Working inside the exocortex vault (/git/exocortex) — garden passes, writing or editing vault notes, checkpointing decisions. Load whenever touching vault/ markdown; encodes the golden rules, note shape, the gardening routine, and pointers to the standing case law so rulings aren't re-derived.
Render a large paste, clipboard, or file into a dense PNG image via pxpipe and load it into context as an image, so bulky content costs vision tokens (3x denser) instead of text tokens — with a verbatim appendix of any byte-exact tokens. Use when a message starts with "pipethis:", or the user says "paste as image"…
Run the weekly review of the big-brain second brain: triage the inbox, walk active projects, reschedule or drop overdue tasks, check vault health, and write a review summary. Use when the user types /weekly, or asks for a "weekly review", "review my projects", "clean up my brain", "triage my inbox".
Publish posts on Threads (threads.com) for the user. Use whenever the user wants to write, draft, or publish a Threads post or thread, with or without an attached image, including "post this", "write a post using this image", or a pasted block of raw post text.
Generate an AI image from a text prompt and load it into context, in one step. Routes to FLUX / SDXL / Ideogram / Recraft (Replicate) or gpt-image-2 (OpenAI). Use when a message starts with "imagethis:", or the user says "generate an image", "make a picture/logo of…", or "draw…".
Use when working from the Alcove hub workspace or routing personal knowledge, pins, projects, prompts, tasks, mounts, connectors, or managed KB operations.
Use when Codex must directly operate or troubleshoot the installed grok-plugin-codex MCP capability surface, including CLI/model checks, literal prompt runs or continuations, session inspection or export, and known background-job control. Do not use for bounded repository delegation, implementation, review…
A data-visualisation MCP server for creating charts, reports, tables, KPI cards, and dashboards from data. It also parses CSV files and provides data checks, formatting, outlier detection, and normalisation.
A machine-learning toolkit covering common methods for classification, prediction, grouping, dimensionality reduction, data preparation, and model evaluation. Classification predicts categories, regression predicts numbers, and clustering groups similar records.
A collection of 30 tools for statistical analysis, including tests, regression models, and time-series methods. It is intended for examining data and checking whether observed patterns are meaningful.
Use when Claude Science must obtain an independent OpenAI Codex review, second opinion, reproducibility check, statistical or figure audit, debugging handoff, or delegated implementation.
Create, revise, and publish implementation, project, architecture, migration, and roadmap plans to post-plan.boyan.live with a backlink to the originating Codex task. Use whenever the user asks Codex to make or update a plan, outline implementation, define phases or milestones, propose an architecture or migration…
Answer a question from PRIMARY academic/scientific databases rather than web search. Two families: (a) ALL-DISCIPLINE literature search — arXiv (incl. stats, maths, CS, physics, economics, quant-finance) and OpenAlex (every field, real DOIs + citation counts); (b) domain databases — PubMed, UniProt, PDB, ChEMBL…
Complete Indeed job postings toolkit via RolesAPI.com. Search Indeed job postings by keyword and location, fetch full role details, look up salary for a job posting, and get descriptions, company info, and benefits across 60+ country editions.
Design world-class SaaS landing pages grounded in real references from saaspo.com (via the saaspo MCP). Use when the user asks to design or build a landing page, marketing site, or any page for a product — especially when they provide copy and want it designed "like a senior designer", or mention saaspo, design…
Forensic retrospective on how work actually FLOWED through the kanban-pro board — reconstruct each card's timeline from the change-log (lane moves, bounces, forced moves, attention, dispatch loops, rounds, cycle time), attribute it to the model that really served it (model-pro requested-vs-resolved, context overflow…
Consolidate the brain — refresh the index, review sessions since the last reflection, distill durable facts into memory files, compact the store, propose skills, commit. Use when asked to "reflect" or "consolidate memory"; also invoked headless by the nightly job.
Verify football match events and result readiness with Proofline evidence, signed x402 proof packets, and the latest Injective testnet settlement commitment. Use when an agent must check a score, event, final result, paid proof, or settlement gate without confusing scheduled, delayed, replay, and live data or…
Search, read, cite, create, append, and—only under explicitly authorized Full management—replace note content, edit frontmatter, move or rename notes, and send notes to Obsidian trash through bounded Obsidian Bridge MCP tools. Use for vault research, note diagnostics, guarded create/append, or managed Markdown…
Use CupOracle to answer FIFA World Cup 2026 questions (fixtures, live scores, consensus odds, knockout bracket) and to buy a vetted, CLV-audited edge that the agent pays for ITSELF via x402 on Injective — under a spend cap, always citing the on-chain receipt. Invoke when the user asks about a World Cup match, "who's…
★not rated 0 yesterdayA98 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: