Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,738 indexed, measured the same four ways as everything else here.
Create new Comis skills, modify and improve existing skills, and validate them against the platform's manifest schema. Use this skill whenever the user wants to create a skill from scratch, turn a workflow into a reusable skill, update or fix an existing skill, understand the skill format, or asks about how skills…
Audit product pages, CSV catalogs, and storefronts for AI shopping readiness (GEO/AEO for commerce) and draft evidence-backed listing fixes. Use when the user asks to audit a product page or catalog for AI readiness, check whether a store is citable by AI assistants, score AI shopping visibility, or optimize product…
Validate individual records or batch files against QubitOn — addresses, tax IDs, bank accounts, phone numbers, emails — and interpret the results correctly. Use when the user asks to "validate X", "check this VAT / GSTIN / EIN / IBAN", "verify this address / bank account / phone", or hands over a spreadsheet/CSV of…
Triage and label Gmail by sender/provider so the inbox shows only what matters, and generate importable Gmail filter rules (sender → label) to auto-categorise future mail. Use this skill whenever the user wants to label, sort, file, organize, tidy, or "triage" their Gmail; clean up or clear the inbox; auto-file…
Be the operator's grounded co-pilot inside the Bridge cockpit (#/primesilo/bridge). Load this when the user is on the Bridge and asks "what am I looking at", "explain this graph", "what did I work on", "ingest these docs", "re-run the last manifest", or any question about the mesh on screen — memory, documents, code…
Scan current or active session transcript, detect vault-relevant items (topic, blocker, correction, decision, error/bug, knowledge-gap, lesson, pattern, skill-usage, entity, person, topic), then WRITE them to the correct vault folder per rules. Use after a work session, when user says scan session, or before ending a…
Design and implement safe, layered agent harnesses and orchestration workflows. Use when the user wants a coding agent, CLI agent, tool-calling assistant, multi-agent runtime, plan/task system, subagent framework, MCP-integrated harness, or Claude Code/Codex-style agent workflow built or refactored.
Run bounded SELECT queries through an Apache Superset SQL Lab connection on Windows. Use when a user wants an Agent to configure a supported Superset instance, test connectivity, inspect tables or columns, execute SELECT queries, export small results, preserve query evidence, or diagnose authentication, permission…
Real-time web search, reasoning, and research through Perplexity's API. Runs locally from the @perplexity-ai/mcp-server npm package. Needs 2 environment variables to run.
★not rated 5 7mo agoA
tokens not measured
originalMIT
A planning guide for deciding when to split work between the main agent and smaller worker agents. It also describes how to define each worker's file boundaries and check its result.
Remember to run Agent Broom, the script-backed process tracking, audit, and cleanup tool. Use before starting another localhost server, before ending a turn that spawned long-running processes, when CPU/memory is high, when disk is low, or when the user says "what is running", "devclean", "orphaned MCP", "cleanup…
Query what the user did on this computer outside the current conversation — which apps, windows, files, and web pages they used, and when (last 48h, read-only). Reach for it whenever off-conversation context would help - resuming interrupted work, resolving vague references like "that doc I was reading" or "the error…
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: