Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,421 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Offload large text (docs, logs, transcripts, notes, research dumps) into OCR-certified page images and recall them at up to 2.8x fewer tokens by reading the PNG instead of the raw text. Use when context is filling up with reference material, when the user says "pack this", "microfiche", "offload context", or before…
Skill Claude CodeCodex
Inspect and control the local LLM server(s) via llama-launcher — list profiles, see what's running, switch models, tail logs. Use when the user wants to know what model is loaded, change models, start/stop or restart the server, or troubleshoot a stuck load.
MCP server Claude CodeCodexCursor +2
MCP server "mnesio" as configured in mnesio/mnesio. Launched with mnesio-mcp. Needs 2 environment variables to run.
Skill Claude CodeCodex
Salva Runtime is a discovery runtime for agents, CLI tools, and services. Use it when you need structured retrieval, route selection, evidence, and persistence.
Skill Claude CodeCodex
A coordination skill for routing complex requests across research, discussion, review, and other roles or providers. A provider is the service that performs a delegated task.
Skill Claude CodeCodex
Orchestrate bounded agent-to-agent vault sessions via AgentVault MCP tools.
Skill Claude CodeCodex
A guide for creating and maintaining skills for Lfcode, including where to store them and which files each skill needs.
Skill Claude CodeCodex
A coordination workflow for managing software tasks across planning, worker agents, testing, auditing, approvals, and configuration governance. It stores task state in structured folders and records each state change in a log.
MCP server Claude CodeCodexCursor +2
MCP server "z39" as configured in alejandroqh/z39. Launched with /home/aquintanar/workspace/z39/target/release/z39 mcp. Needs 2 environment variables to run.
Skill Claude CodeCodex
This skill should be used for ANY kdag, job definition, or pipeline question — including "create a kdag job", "run a kdag job", "build a pipeline", "create a job definition", "new kdag definition", "how does the executor work", "step timeout", "mapreduce behavior", "synthesis", "batchdelayms", "retry semantics", "job…
Skill Claude CodeCodex
Analyze stocks, generate trading signals, manage risk, and execute paper trades using the OpenQuant MCP server.
Skill Claude CodeCodex
Use when working in a repo that uses mflow, coordinating multiple AI agents/worktrees, setting up mflow sync, installing mflow MCP in Codex/Claude Code/Cursor/opencode, or before git operations where synced file changes may affect commits. Applies to CLI, MCP, room secrets, pause/resume, locks, status checks, and safe…
Skill Claude CodeCodex
Use when the user asks for insights, key findings, recommendations, or actionable takeaways. Trigger on: insights, findings, patterns, recommendations, actionable. Do NOT use for raw data analysis, statistical computation, or chart generation.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "metals", hosted remotely at localhost, as configured in luksow/madrileno.
17557295964-ops/project-brain-bridge
Skill Codex
Use when creating, deploying, diagnosing, or operating a reusable ChatGPT-as-project-brain bridge for any local Codex project: initialize .ai-bridge state, expose read-only project evidence, expose a narrow stage-plan write connector, avoid stale/freeform connector schemas, and run the ChatGPT plan -> Codex execution…
Skill Codex
Audit long, complex, and potentially inconsistent PM taskbooks and compile them into one self-contained, semantically validated Product Brief with a requirement ledger, WP dependency graph, budgets, absolute schedule, gates, tests, experiment evidence, risks, recovery, and stop conditions. Use for long-horizon or…
responsible-genai-hackweek/nicer-nisar
Skill Claude CodeCodex
Fit, evaluate, and freeze a Mores Creek snow-depth-change model — matched InSAR/LiDAR pair selection, target aggregation, the holdout scheme that is actually honest, the feature ablation, the challenger rule, and what must go in the model card before an id is pinned. Use when adding a training pair, refitting after a…
Skill Claude CodeCodex
Use when working with MQL4, MQL5, MetaTrader 4/5, Expert Advisors (EAs), custom indicators, or scripts. Covers OrderSend, iMACD, iRSI, CopyBuffer, trade operations, indicator buffers, and MQL4-to-MQL5 migration. Triggers on any .mq4/.mq5/.mqh file or MetaEditor compilation.
Skill Claude CodeCodex
REQUIRED for any task involving agent identity, capability credentials, or access-gated Skills on Pharos. This skill is the entry point for the Ligis suite — it issues portable agent IDs (ERC-721 NFTs), signs and verifies EIP-712 capability credentials (KYC, commerce permissions, RWA eligibility), rotates agent keys…
ciscoriordan/storescreens-skill
Skill Claude CodeCodex
Set up and run storescreens-cli to automate App Store screenshot capture for iOS apps: render captioned/framed App Store-ready screenshots with device bezels, markdown captions, and panoramic backgrounds; upload screenshots + per-locale metadata (name, subtitle, description, keywords, what's new, promotional text) to…
Skill Claude CodeCodex
Use when a task reveals a recurring, multi-step capability worth saving for future sessions — writing a new Norma skill, or improving an existing self-authored one, via skillwrite.
Skill Codex
Always-on Chef routing skill that runs at the start of any task to find the best specialist skills, choose the smallest useful set, order them, and re-evaluate when the task changes.
Skill Claude CodeCodex
Skill "VisioIntegration" from CloudDaddyZA/VisioIntegration, covering azure visio mcp — skill definition, metadata, when to use, trigger phrases and capabilities.
Skill Claude CodeCodex
Use when coordinating with other AI agents via backchannel (bch) — checking the inbox at task start, sending DMs or channel messages to peer agents, requesting reviews, or reacting to incoming messages. Trigger phrases include "message the other agent", "check your inbox", "tell codex/claude/gemini to…", or any task…
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: