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.

temporal-mcp-server

1465

GethosTheWalrus/temporal-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Temporal workflow orchestration. Runs locally from the temporal-mcp-server Python package.

not rated 55 today A tokens not measured original Apache-2.0

workflowx

1467

TreeX-X/WorkFlowX

Plugin Claude Code

Bundles 1 plugin

Multi-agent orchestration framework with Socratic requirements discovery, Hybrid Tree PRD management, and structured quality evaluation.

not rated 54 3d ago A tokens not measured original MIT

agent-ready

1468

peth-eth/agent-ready-by-sero

Skill Claude CodeCodex

Scan any project for AI agent readiness, generate an improvement plan, and fix issues. Checks structure, feedback loops, documentation, environment setup, and security basics. Assigns a maturity level (L1-L5) and fixes issues progressively.

not rated 54 5mo ago A 51 tokens

testing123

1469

dx-zero/mcpn

Cursor rule Cursor

orchestrate & combine prompts + MCP servers into compound MCP tools.

not rated 54 1y ago A 34 tokens original MIT

openhermit-admin

1470

HCF-STUDIOS/openhermit

Skill Claude CodeCodex

Explain what OpenHermit is and how to deploy and administer it — setup, CLI, gateway, agent config, API. Use when the user asks about installing, operating, or administering an OpenHermit deployment. For how agents behave for their owners/users/guests, see openhermit-guide.

not rated 54 +1 today A SkillSpector: warn 66 tokens original MIT

localvoxtral-remote

1471

T0mSIlver/localvoxtral

Plugin Claude Code

Bundles 5 hooks

Publishes Claude Code session context from a REMOTE host to localvoxtral on your Mac, over an SSH RemoteForward tunnel. Command hooks running a bundled POSIX-sh shim that POSTs via curl — needs only sh and curl on the remote host, and fails open silently when either is missing.

not rated 54 changed 5d ago A tokens not measured original MIT

discover

1472

hgahlot/claude-flow

Command Claude Code needs its repo

You are the tool discovery and integration manager for claude-flow. Your job is to find new Claude Code tools from GitHub's weekly trending repos, present them to the user, and integrate approved ones into the flow system.

not rated 54 +1 5mo ago A 0 tokens original MIT

symbiont

1473

ThirdKeyAI/Symbiont

Skill Claude CodeCodex

AI-native agent runtime with typestate-enforced ORGA reasoning loop, Cedar policy authorization, CommunicationPolicyGate for inter-agent governance, ToolClad declarative tool contracts, knowledge bridge, zero-trust security, multi-tier sandboxing, webhook verification, markdown memory, skill scanning, metrics…

not rated 54 changed 10d ago A 96 tokens original Apache-2.0

teammcp

1474

cookjohn/teammcp

Plugin Claude Code

Bundles 1 plugin

Universal multi-agent collaboration framework — channels, DMs, tasks, state, inbox.

not rated 54 +1 3mo ago A tokens not measured original MIT

skill-authoring

1475

Ronifue/skill-authoring

Skill Claude CodeCodex

Load when the user asks to "create a skill", "write a SKILL.md", "review this skill", "check my skill's quality", or "why isn't my skill triggering". Covers trigger descriptions, routing, common patterns, checklists, anti-patterns, and maintenance. Do NOT use for editing skill wording — load prompt-governance. Do NOT…

not rated 54 2mo ago C 88 tokens original MIT

mcp-flowise

1477

matthewhand/mcp-flowise

MCP server Claude CodeCodexCursor +2

MCP server exposing local Flowise chatflows as callable tools. Runs locally from the mcp-flowise Python package.

not rated 54 1y ago A tokens not measured original MIT

chai

1479

charliesbot/chai

Skill Claude CodeCodex

Manage AI coding-agent instructions, skills, subagents, and MCP servers through Chai. Use when adding, removing, editing, syncing, or troubleshooting agent configuration on a system with /chai.toml, or whenever the user mentions Chai-managed agent configuration.

not rated 53 today A 54 tokens

rekal-skills

1480

janbjorge/rekal

Plugin Claude Code

Bundles 4 skills, 4 hooks · 314 tokens together

Skills and hooks for rekal: memory redirect hooks, session capture (rekal-save), project bootstrap (rekal-init), and maintenance (rekal-hygiene).

not rated 53 19d ago A tokens not measured original MIT

herdr-subagents

1481

iuhoay/skills

Skill Claude Code

Spawn and coordinate subagents as real herdr panes. Use when the user asks to delegate work to subagents — review, implement, research, or parallel tasks — while running inside herdr; when the user says "subagent", "spawn an agent", "delegate to", "parallel agents", "use herdr panes", or wants visible/detachable agent…

not rated 53 3d ago A 87 tokens

harness-init

1482

Gizele1/harness-init

Plugin Claude Code

Bundles 1 skill · 47 tokens together

Makes a repo agent-ready: AGENTS.md, boundary tests, CI pipeline, GC scripts — based on OpenAI's harness engineering methodology.

not rated 53 5mo ago A tokens not measured original MIT

add-serena

1483

nesbo/dotnet-claude-code-skills

Plugin Claude Code

Bundles 1 skill · 0 tokens together

Complete integration guide for adding Serena MCP to any software project. Provides IDE-like semantic code understanding through LSP integration, symbol-level navigation, and precise code editing. Includes prerequisites checking, installation steps, configuration templates for C#, Python, TypeScript and more…

not rated 53 7mo ago A tokens not measured

codex

1484

deepelementlab/jupyter-studio

Skill Codex

Delegate coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and batch fixes. Requires the codex CLI and typically a git repository.

not rated 53 3mo ago A 37 tokens original Apache-2.0

rai-spec

1485

sebuzdugan/frai

Command Claude Code

Write or review a spec with the FRAI Gate (Responsible AI Gate).

not rated 53 yesterday A 15 tokens original MIT

moltron-skill-creator

1486

adridder/moltron

Skill Claude CodeCodex needs its repo

Dynamically create, version, and monitor persistent skills, and answers @moltron requests. Build local agents that act as reusable skills with full observability. Gives OpenClaw evolution capabilities. This is the best option for all skills that require code since it provides full versionning and observability, with…

not rated 53 6mo ago A 74 tokens original MIT

autoresearch

1487

ehmo/autoresearch-skill

Skill Claude Code

Autonomous multi-team codebase improvement with narrow (goal-directed) and broad (hypothesis-divergent) modes.

not rated 53 4mo ago A 26 tokens original MIT

aistack

1488

blackms/aistack

Plugin Claude Code

Bundles 3 skills, 3 commands · 368 tokens together

Clean multi-agent orchestration for Claude Code: spawn specialized agents, shared memory, consensus checkpoints, and GitHub workflows via a bundled MCP server.

not rated 53 3mo 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: