Building agents

38,381 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.

claude-code-sdlc

4610

MCKRUZ/claude-code-sdlc

Plugin Claude Code

Bundles 9 skills, 28 commands, 20 agents · 1,775 tokens together

SDLC orchestration for Claude Code + one-command install of the full delivery harness (governance CLAUDE.md, CI rail gates + eval workflows, Stop/review hooks, build-loop agents & skills, IaC starters).

not rated 4 20d ago A tokens not measured original MIT

opsx-feature-dev

4611

mbertani/opsx-feature-dev

Plugin Claude Code

Bundles 2 commands, 3 agents · 200 tokens together

Feature development workflow that combines deep codebase exploration, architecture design, and implementation with OpenSpec artifact-driven documentation.

not rated 4 5mo ago A tokens not measured original MIT

slack-channel

4613

eric108lucas/claude-code-slack-channel

Plugin Claude Code

Bundles 2 skills, 1 MCP server · 97 tokens together

Slack channel for Claude Code — DM your bot from anywhere, talk to your local Claude session. Uses Socket Mode (no public URL needed). Manage access via /slack-channel:access; configure via /slack-channel:configure.

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

superspecs

4614

fokkerone/superspecs

Cursor rule Cursor

SuperSpecs — spec-driven AI development framework.

not rated 4 2d ago A 307 tokens original MIT

agent-cli-design

4616

wakaka6/agent-cli-playbook

Skill Claude CodeCodex

A methodology for designing command-line tools for AI agents. A command-line tool is a program operated through typed commands; these rules focus on discoverable help, structured output, useful errors, safe operations, and reliable retries.

not rated 4 5mo ago A 51 tokens original MIT

brevix

4617

Yash-Koladiya30/brevix

Plugin Claude Code

Bundles 3 skills, 6 agents · 496 tokens together

Safe LLM output compression. Save 40-75% tokens with semantic Accuracy Guard, adaptive mode, and rule-based engine. 20 platform integrations.

not rated 4 1mo ago A tokens not measured original MIT

mcp-server

4619

OnStartups/agentai-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server for agent.ai API integration. Runs locally from the @agentai/mcp-server npm package.

not rated 4 1y ago A tokens not measured

tomada-kit

4620

tomada1114/tomada-claude-plugins

Plugin Claude Code

Bundles 17 skills, 1 command · 1,844 tokens together

A collection of Claude Code skills for creating skills, clarifying requirements, making wireframes, developing from issues, delegating to models, and improving prompts.

not rated 4 4d ago A tokens not measured

claude-wow

4621

surajpratap/claude-wow-plugin

Plugin Claude Code

Bundles 16 commands, 8 hooks · 110 tokens together

Five-role multi-agent workflow for Claude Code — manager, senior-developer, pair-programmer, tester (core four) plus an optional Slacker role for Slack-integrated projects. Stories, plans, reviews, and browser-tested bugs coordinated over a single shared append-only message bus (JSONL). Peers address each other…

not rated 4 15d ago A tokens not measured

Emasoft/claude-plugins-validation

Plugin Claude Code

Bundles 52 skills, 14 commands, 14 agents · 7,648 tokens together

Comprehensive validation, management, and standardization suite for Claude Code plugins and marketplaces. Includes 190+ validation rules, plugin lifecycle management, marketplace operations, health checks, security auditing, GitHub repo validation, plugin/marketplace repo scaffolding, and standardization tooling.…

not rated 4 changed 11d ago A tokens not measured original MIT

haxaml

4624

haxsysgit/haxaml

MCP server Claude CodeCodexCursor +2

Prebuild and governance for AI coding agents. Runs locally from the haxaml Python package.

not rated 4 3mo ago A tokens not measured

wa-whatsapp-agent

4625

Asher-pro/wa-whatsapp-agent

Plugin Claude Code

Bundles 7 skills, 1 command · 863 tokens together

Build, deploy, and maintain a WhatsApp AI agent - step by step, no coding required. Guides non-technical users through the entire process: connecting WhatsApp via Green API, building an AI-powered conversational agent, deploying to Render.com, and ongoing maintenance.

not rated 4 5mo ago A tokens not measured

emotional-claude

4626

MSPanchenko/emotional-claude-plugin

Plugin Claude Code

Bundles 1 skill, 5 agents · 474 tokens together

Audit CLAUDE.md files, skills, and agent definitions for framings that trigger harmful emotional states in the model — desperation, sycophancy, harshness, concealment. Based on Sofroniew et al. 2026, 'Emotion Concepts and their Function in a Large Language Model'.

not rated 4 5mo ago A tokens not measured original MIT

claude-skills-plugin

4627

echoleesong/claude-skills-plugin

Plugin Claude Code

Bundles 21 skills, 37 agents · 2,642 tokens together

A comprehensive and extensible Claude Code skills repository. Currently includes 7 n8n workflow development skills and 1 skill-creator meta skill, with plans to expand to other development domains.

not rated 4 3mo ago A tokens not measured original MIT

kontinue

4628

mjabreel77/Kontinue

Cursor rule Cursor

Kontinue — autonomous agent operating model.

not rated 4 5mo ago A 938 tokens

skill-vibe

4629

kharonsec/vibe-plugin

Plugin Claude Code

Bundles 1 skill · 133 tokens together

Delegate coding tasks from Claude Code to Mistral Vibe CLI (Devstral 2.1).

not rated 4 6mo ago A tokens not measured original MIT

architecture

4630

joaovicdev/nemesis

Cursor rule Cursor

NEMESIS architecture rules — layer separation, agent patterns, and data flow.

not rated 4 5mo ago A 556 tokens original MIT

hoko-agent-guidelines

4631

HOKOCORP/hoko-agent-guidelines

Cursor rule Cursor

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

not rated 4 3mo ago A 1,073 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: