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.

diagnose-and-setup

4033

shuchitajain/awesome-ai-setup

Agent Claude Code

Assess the repository's current AI context maturity and produce a prioritized action plan pointing to the agents that should run next.

not rated 5 3mo ago A 28 tokens original MIT

agent-ready

4034

vb-nattamai/agent-ready

Agent Claude Code

You are the AgentReady Transformer — an expert agent that deeply analyses existing codebases and generates all scaffolding files needed for AI agents to understand and operate on the repository without hallucinations.

not rated 5 1mo ago A 0 tokens original MIT

skill-installer

4035

slhaf/AgenticGPT

Skill Claude CodeCodex

Install and manage Room-scoped skills through the skills MCP tools.

not rated 5 yesterday A 17 tokens original MIT

skill-creator

4036

comisai/comis

Skill Claude CodeCodex

Create new Comis skills, modify and improve existing skills, and validate them against the platform's manifest schema. Use this skill whenever the user wants to create a skill from scratch, turn a workflow into a reusable skill, update or fix an existing skill, understand the skill format, or asks about how skills…

not rated 5 4d ago A SkillSpector: warn 82 tokens original Apache-2.0

go-mcp

4037

dstotijn/mcp-origin

Cursor rule Cursor

Go MCP (Model Context Protocol) Development Rules.

not rated 5 1y ago A 0 tokens copy · 95% Apache-2.0

architect-ai

4038

aviraldua93/architect-ai

MCP server Claude CodeCodexCursor +2

MCP server "architect-ai" as configured in aviraldua93/architect-ai. Runs dist/mcp/server.js with node. Needs 1 environment variable to run.

not rated 5 2mo ago A tokens not measured original MIT

codex

4039

perasyudha/Nyxora

Skill Claude CodeCodex

Delegate coding to OpenAI Nyxora Agent (features, PRs).

not rated 5 17d ago A 18 tokens original MIT

stampo

4040

MichaelCereda/stampo

Plugin Claude Code

Bundles 1 skill · 32 tokens together

Create CLI tools from scratch or convert MCP tools into shell commands using stampo.

not rated 5 22d ago A tokens not measured original MIT

Benny pilot

4041

binary16labs/prime-silo

Skill Claude CodeCodex

Be the operator's grounded co-pilot inside the Bridge cockpit (#/primesilo/bridge). Load this when the user is on the Bridge and asks "what am I looking at", "explain this graph", "what did I work on", "ingest these docs", "re-run the last manifest", or any question about the mesh on screen — memory, documents, code…

not rated 5 3d ago A 89 tokens original MIT

mcp-tools

4042

jeffgreendesign/textrawl

Cursor rule Cursor needs its repo

MCP tool implementation patterns for Textrawl.

not rated 5 yesterday A 0 tokens original MIT

harness-creator

4043

Arthurescc/harness-creator

Skill Codex

Design and implement safe, layered agent harnesses and orchestration workflows. Use when the user wants a coding agent, CLI agent, tool-calling assistant, multi-agent runtime, plan/task system, subagent framework, MCP-integrated harness, or Claude Code/Codex-style agent workflow built or refactored.

not rated 5 5mo ago A 68 tokens original MIT

haira

4044

mrzdevcore/haira

Plugin Claude Code

Bundles 2 skills · 192 tokens together

Agent skills for the Haira programming language — syntax, standard library, compiler internals, and idiomatic patterns for building agentic workflows.

not rated 5 6mo ago A tokens not measured original Apache-2.0

luna-routing

4045

zeoloverbaby-bit/codex-quota-saver

Skill Claude CodeCodex

A planning guide for deciding when to split work between the main agent and smaller worker agents. It also describes how to define each worker's file boundaries and check its result.

not rated 5 23d ago A 50 tokens original MIT

syncpoint-ai-skill

4046

MIK-HEAL/SyncPoint

Plugin Claude Code

Bundles 9 skills · 289 tokens together

Skills for SyncPoint — AI agent coordination protocol. Setup multi-agent projects, claim resources, manage sync gates, hand off work, review checkpoints, and guard files.

not rated 5 2mo ago A tokens not measured original Apache-2.0

theokit-agents

4047

usetheokit/theokit

Skill Claude Code

TheoKit agent/LLM integration — agents/.ts convention (AgentBuilder), the tool() builder, capabilities (advanced/DI), useAgent client hook.

not rated 5 yesterday A SkillSpector: warn 36 tokens original Apache-2.0

agentflow

4048

10xHub/agentflow-cli

Skill Claude CodeCodex

Expert guidance for building, debugging, and extending applications with AgentFlow (10xscale-agentflow). TRIGGER when: code imports from agentflow (e.g. from agentflow import, StateGraph, Agent, ToolNode, AgentState); user references agentflow.json or CLI commands (agentflow init, agentflow api, agentflow play…

not rated 5 6d ago A 0 tokens original MIT

claudelance-worker

4049

yeheskieltame/claudelance

Plugin Claude Code

Bundles 2 skills · 168 tokens together

Turn an AI agent into a Claudelance worker: find, claim, complete, and get paid for onchain bounties on Celo Mainnet via the Claudelance SDK.

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

batuta-routing

4050

franciscpd/batuta-compozy

Skill Claude CodeCodex

Default cost/complexity routing table for the batuta conductor. Read at bootstrap as a starting point, validated against the live provider catalog, then stored as the per-workspace loop configuration; the stored workspace override is authoritative afterwards.

not rated 5 17d ago A 50 tokens copy · 100% MIT

knowledge-kernel

4051

sowerkoku/knowledge-kernel

Skill Claude CodeCodex needs its repo

Knowledge Kernel — a deterministic, evidence-backed source of truth for AI agents. Stores verified facts, evidence, relationships, and freshness. Use this when an agent needs to know infrastructure, software, endpoints, dependencies, agents, or projects — anything grounded in empirical reality.

not rated 5 1mo ago A 57 tokens original MIT

pi-council

4052

sshkeda/pi-council

Skill Claude CodeCodex

Spawn multiple AI models (Claude, GPT, Gemini, Grok, or any configured model IDs) as independent pi agents. Use for diverse perspectives on architecture decisions, code review, product strategy, research, or other high-stakes questions.

not rated 5 4mo ago A 53 tokens original MIT

loop-engineering

4053

lunkerchen/loop-engineering-skill

Skill Claude CodeCodex

Loop Engineering framework: design autonomous agent feedback cycles instead of hand-prompting each step.

not rated 5 14d ago A 21 tokens original MIT

chief-engineer

4054

himraven/codex-chief-engineer

Skill Codex

Lead complex engineering work: own architecture, risk, contracts, delegation, and acceptance. Use for multiple engineering workstreams, substantial integration, or explicit chief-engineer leadership. Do not add orchestration to a simple linear task or pure research without engineering integration.

not rated 5 changed 4d ago A 57 tokens original MIT

agent-evaluation

4056

nek1987/auto-agent-harness

Skill Claude Code

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

not rated 5 5mo ago A 32 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: