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.

dify-mcp-server

3649

overpod/dify-mcp-server

MCP server Claude CodeCodexCursor +2

MCP Server for Dify workflow integration. Runs locally from the dify-mcp-server npm package.

not rated 7 5mo ago A tokens not measured original MIT

task-orchestrator

3650

coderexpert123/task-orchestrator

MCP server Claude CodeCodexCursor +2

Autonomous task execution engine with atomic claiming, convergence tracking, and sharded state. Runs locally from the task-orchestrator npm package.

not rated 7 4mo ago A tokens not measured original MIT

chisel-mcp

3651

EYamanS/chisel

MCP server Claude CodeCodexCursor +2

MCP server "chisel-mcp" as configured in EYamanS/chisel. Runs locally from the chisel-mcp npm package.

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

create-agent

3652

plmbr/nui

Skill Claude CodeCodex

Create a nui ADL agent definition from the current conversation and save it to /.nui/agents/.

not rated 7 changed 10d ago A SkillSpector: warn 24 tokens original MIT

agent-office

3653

Mr-AK-AI/agent-office

Skill Claude CodeCodex

A command-line tool for delegating work from one coding agent to other local command-line agents in shared tmux rooms, which are terminal sessions that can stay open and be shared.

not rated 7 +1 25d ago A 107 tokens copy · 100% MIT

shiploop

3654

anshss/shiploop

Plugin Claude Code

Bundles 2 skills, 8 commands, 3 agents · 277 tokens together

Self-improving multi-agent harness that dispatches the tickets you name across every repo in your product — guarded auto-merge on green CI, and every resolved ticket writes a lesson into your git-tracked CLAUDE.md. Every ticket starts on a cheap tier and escalates once, on measured failure, instead of being predicted…

not rated 7 changed 2d ago A tokens not measured original Apache-2.0

auspex-coordination

3655

AstroQore/auspex

Skill Claude CodeCodex

Coordinate Supervisor, Worker, and Reviewer work through Auspex when a brief names an Auspex task, when handing work to another agent, or when reviewing shared task progress. Auspex remains the task state source; this skill is only the operating playbook.

not rated 7 9d ago A 56 tokens AGPL-3.0

skill-creator

3656

mfmezger/ai_agent_dotfiles

Command Claude CodeGemini CLI

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 7 +1 1mo ago A 59 tokens original MIT

resume-from

3657

alexei-led/resume-from

Plugin Claude Code

Bundles 1 command · 12 tokens together

Continue a coding session from another agent, or another profile of the same agent.

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

build-capability

3658

IvanSkainet/arena-agent

Skill Claude CodeCodex

When you need an ability the bridge does not have, build it from the general tools instead of asking for a bespoke one. This skill is the map of how.

not rated 7 +1 today A 0 tokens original MIT

click-to-mcp

3659

Coding-Dev-Tools/click-to-mcp

Plugin Claude Code

Bundles 1 skill · 104 tokens together

Auto-wrap any Click/typer CLI as an MCP server — zero-code transformation. Supports stdio, HTTP+SSE, and Streamable HTTP transport with automatic tool discovery. Turn your Python CLI tools into MCP servers Claude Code can call directly.

not rated 7 22d ago A tokens not measured

mcp-server-builder

3660

archimedes-run/omniHarness

Skill Claude CodeCodex

Scaffold, generate, and test a FastMCP server that can be used as an MCP tool provider. Handles API wrapper, database connector, and custom tool templates.

not rated 7 22d ago A 39 tokens original MIT

admin

3661

fa-mc/vibe-cading

Agent Claude Code

Use this agent for workflow governance, instruction maintenance, mid-session interventions, and design-flow orchestration. Invoke when another role is stuck, looping, or out of scope; when an instruction gap surfaces; to initiate the design flow for a non-trivial task; or to run a session wrap-up. Admin diagnoses and…

not rated 7 +1 changed 12d ago A 84 tokens AGPL-3.0

prompt_control_lab

3662

VeraPyuyi/prompt_control_lab

Skill Claude CodeCodex

Guard and improve prompts before expensive Codex, IDE, or CLI agent work. Use when a prompt is vague, broad, risky, costly, or should be optimized before implementation.

not rated 7 20d ago A 40 tokens

orchestrator

3663

Andyduck-ops/omp-flow

Agent Claude Code

Main coordinator for linked task Bundles and OMP native task operations.

not rated 7 +1 11d ago A 18 tokens original MIT

thinking-os

3664

vdmcb/thinking-os

Plugin Claude Code

Bundles 2 skills · 214 tokens together

Portable cognitive skills for capable AI agents: Understand produces an audited stakeholder brief with a scoped stance, three answered questions, and three source-specific follow-ups; ELI5 explains a file from first principles for a reader with no background.

not rated 7 18d ago A tokens not measured

ask-ui

3665

Angus221/ak.skills_sample

Skill Codex

Render independent questions from an Agent workflow as a local interactive form, preselect recommended answers, collect an optional supplement for every question, save responses as portable JSON, and return submitted answers directly to the waiting Agent command. Use for grill-me, grill-with-docs, brainstorming…

not rated 7 1mo ago A 121 tokens

grok-remote

3666

Amnibro/grok-remote

Plugin Claude Code

Bundles 1 skill, 4 commands, 1 hook · 133 tokens together

Live phone controller for Grok Build. LAN UI+ACP proxy, multi-session, live stream, Skills, New Task. Optional auto-start on Grok SessionStart and/or Windows logon. Commands: /remote /remote-stop /remote-autostart.

not rated 7 changed 12d ago A tokens not measured original MIT

skill-optimizer

3667

chujianyun/skill-optimizer

Skill Claude CodeCodex

A review and improvement workflow for existing coding-agent skills, including their instructions, triggers, resources, and safety rules.

not rated 7 +2 changed 4d ago A 41 tokens

skill-creator

3668

SocialGouv/claw-code-go

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 7 +1 yesterday A 64 tokens copy · 88% MIT

draugr

3670

draugr-dev/draugr

MCP server Claude CodeCodexCursor +2

MCP server "draugr" as configured in draugr-dev/draugr. Launched with https://github.com/draugr-dev/draugr/releases/download/v0.99.1/draugr-0.99.1.mcp.

not rated 7 +1 today A tokens not measured original Apache-2.0

skill-dispatcher

3671

farhanic017/dynamic-skill-loader

Skill Claude CodeCodex

Universal MCP skill dispatcher for AI coding agents. Loads Claude Code, OpenCode, Cursor, Gemini-style, command, plain markdown, and GitHub-hosted skills on demand. Includes agent routing, active skill lifecycle tracking, external repo import, nested skill discovery, origin filtering, and hardened parsing for secure…

not rated 7 3mo ago A 68 tokens GPL-3.0

sanity-io/context

Skill Claude CodeCodex

Build AI agents with structured access to Sanity content via Sanity Context. Use when setting up a Sanity-powered chatbot, connecting an AI assistant to Sanity content, or adding client-side tools to an agent. Covers Studio setup, agent implementation, and advanced patterns. Always use this skill when users mention…

not rated 7 yesterday A ✓ AI review Socket: passSnyk: warn 127 tokens

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: