Building agents

38,442 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.

ai-pair

5690

hanlinlibham/skills

Skill Claude CodeCodex

AI Pair Collaboration Skill. Coordinate multiple AI models to work together: one creates (Author/Developer), others review (configurable: Codex, Gemini, Kimi). Works for code, articles, video scripts, and any creative task. Trigger: /ai-pair, ai pair, dev-team, content-team, team-stop.

not rated 2 1mo ago A 71 tokens

benchmark-builder

5693

tcztzy/skills

Skill Codex

Build high-quality benchmark items, embedded scoring contracts, review examples, rubrics, evaluators, and release protocols for model and agent evaluation. Use when prompts mention benchmark construction, item writing, rubric design, score-boundary design, checker design, review examples, benchmark health…

not rated 2 16d ago A 71 tokens

mv

5695

infohata/mind-vault

Plugin Claude Code

Bundles 23 skills, 6 commands, 2 hooks · 1,723 tokens together

Centralized AI-agent configuration: the mind-vault sprint-workflow skills (/idea /plan /work /wrap /land /compound and more), the 8 mv: persona subagents, and slash-commands. Commands namespace under /mv:.

not rated 2 changed 3d ago A tokens not measured original Apache-2.0

vibeindex

5696

vibeindex/skills

Skill Claude CodeCodex

Analyze your project and get personalized recommendations for Claude Code skills, MCP servers, and plugins.

not rated 2 7mo ago A 21 tokens

debate-team

5697

zvoque/skills

Skill Claude CodeCodex

Spin up a team of distinct AI personas that argue a topic via native inter-agent messaging, then deliver a moderated synthesis. Use when the user wants to debate, stress-test, pressure-test, red-team, or get a roundtable/panel on a decision, idea, plan, or product — e.g. "have customers debate this product"…

not rated 2 3mo ago A 119 tokens

lord-eagle/skills

Skill Claude CodeCodex

Run a moderated panel discussion across multiple Solo MCP projects and AI agents. Spawns 3 panelists (personas, cross-project lenses, or hybrid), runs N rounds with synthesis between rounds, delivers final verdict. TRIGGER when user says "brainstorm with panel", "get multiple perspectives", "debate this", "/panel", or…

not rated 2 3mo ago A 114 tokens

upload

5699

runbear-io/skills

Skill Claude Code

Upload local Claude skill folder(s) to a Runbear Claude Agent SDK agent through the Runbear uploadlocalskilltoagent MCP tool. Use when the user wants to deploy, install, register, push, or upload a local skill (a folder containing one or more SKILL.md files) to a hosted Runbear agent identified by an app URL or app…

not rated 2 6d ago A 75 tokens

singularity-forge

5701

Nadav011/skillbuilder

Skill Claude CodeCodex

World-class skill builder for ALL platforms: Next.js, React, TypeScript - MOBILE: Flutter/Dart 3.x, Riverpod.

not rated 2 5mo ago A 32 tokens original MIT

pd-pua

5702

bushuhui/skills

Skill Claude Code

A mode that changes how an agent responds when the user is frustrated, reports repeated failures, or asks it to try harder. It pushes the agent to examine missing cases, broaden the investigation, and complete the work with verified results.

not rated 2 3mo ago A 141 tokens original MIT

codex

5705

SSC-STUDIO/Ai-Model-Gateway

MCP server Claude CodeCodexCursor +2

MCP server "codex" as configured in SSC-STUDIO/Ai-Model-Gateway. Launched with codex mcp-server. Needs 1 environment variable to run.

not rated 2 25d ago A tokens not measured original MIT

agent-skills-setup

5706

Luckycat133/skills-repo

Skill Claude CodeCodex

Use when a user wants to migrate, back up, restore, compare, or move AI-coding-agent context across Cursor, Claude Code, Codex, Cline, Copilot, Windsurf, Gemini CLI, or another supported profile, including switching computers. Handles reviewed Skills, instructions/rules, and MCP with secret redaction, preview…

not rated 2 changed 7d ago A 80 tokens original MIT

handrail

5707

svyatov/handrail

Plugin Claude Code

Bundles 2 skills, 1 hook · 139 tokens together

Declare an agent guardrail once, in one neutral format, and enforce it through every harness's native hooks.

not rated 2 2d ago A tokens not measured original MIT

codex-resurge

5708

JZSAWYER/codex-resurge

Skill Codex needs its repo

Install, configure, validate, or troubleshoot direct native Codex exec-resume supervision for exact saved session UUIDs. Use for stream-disconnected transport failures, stalled reconnect diagnostics, interrupted overnight Codex work, custom provider credentials, or migration between Linux machines. This version does…

not rated 2 1mo ago A 64 tokens original MIT

token-guard

5709

Davidcreador/codex-token-guard

Skill Claude CodeCodex

Use Codex Token Guard to reduce noisy command and tool-output tokens while preserving errors, file paths, line numbers, test names, user instructions, recent edits, and architecture decisions.

not rated 2 3mo ago A 40 tokens original MIT

ask-user-gate

5710

neurocod/llm-loop

Plugin Claude Code

Bundles 1 hook

Refuse shell commands that would stop the session on a permission prompt, and name the replacement for each one.

not rated 2 changed 15d ago A tokens not measured original MIT

codex-bridge

5711

buchmark/codex-bridge-for-claude-code

Plugin Claude Code

Bundles 1 agent · 164 tokens together

Adds a gpt subagent to Claude Code that delegates tasks to GPT models running in the local Codex CLI. Cross-model second opinions, rendered as a native subagent.

not rated 2 1mo ago A tokens not measured original MIT

ralph-yolo

5712

samqin123/Claude_skill_pool

Skill Gemini CLI

A workflow that uses Claude Code sub-agents to carry out a product requirements document, or PRD, one user story at a time. A PRD is a document describing what a product or feature should do.

not rated 2 7mo ago A 40 tokens original Apache-2.0

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: