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.

amplihack marketplace

1249

rysweet/amplihack

Plugin Claude Code

Lists 1 plugin

AI-powered development framework with specialized agents, automated workflows, and memory systems for Claude Code.

not rated 77 1mo ago A tokens not measured archived

agentphone

1250

vm0-ai/vm0-skills

Skill Claude CodeCodex

Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related to telephony, phone numbers, or voice AI.

not rated 77 yesterday A 57 tokens

workflow-builder

1251

TechNickAI/openclaw-config

Skill Claude CodeCodex

Design, build, and maintain autonomous OpenClaw workflows (stewards). Use when creating new workflow agents, improving existing ones, evaluating automation opportunities, or debugging workflow reliability. Triggers on "build a workflow", "create a steward", "automate this process", "workflow audit", "what should I…

not rated 76 1mo ago A 86 tokens

sous-chef

1252

tomascupr/sous-chef

Plugin Claude Code

Bundles 7 skills · 536 tokens together

Claude plans, delegates, and tastes every plate. Sonnet, Codex, GLM, or Grok does the knife work. A Claude Code plugin for the orchestrator/implementer split: /serve runs the whole line autonomously (implement, cross-review, fix, verify), /fire hands specced implementation to the worker, /taste runs cross-model review.

not rated 76 1mo ago A tokens not measured original MIT

ChuckSRQ/awesome-hermes-skills

Skill Claude CodeCodex

Run behavioral benchmarks against the agent, detect failure patterns, generate guidance patches, apply them with auto-revert safety net. Implements the closed-loop self-improvement cycle from Hermes PR.

not rated 76 4mo ago A 41 tokens original MIT

mind

1254

Da7-Tech/mind

Skill Claude CodeCodex

Local project memory with recall, provenance, policy, and dreams.

not rated 76 1mo ago A 15 tokens original MIT

longgraph

1256

levi-qiao/longgraph-skill

Plugin Claude Code

Bundles 5 skills · 467 tokens together

Long-horizon agent skill: durable loop-graph runs (executor + clean-context supervisor), verified gates, owner A/B/C cards. Works with Claude Code, Codex, Cursor, and Grok Build. Invoke /longgraph, /loop-converge, /loop-deliver, or /loop-research.

not rated 76 +3 3d ago A tokens not measured original MIT

wave-executor

1257

9thLevelSoftware/legion

Skill Claude CodeCodex

Executes wave-structured plans with personality-injected agents — parallel or sequential per CLI adapter.

not rated 76 1mo ago A 22 tokens

network-ai

1258

Jovancoding/Network-AI

Plugin Gemini CLI

Multi-agent coordination layer for Gemini CLI — atomic shared blackboard (propose/validate/commit), permission gating with HMAC/Ed25519-signed tokens, federated token-budget tracking, and append-only audit-log queries over MCP.

not rated 76 +2 6d ago A tokens not measured original MIT

mlflow

1259

mlflow/skills

Plugin Claude Code

Bundles 12 skills, 1 hook · 1,346 tokens together

Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate.

not rated 75 yesterday A tokens not measured original Apache-2.0

mission-driver

1261

entropy-cloud/attractor-guided-engineering-template

Skill OpenCode needs its repo

Create roadmaps and mission configs, then drive the mission-driver AI dev-loop engine. mission-driver lives at tools/mission-driver/ — it reads missions/ .json and loops CHECK → REVIEWPLANS → EXECPLANS → DRAFTPLANS → DEEPAUDIT until the roadmap is done or the audit budget is exhausted. Use this skill when the user…

not rated 75 +1 7d ago A SkillSpector: warn 199 tokens original MIT

mcp-tool-definition

1262

netanelavr/trading-mcp

Cursor rule Cursor

A rule for defining tools in the MCP server is clearly and effectively defined. Ensures each tool includes a well-structured title and description that communicates its purpose, functionality, ideal usage scenarios, and expected output. This improves tool discoverability, relevance ranking, and clarity for AI agents.

not rated 75 1y ago A 58 tokens original MIT

skill-scorer

1263

AndrewNgGirl/SkillLens

Skill Claude CodeCodex needs its repo

A review tool for Agent Skills, which are instruction files that guide coding agents. It supports skills made for Cursor, Claude, and OpenClaw.

not rated 75 3mo ago A 95 tokens original MIT

rocket-fuel

1264

NulightJens/rocket-fuel-skill

Skill Claude CodeCodex

Runs Fable 5 and OpenAI Codex as co-founders on the Rocket Fuel operating system. Fable is the Visionary (vision, plan, standards, final review); Codex is the Integrator (filters the plan, executes the build, reports). Context-routed, one entry point, four functions: KICKOFF a new project, CLARITY BREAK to refactor an…

not rated 75 2mo ago A 149 tokens original MIT

paneflow-conductor

1265

arthjean/paneflow

Skill Claude CodeCodex

Orchestrate a fleet of CLI coding agents running side by side in Paneflow panes - discover them, read their live state, dispatch prompts, and wait on events - all over the public paneflow CLI. Use when the user asks you to coordinate, supervise, or hand work between multiple agents (Claude Code, Codex, OpenCode…

not rated 75 +5 changed 6d ago C 90 tokens GPL-3.0

spherse-use-ui-sdk

1266

mengrru/Spherse

Skill Claude CodeCodex

A browser-side JavaScript interface injected into Spherse HTML pages. It lets page controls communicate with the Spherse app, including opening files or sessions, sending messages, storing data, and showing notifications.

not rated 75 +5 today A SkillSpector: pass 92 tokens original MIT

mcp

1267

discourse/discourse-mcp

MCP server Claude CodeCodexCursor +2

Discourse MCP CLI server (stdio) exposing Discourse tools via MCP. Runs locally from the @discourse/mcp npm package.

not rated 75 +1 20d ago A tokens not measured original MIT

example-skills

1268

datascienceworld-kan/vinagent

Plugin Claude Code

Bundles 12 skills · 729 tokens together

Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling.

not rated 75 +1 5mo ago A tokens not measured original MIT

notion-skills-usage

1269

brianlovin/notion-skills

Skill Claude CodeCodex

Use the notion-skills CLI to manage AI agent skills from one or more Notion-backed workspace stores. Invoke when the user wants to install a skill from their team's store, publish a local skill they authored, sync installed skills, generate a new skill via their coding agent, manage Notion sources (one database per…

not rated 74 1mo ago C 118 tokens

callee-create-agent

1270

baldaworks/callee

Skill Claude CodeCodex

Create project-defined Callee Role, Script, Human, Sequential, Loop, and Router agents in Markdown or YAML. Use when the user asks to generate, scaffold, compose, or author a Callee agent or deterministic workflow.

not rated 74 1mo ago A SkillSpector: warn 49 tokens original MIT

Caph-dev/agents-progressive-disclosure

Skill Claude CodeCodex

Refactor bloated AGENTS.md/CLAUDE.md-style instruction files into a compact router plus focused on-demand docs. Use when users ask to apply progressive disclosure, split agent rules into docs, reduce instruction bloat, or turn one large rule file into an entrypoint.

not rated 74 2mo ago A 62 tokens

agentos

1272

imran-siddique/agent-os

MCP server Claude CodeCodexCursor +2

Build and manage policy-compliant AI agents with safety enforcement and compliance checking. Runs locally from the agentos-mcp-server npm package. Needs 2 environment variables to run.

not rated 74 6mo ago A tokens not measured original MIT archived

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: