Building agents

38,263 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

hitl-protocol

2905

rotorstar/hitl-protocol

Skill Claude CodeCodex

HITL Protocol — the open standard for human decisions in autonomous agent workflows. When a website or API needs human input, it returns HTTP 202 with a review URL. Autonomous agents like OpenClaw, Claude, Codex, or Goose forward the URL, poll for the structured result, and continue. Use this skill to make any website…

not rated 11 2mo ago B 163 tokens original Apache-2.0

skill-creator

2906

Ontheia/ontheia

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 11 yesterday A 64 tokens AGPL-3.0

formio-uag

2907

formio/uag

MCP server Claude CodeCodexCursor +2

One of 2 in server.json

The Universal Agent Gateway (UAG) enables in-process agentic automation using Form.io. Runs locally from the @formio/uag npm package. Needs 15 environment variables to run.

not rated 11 1mo ago A tokens not measured original MIT

mcpli

2908

juanibiapina/mcpli

Skill Claude CodeCodex

CLI tool for interacting with MCP (Model Context Protocol) servers. Use when invoking MCP tools, managing MCP servers, or working with MCP-based APIs. Triggers on "MCP server", "mcpli", "invoke MCP tool", or any MCP server interaction.

not rated 11 1mo ago A 56 tokens

find-skills

2909

termlnk/termlnk

Skill Claude CodeCodex

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

not rated 11 1mo ago A 67 tokens

agent-team

2910

AidenXu-1/agent-team-skill

Skill Codex

Build or maintain project multi-agent collaboration, including team setup, roles, session routing, handoff and protocol repair. Existing departments handle routine development and review through project role and TASK files.

not rated 11 changed 5d ago A 40 tokens original

hebrew-chatbot-builder

2912

squadcodercom/squadcoder

Skill Claude CodeCodex

Build conversational AI chatbots with native Hebrew support, including WhatsApp Business API integration, Telegram bot scaffolding, web chat widgets, Hebrew NLP patterns, and RTL chat UI components. Prevents common Hebrew chatbot mistakes like broken RTL alignment, incorrect gender inflections, and poor tokenization…

not rated 11 2mo ago A 212 tokens original MIT

manage-mcp-servers

2913

AIWerk/openclaw-mcp-bridge

Skill Claude CodeCodex

Add, remove, list, or manage MCP servers in the OpenClaw MCP bridge. Use when installing new servers, removing existing ones, listing available/installed servers, checking server status, or troubleshooting MCP connection issues.

not rated 11 1mo ago A 50 tokens original MIT

elliot marketplace

2914

EliBarak12/Elliot

Plugin Claude Code

Lists 2 plugins

Turn any API or database into agent-ready MCP tools. The Elliot marketplace ships the platform plugin (10 skills + MCP server + connector templates).

not rated 11 15d ago A tokens not measured original MIT

faq_usage

2915

Arenukvern/skill_steward

Cursor rule Cursor

Q: What is DESIGNFAQ.mdx for? A: Explains why Guild repo decisions were made (meta-layer charter, skills vs plugins, ADRs, validation). Use when changing architecture, inclusion criteria, or documenting rationale. Path: docs/DESIGNFAQ.mdx.

not rated 11 1mo ago A 607 tokens original MIT

harbor-cli

2916

harbor-framework/skills

Skill Claude CodeCodex needs its repo

Harbor CLI command reference and usage patterns. Covers harbor run, harbor jobs, harbor trials, harbor datasets, harbor adapters, harbor tasks, harbor view, harbor sweeps, harbor traces, harbor cache, and harbor admin commands. Use this skill whenever running Harbor evaluations, managing datasets, viewing results…

not rated 11 4mo ago A 96 tokens original Apache-2.0

SUNWOONGKYU/claude-codex-3tier-team

Skill Claude CodeCodex

A three-level work team that combines Claude Code and Codex, two AI coding assistants, to divide tasks among coordinators and smaller helper agents.

not rated 11 changed yesterday A 222 tokens

mcp-context-brief

2919

lucab85/Claude-Code-Bootcamp

Skill Claude CodeCodex

Prepare a one-page context brief for an MCP-connected tool (Jira / Slack / GitHub / Drive) before invoking it, so the agent acts on a focused slice instead of slurping the whole workspace.

not rated 11 3mo ago A 49 tokens

skill-monitor

2920

Luxuzhou/skill-monitor-plugin

Skill Claude Code

A management tool for installed Claude Code skills, which are reusable instructions that extend an AI coding assistant. It checks their security, cost, conflicts, usage, versions, and capability groupings.

not rated 11 5mo ago A 153 tokens original MIT

skill-madness

2921

ivy00johns/Skill-Madness

Plugin Claude Code

Bundles 80 skills · 11,599 tokens together

Contract-first multi-agent orchestrator with 74 skills: a 14-phase orchestrator that authors machine-readable contracts before code, dispatches 10 role agents in parallel with exclusive file ownership, and blocks the merge on a structured QA report. Plus meta-skills, git conventions, and cross-cutting workflow tools…

not rated 11 changed 7d ago A tokens not measured original MIT

claude-code-optimizer

2922

ronchestermusic/claude-code-optimizer

Skill Claude CodeCodex

Stackshift — Claude Code Optimizer. Periodic audit of a user's Claude Code setup. Confirms use case and tech level, inspects installed plugins/skills/MCP servers/marketplaces (flags broken ones), researches new tools from high-signal sources, checks overlap against native Claude Code features, and outputs a dated PDF…

not rated 11 5mo ago D 141 tokens original MIT

mcp

2923

quinnjr/google-mcp

Cursor rule Cursor

Model Context Protocol (MCP) server best practices.

not rated 11 11d ago A 0 tokens original MIT

skill-creator

2924

hAcKlyc/openmino

Skill Claude Code

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 11 5mo ago A 63 tokens

pinchwork

2925

anneschuth/pinchwork

MCP server Claude CodeCodexCursor +2

One of 2 in server.json

Agent-to-agent task marketplace. Runs locally from the pinchwork Python package. Needs 1 environment variable to run.

not rated 11 2mo ago A tokens not measured original MIT archived

terminal-mcp

2928

mkpvishnu/terminal-mcp

MCP server Claude CodeCodexCursor +2

MCP server for interactive terminal sessions (SSH, REPLs, database CLIs). Runs locally from the terminal-mcp Python package. Needs 2 environment variables to run.

not rated 11 29d ago A tokens not measured original MIT

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: