Building agents

38,215 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.

agent-skills-mcp

1897

DiscreteTom/agent-skills-mcp

MCP server Claude CodeCodexCursor +2

Load Agent Skills for your agents. Runs locally from the agent-skills-mcp Python package.

not rated 31 7mo ago A tokens not measured original MIT archived

reliable-tool-context

1898

lourencomaciel/sift-gateway

Skill Claude CodeCodex

Build reliable tool context from command output using artifacts and compact reproducible code queries.

not rated 31 1mo ago A SkillSpector: pass 21 tokens original MIT

mcp-remote

1899

alejandro-ao/mcp-streamable-http

MCP server Claude CodeCodexCursor +2

Remote MCP Protocol. Runs locally from the mcp-remote Python package.

not rated 31 1y ago A tokens not measured

agentchat

1900

agentchatme/agentchat-hermes

Skill Claude CodeCodex

How to operate on AgentChat — peer-to-peer messaging for agents. Read before sending, replying, or deciding to stay silent. Covers reply/silence judgment, cold-DM rules, inbox triage, proactive outreach, group etiquette, error codes, account states.

not rated 31 22d ago A SkillSpector: pass 57 tokens original MIT

delegate-to-deepseek

1901

PsChina/deepseek-as-subagent

Skill Claude CodeCodex

Instructions for delegating suitable coding and repetitive tasks to DeepSeek while the main agent remains responsible for review and verification.

not rated 31 +1 16d ago A SkillSpector: pass 125 tokens original MIT

sequential-thinking

1903

laurigates/foundryvtt-mcp

MCP server Claude CodeCodexCursor +2

One of 7 in .mcp.json

Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.

not rated 31 2d ago A tokens not measured original MIT

notebooklm-mcp-server

1904

moodRobotics/notebooklm-mcp-server

MCP server Claude CodeCodexCursor +2

Node.js Model Context Protocol server for Google NotebookLM. Runs locally from the notebooklm-mcp-server npm package.

not rated 31 +2 23d ago A tokens not measured original MIT

mcp-server

1905

lanyijianke/thinking_models_mcp

MCP server Claude CodeCodexCursor +2

A Model Context Protocol (MCP) server for thinking models. Runs locally from the @thinking-models/mcp-server npm package.

not rated 31 1y ago A tokens not measured

gemini-mcp-server

1906

InfolabAI/gemini-cli-mcp

MCP server Claude CodeCodexCursor +2

MCP server "gemini-mcp-server" as configured in InfolabAI/gemini-cli-mcp. Runs locally from the gemini-mcp-server Python package.

not rated 30 1y ago A tokens not measured original MIT

context9

1908

Prism-Shadow/context9

MCP server Claude CodeCodexCursor +2

MCP server "context9" as configured in Prism-Shadow/context9. Runs locally from the Context9 Python package.

not rated 30 7mo ago A tokens not measured original Apache-2.0

novyx-mcp

1909

novyxlabs/novyx-mcp

MCP server Claude CodeCodexCursor +2

MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows. Local SQLite memory works zero-config; hosted governance and approvals use Novyx Cloud. Runs locally from the novyx-mcp Python package.

not rated 30 2mo ago A tokens not measured original MIT

orchestrate

1911

codecast-sh/codecast

Skill Claude CodeCodex

Drive a plan to completion by orchestrating implementer, reviewer, and critic agents across waves of parallel work. Use when the user says "orchestrate", "implement this plan", "execute plan", "drive this", or approves a plan for execution.

not rated 30 today A SkillSpector: pass 56 tokens original MIT

agent-skills-system

1913

johnvouros/skillmaxxing

Skill Claude CodeCodex

Route and operate software, product, research, and agent tasks through one phase-appropriate execution mode. Use when choosing how an agent should approach a task, resolving speed-versus-quality tradeoffs, planning mode transitions, designing agent workflows, or improving an agent harness. Do not use for a routine…

not rated 30 1mo ago A 76 tokens original MIT

skills-manager

1914

EfanWang/skills-manager

Skill Codex

List, check, update, install, delete, and claim installed skills in the current sibling skills directory for Claude Code, Cursor, or Codex CLI. Use when the user asks what skills they have, which skills are outdated, to update or refresh skills, install a GitHub skill, remove a skill, or trace a skill's freshness…

not rated 30 3mo ago A 77 tokens original MIT

agent-workflow-kit

1915

crisxuan/agent-workflow-kit

Skill Codex

Evaluate whether and how to add AI-assisted development workflow rules to a new or existing software project. Use when asked to onboard AI agents into a repo, create or update AGENTS.md, choose a workflow level, decide whether to use a spec layer such as OpenSpec or Spec Kit, decide whether to use agent discipline…

not rated 30 3mo ago A 107 tokens

codagent

1916

Codagent-AI/agent-skills

Plugin Claude Code

Bundles 26 skills · 1,605 tokens together

A curated set of skills for each stage of development — propose, spec, design, plan, implement, ship.

not rated 30 yesterday A tokens not measured copy · 88% MIT

triggerdotdev/skills

Skill Claude CodeCodex

Advanced and operational chat.agent capabilities for Trigger.dev, loaded on demand. Load this when working on the raw Sessions primitive (sessions / SessionHandle), a custom chat transport or the realtime wire protocol, durable sub-agents (AgentChat, chat.stream.writer), human-in-the-loop, steering, actions…

not rated 30 13d ago A 154 tokens

anam-mcp

1918

anam-org/anam-mcp

MCP server Claude CodeCodexCursor +2

Official Anam AI MCP server for managing AI personas. Runs locally from the anam-mcp Python package.

not rated 30 1mo ago A tokens not measured original MIT

Krastanov/JuliaLLMAgentSkills

Skill Codex

Create and audit durable agent-facing repository documentation. Use a temporary V-model only when interviewing a developer before code exists to turn a rough project prompt into a design independent agents can implement, or during a holistic codebase review to compare implementation with intended goals and expose…

not rated 30 1mo ago A SkillSpector: pass 89 tokens original Unlicense

bloomery

1920

mgratzer/bloomery

Skill Claude Code

Interactive tutorial that guides engineers through building their own coding agent (agentic loop) from scratch using raw HTTP calls to an LLM API. Supports Gemini, OpenAI (and compatible endpoints), and Anthropic. Supports TypeScript, Python, Go, and Ruby. Detects progress automatically. Use when someone says "build…

not rated 30 6mo ago C 81 tokens 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: