Building agents

38,360 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.

grok-mcp

3625

BrewMyTech/grok-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Grok AI API integration. Runs locally from the grok-mcp npm package.

not rated 7 1y ago A tokens not measured original MIT

outfit

3626

MyceliumInc/Outfit

MCP server Claude CodeCodexCursor +2

Portable, enforced agent personas. One spec - any runtime. Runs locally from the @myceliuminc/outfit npm package.

not rated 7 1mo ago A tokens not measured original MIT

mcp-chain

3627

ruliana/mcp-chain

MCP server Claude CodeCodexCursor +2

An MCP server proxy with to modify and enrich calls to other MCP servers. Runs locally from the mcp-chain Python package.

not rated 7 1y ago A tokens not measured original MIT

lore

3628

andresanemic/lore-plugin

Plugin Claude Code

Bundles 8 skills, 3 hooks · 1,057 tokens together

Local fine-tuning for your own tasks, except the one doing the training is you. A provider-neutral kit that turns scattered project criteria into distilled, invariant Lore — and operates it with seven skills: use-lore, brainstorming-lore, create-area, create-project, create-bot, save-to-lore, transmute-lore.

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

skeletongraph

3629

yashdoke7/skeletongraph

MCP server Claude CodeCodexCursor +2

Token-minimal, constraint-preserving context assembly for AI coding agents. Runs locally from the skeletongraph Python package.

not rated 7 today A tokens not measured original MIT

maintain-agent-plugins

3630

gaelic-ghost/socket

Skill Codex

Create or align agent plugin repositories, install deterministic managed FSX plugin maintenance, and validate or apply the whole plugin set through exactly two aggregate Just commands.

not rated 7 21d ago A 36 tokens original Apache-2.0

ai-skills marketplace

3631

Amey-Thakur/AI-SKILLS

Plugin Claude Code

Plugin marketplace listing 68 plugins: accessibility-skills, ai-coding-tools-skills, ai-memory-rag-skills, api-integration-skills, apis-skills.

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

claude-anatomy

3632

Hainrixz/claude-anatomy

Plugin Claude Code

Bundles 1 skill · 267 tokens together

Te dice qué construir en Claude Code —skill, subagente, hook, servidor MCP, plugin, rutina, una página web, una app, o nada— con el árbol de decisión y el esqueleto de archivos de la pieza elegida.

not rated 7 1mo ago A tokens not measured copy · 86% MIT

WalterSumbon/claude-agent-sdk-skill

Skill Claude Code

Expert guidance for building AI agents with the Claude Agent SDK in Python. Use when the user writes Python code with the SDK, imports claudeagentsdk, uses query(), ClaudeSDKClient, ClaudeAgentOptions, AgentDefinition, creates custom @tool functions, sets up hooks, integrates MCP servers, manages sessions, or debugs…

not rated 7 6mo ago A ✓ AI review 120 tokens original Apache-2.0

faf-ide

3634

Wolfe-Jam/faf-mcp

Skill Claude CodeCodex

Use FAF context and IDE interop tools on this server — score, sync, platform formats; claim equals wire.

not rated 7 changed 6d ago A 27 tokens original MIT

agent-loader

3635

samzong/agent-brains

Skill Claude CodeCodex

Load or list repo-scoped and user-scoped agent brains. Use when the user asks to load an agent by name, list available agents, inspect agent descriptions or workflows, or start a session or task with a personal agent brain.

not rated 7 +1 3mo ago A 50 tokens original MIT

developer-skills

3636

sgomez/developer-skills

Plugin Claude Code

Bundles 5 skills, 3 agents, 1 hook · 685 tokens together

Unattended spec delivery pipeline: /developer loops over a spec's sub-issues with dispatcher → code-author → diff-reviewer workers, review→fix cycles, and a configurable merge policy (auto or hand-off), with parallel or sequential execution.

not rated 7 changed 7d ago A tokens not measured EUPL-1.2

codex-prompt

3637

TAKEOFF69/codex-skills-kit

Skill Codex

Generate structured, self-contained Codex task prompts. Use when the user asks for a Codex prompt, delegation task, fix, build, audit, ops/tuning, refactor, PR-series, or master-session brief to hand to another Codex run. Grounds every cited path and command, distinguishes directive from investigative work, and binds…

not rated 7 1mo ago A 77 tokens original MIT

shipd-olympus

3638

mashhoorahdal/shipd-olympus-skill

Skill Claude CodeCodex

Use when creating or reviewing a shipd.ai Olympus quest submission — picking a candidate GitHub repo, designing a challenge task hard enough for the ≤50% pass-rate bar, writing the test patch, solution patch, test.sh, or Dockerfile, or when a platform check fails (naming collisions, Dockerfile warnings, description…

not rated 7 1mo ago A 79 tokens original MIT

sophon

3639

lacausecrypto/mcp-sophon

MCP server Claude CodeCodexCursor +2

Honest token economics for MCP agents. 68% tokens saved, zero-ML Rust binary. Runs locally from the mcp-sophon npm package.

not rated 7 +1 2mo ago A tokens not measured original MIT

creating-skills

3640

chinkan/RustFox

Skill Claude CodeCodex

Use when the user asks to create, add, or write a new bot skill, or wants to teach the bot a new behavior, capability, or workflow.

not rated 7 yesterday A 36 tokens original MIT

dispatch

3641

sparklingneuronics/sparkling-skills

Plugin Claude Code

Bundles 2 skills, 3 commands · 571 tokens together

Delegate a task to an external AI CLI — OpenAI Codex (/codex) or Google Antigravity (/agy, multi-model: Gemini/Claude/GPT-OSS): second opinions, parallel checks, side tasks, images.

not rated 7 +1 changed 8d ago A tokens not measured original MIT

karpathy-skills

3643

clawnify/greybeard

Cursor rule Cursor

Karpathy-inspired coding-agent behavior — think before coding, simplicity, surgical changes, goal-driven execution, recalibrate time, skillify & resolve, ground in reality.

not rated 7 changed 12d ago A 3,741 tokens original MIT

mtk

3644

moberghr/mtk-agent-toolkit

Plugin Claude Code

Bundles 45 skills, 6 agents, 7 hooks, 1 MCP server · 1,693 tokens together

MTK (Moberg Toolkit) — AI-assisted development toolkit with pluggable tech stacks (.NET, Python, TypeScript). Language-agnostic workflow skills, review agents, and compliance-first workflows.

not rated 7 changed 8d ago B tokens not measured original MIT

om-superpowers

3645

SHGrowth/om-superpowers

Plugin Claude Code

Bundles 11 skills, 1 hook · 759 tokens together

Claude Code plugin for Open Mercato developers — 11 user-facing skills (plus on-demand specialist references) covering the full OM lifecycle from ideation through PR review.

not rated 7 +1 today A tokens not measured original MIT

duvo

3646

duvoai/skills

Plugin Claude Code

Bundles 7 skills · 969 tokens together

Operate Duvo from Claude: debug failed Runs, audit Agents and Queues, doctor Connections, and write AOPs — with the Duvo MCP connector wired in.

not rated 7 2d ago A tokens not measured original MIT

mcp-scribe

3647

The-Swarm-Corporation/mcp-scribe

MCP server Claude CodeCodexCursor +2

Transcribe any OpenAPI schema into a production-grade MCP server. Runs locally from the mcp-scribe Python package.

not rated 7 25d ago A tokens not measured original Apache-2.0

tough-tongue/toughtongue-skills

Plugin Claude Code

Lists 1 plugin

Skills and MCP server for Tough Tongue AI — the platform for tough conversations. Some, the AI takes: voice agents that call, demo, screen, and book. Others, you nail: realistic roleplay for negotiations, interviews, and coaching. Create agents, refine them from real transcripts, and analyze sessions from your coding…

not rated 7 changed 8d 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: