Building agents

38,263 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.

autoresearch

2569

Muminur/autoresearch-skill-Andrej-Karpathy

Skill Claude CodeCodex

Autonomous Goal-directed Iteration. Apply Karpathy's autoresearch principles to ANY task. Loops autonomously — modify, verify, keep/discard, repeat. Supports optional loop count via Claude Code's /loop command. Invoking /autoresearch builds a real-data benchmark harness, captures a baseline, and iterates with a…

not rated 16 4mo ago A 82 tokens original MIT

codewiki-mcp

2570

izzzzzi/codewiki-mcp

MCP server Claude CodeCodexCursor +2

MCP server for codewiki.google: search repos, fetch wiki docs, ask questions. Runs locally from the codewiki-mcp npm package.

not rated 16 2mo ago A tokens not measured original MIT

task-mcp

2571

parallel-web/task-mcp

MCP server Claude CodeCodexCursor +2

An MCP server for deep research or task groups. Remote server at task-mcp.parallel.ai.

not rated 16 +1 3d ago A tokens not measured

a2anet-mcp

2572

a2anet/a2a-mcp

MCP server Claude CodeCodexCursor +2

An MCP server for the Agent2Agent (A2A) protocol. Runs locally from the a2anet-mcp Python package.

not rated 16 3mo ago A tokens not measured original Apache-2.0

archsight-aios

2574

ArchSightLabs/archsight-aios

Plugin Claude Code

Bundles 33 skills · 1,987 tokens together

A toolkit of coding-agent skills, workflows, and multi-agent tools for construction-industry work, including BIM, IFC models, document retrieval, project evidence, reviews, and runtime oversight. BIM is building information modeling; IFC is a common format for exchanging building-model data.

not rated 16 +2 19d ago A tokens not measured original Apache-2.0

agent-bridge

2575

kununu/agent-bridge

Skill Claude CodeCodex

Delegate real coding work to a peer AI agent (such as Claude Code, Codex (ChatGPT), or Gemini (Antigravity)) that runs its own full harness, or use that peer as an independent reviewer, adversarial red-team, ideation & planning partner. Trigger when the user says "use agent bridge", "ask ", "delegate to ", "have…

not rated 16 +1 changed 11d ago A SkillSpector: pass 167 tokens original MIT

codex-universal-proxy

2577

bharat2808/codex-universal-proxy

Skill Claude CodeCodex

Install and manage the unofficial codex-universal-proxy local compatibility tool. Use when the user wants Codex to install it from npm, clone/download the repo, configure model routing, start/restart/inspect the proxy, switch the local experimental Ollama/proxy workflow on or off, or uninstall it.

not rated 16 +1 23d ago A SkillSpector: warn 69 tokens original MIT

agentsync

2578

yelmuratoff/agent_sync

Skill Claude CodeCodex

Create or edit AgentSync configuration — AGENTS.md, rules, skills, commands, subagents, settings, MCP servers, hooks, or per-tool configs. Use this skill when adding a rule, creating or scaffolding a skill, writing a slash command, defining a subagent persona, editing permissions, configuring an MCP server, setting up…

not rated 16 +2 changed 3d ago C 142 tokens GPL-3.0

claude-ops

2580

melodic-software/claude-code-plugins

Plugin Claude Code

Bundles 11 skills · 2,035 tokens together

Claude Code operations toolkit. Twelve skills: audit-skill-visibility (audit whether each installed skill is actually VISIBLE to the model, and diagnose why most of a fleet never gets used: a skill is invisible when its description is dropped by Claude Code's skill-listing context budget, which sheds descriptions…

not rated 16 changed today A tokens not measured original MIT

superstack

2581

edvardgrishin27/superstack-plugin

Plugin Claude Code

Bundles 7 skills, 3 agents, 3 hooks · 313 tokens together

An agent-based software-development system that guides work from a short request to a tested, demonstrated piece of software. It uses checkpoints for planning and verification and explains conclusions in plain language.

not rated 16 +2 changed 5d ago A tokens not measured original MIT

jongio-skills

2582

jongio/skills

Plugin Claude Code

Bundles 10 skills · 1,672 tokens together

Jon Gallant's collection of reusable skills for AI coding agents.

not rated 16 9d ago A tokens not measured original MIT

beastmode

2585

BugRoger/beastmode

Plugin Claude Code

Bundles 6 skills · 202 tokens together

Agentic workflow skills for Claude Code. Activate beastmode.

not rated 16 4mo ago A tokens not measured original MIT

omg_cli_tools

2587

NetVar1337/omniwire

MCP server Gemini CLI

MCP server "omgclitools" as configured in NetVar1337/omniwire. Launched with oh-my-gemini tools serve.

not rated 16 +1 7d ago A tokens not measured GPL-3.0

eshell-config

2588

mahoushoujyo-eee/eshell

Skill Claude CodeCodex

Edit eShell's SSH, ACP, and Ops Agent config files and understand .eshell-data. Use when the user asks to add/change an SSH server profile, adjust agent login or spawn settings, add an ACP agent, explain what a .eshell-data file does, or tune connection/agent behavior via one of the JSON config files. Covers the exact…

not rated 16 7d ago A 146 tokens

openchronicle-mcp

2589

CarlDog/openchronicle-mcp

MCP server Claude CodeCodexCursor +2

Memory database for LLM agents — persistent semantic + keyword memory, project namespacing, served over HTTP REST and MCP. Runs locally from the openchronicle-mcp Python package.

not rated 16 yesterday A Socket: warn tokens not measured AGPL-3.0

skill-audit

2590

okjpg/skill-audit

Skill Claude CodeCodex

Audits a Claude Code / Agent SDK skill (or folder of skills) against 10 QA checks to verify it will trigger and execute correctly in any LLM (Claude, GPT, Gemini). Ativa quando o usuário diz "audit my skill", "roda skill-audit", "verifica se essa skill funciona", "check skill quality", "skill-audit ./my-skill", "minha…

not rated 15 4mo ago A 169 tokens

x2

2591

teklabsdigital/x2-method

Plugin Claude Code

Bundles 13 skills, 1 hook · 1,049 tokens together

Build production software with AI coding agents. Invariants in the build, decisions with people, progress in human turns per shipped slice.

not rated 15 1mo ago A tokens not measured

claude-codex-bridge

2592

Jayden-X-L/claude-codex-bridge

Skill Claude Code

Bridge Claude Code and Codex for bidirectional execution review. Use when Claude should send its result to Codex/GPT-5.5 for audit, audit Codex/GPT-5.5 handoffs, return feedback to Codex, or run an automated Claude-Codex review loop.

not rated 15 3mo ago A 68 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: