Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 267,565 indexed, measured the same four ways as everything else here.
Plan and execute complex work with parallel CLI agent-harness workers in git worktrees. Use for task decomposition, tmux worker spawning, deterministic loops, integration, verification, changelogs, and cleanup.
Run a full 5-phase agent-readiness audit on the current repository — scan, discover apps, evaluate 82 criteria via parallel subagents, validate, and generate report + dashboard with persistent score history.
Terraform and Infrastructure as Code optimization guidelines from Terramate. This skill should be used when writing, reviewing, or refactoring Terraform/OpenTofu code to ensure optimal patterns for security, maintainability, and reliability. Triggers on tasks involving Terraform modules, infrastructure provisioning…
Build custom Panel components using JSComponent (vanilla JS, web components), ReactComponent (React/JSX), AnyWidgetComponent (AnyWidget spec for cross-platform), or MaterialUIComponent (Material UI themed). Use when wrapping JS libraries, creating interactive widgets, or building themed components. Includes decision…
Generic smart-contract interaction for Capminal — read (call), batch-read (multicall) and write (send tx) ANY contract on Base or Robinhood chain by passing a flexible ABI, contract address, function name and parameters, using your CAP API key.
Use the OpenFusion fusion tool to get a consolidated council-of-models answer for a hard, high-stakes decision — code review/QA after implementing, debug root-cause from a dossier you gathered, research consolidation, architecture/plan review, or a second opinion. Do the groundwork yourself first (read, code, search…
A response-adjustment rule that changes explanation depth and format only when a specific approval-gate command is requested. It uses evidence from the current conversation to account for the reader’s role and familiarity.
Use when the user wants a real data analysis on a dataset — finding what drives a metric, testing whether a difference is real, building a predictive model, reducing many variables to a few, or interpreting what numbers mean for the business. Trigger phrases include "analyze this data", "what drives X", "is this…
Integrate Grow by Meshulam payment gateway into Israeli applications -- covers payment pages (iframe/redirect/SDK), tokenization, recurring billing, payment links, refunds, invoices, webhooks, and 3DS authentication via the Grow Light API. Use when user asks to accept payments via Grow or Meshulam, set up "slikat…
Use when a human wants to share a logged-in tab from the isolated OpenClaw browser so the agent can work through LobsterLink in that authenticated session. Triggers include requests to share a tab, give a LobsterLink peer/share ID, use a logged-in tab, or host/stop hosting a tab through LobsterLink. Skip…
A workflow for investigating database crashes from core dump files, which are saved snapshots of a program's memory after a crash. It uses GDB, a debugger, to inspect threads and call stacks.
Search and retrieve AI prompts from prompts.chat, the social platform for AI prompts. Runs locally from the @fkadev/prompts.chat-mcp npm package. Needs 2 environment variables to run.
Estonian e-arveldaja (RIK e-Financials) accounting — invoices, bank import, reports. Runs locally from the e-arveldaja-mcp npm package. Needs 7 environment variables to run.
★not rated 34 14d agoA
tokens not measured
originalApache-2.0
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: