC protocol (WebSocket primary, HTTP fallback). Use when the user says "send a cross-pc message", "broadcast to peers", "DM peer X", "/cross-pc-sendmsg", or wants to publish an envelope to the local protocol gateway. Aliases - xpc-send, cross-pc-send, sendmsg.

Catalog of every available peer-review / multi-AI consultation mechanism in this repo. Use when picking the right tool for swarm-reviewing PRs, validating findings, or fan-out brainstorming. Pros/cons + cost/latency/auth for each.

Content-dedup a list of markdown paths (handles many worktree copies of the same report). Returns the canonical (shortest-path) file per unique content hash so a reviewer doesn't read the same .md N times.

Content-dedup markdown paths before batch review — returns canonical (shortest-path) files so the same report is never read twice. Handles Windows E:\ paths, worktree copies, and stdin/file lists.

Push session summary to cross-PC gateway with peer ID "ELTONSLAPTOP_QWEN". Triggers — /dropchat-multipc, "drop chat to multi-pc", "broadcast session summary". Aliases — dropchat, dctm, multipc-sync, peer-sync.

Local LiteLLM proxy on http://localhost:4000 that fronts 14+ LLM providers (NVIDIA NIM, Groq, Cerebras, Together, Fireworks, GitHub Models, Gemini, DeepInfra, Nous, Mistral, AIMLAPI, Hypereal, Cloudflare, optional local vLLM) behind one OpenAI-compatible endpoint with auto-rotation on rate-limit / 429 / 401 failures. Use when the user says "/litellm-proxy", "start the rotating proxy", "set up routing for Roo/Kilo", or wants Roo / Kilo / any openai-SDK client to transparently fall through a key pool when one provider hits limits. Subcommands - start, stop, status, test.

Unified multi-provider AI consult tool. Wraps 11 LLM providers (NVIDIA NIM, Groq, Cerebras, Together, Fireworks, GitHub Models, HuggingFace, Gemini API, Cloudflare Workers AI, DeepInfra, Nous Research Portal) behind one CLI so multi-AI fan-outs and single-provider consults share one well-tested code path. Reads keys from ~/dbpasses.txt (gitignored). Use when the user says "/consult-multi", "fan to N peers", "multi-provider consult", or wants triangulation across many providers in one call. Subcommands - list, run (--provider), fan-out (--fanout).

Query multiple AI models via NVIDIA NIM API for second opinions on trading data, code, or analysis. Use when the user says "/consult-nvidiamodels", "ask nvidia models", "nim second opinion", or wants peer model consensus on quantitative/analytical questions.

Multi-model fan-out across NVIDIA Integrate API (NIM). Lists all available text-gen models (DeepSeek v4 Pro, MiniMax, Kimi-K2.6, Nemotron, GPT-OSS, Z-AI GLM, Qwen, Llama-4, Mistral, etc.) and fans a single prompt to N of them in parallel, then aggregates replies. Use when the user says "/consult-nvidia-models", "/consult-nvidiamodels", "ask nvidia models", "nvidia multi-model", "nvidia fan-out", or wants triangulation across multiple NIM-hosted models. Subcommands - list, search, run, fan-out.

Query multiple AI models via Cloudflare Workers AI API for second opinions on trading data, code, or analysis. Use when the user says "/consult-cloudflaremodels", "ask cloudflare models", or wants peer model consensus via Cloudflare's AI gateway.

Consult NVIDIA Integrate API with DeepSeek v4 Pro by default (or override model, e.g. minimaxai/minimax-m2.7). Use when the user says "/CONSULT-NVIDIA-DEEPSEEK", "/consult-nvidia-deepseek", or asks for an NVIDIA-hosted second opinion.

Use when checking for failed GitHub Actions jobs that have no subsequent successful run, or when user wants to find and rerun stale failures. Aliases - fixGHACTIONS, FIXGH, fixjobs