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.

yandex-messenger-mcp

5137

conarti/yandex-messenger-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Yandex Messenger (cookie/xiva transport). Runs locally from the yandex-messenger-mcp npm package.

not rated 3 21d ago A tokens not measured

archetypal-ai

5139

archetypal-ai/archetypal-ai

MCP server Claude CodeCodexCursor +2

Persistent memory for AI agents. recall, remember, checkpoint — soul preservation. Runs locally from the archetypal-ai npm package.

not rated 4 5mo ago A tokens not measured

MAXential-Thinking-MCP

5140

BAM-DevCrew/MAXential-Thinking-MCP

MCP server Claude CodeCodexCursor +2

11 focused tools for structured thinking, branching, revision, and navigation. Runs locally from the @bam-devcrew/maxential-thinking-mcp npm package.

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

telegram-mcp

5141

Anonymouse8882/TelegamMCP

MCP server Claude CodeCodexCursor +2

MCP server for Telegram - lets AI agents communicate with users via Telegram. Runs locally from the telegram-mcp Python package.

not rated 3 1mo ago A tokens not measured

codex-debate

5142

octanevz/codex-debate

Plugin Claude Code

Bundles 1 skill · 182 tokens together

Second opinions: iterative adversarial debates between Claude and Codex over any subject, from specs, designs, and code to non-technical positions, ending in genuine agreement or a documented dispute.

not rated 3 +1 1mo ago A tokens not measured original MIT

skill-creator

5143

stabruriss/kota-app

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 3 yesterday A 64 tokens copy · 88% Apache-2.0

agent-stack

5144

ssheleg/agent-stack

Plugin Claude Code

Bundles 4 skills · 931 tokens together

Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent…

not rated 3 +1 changed 4d ago A tokens not measured original MIT

claude-oracle

5145

Vvkmnn/claude-oracle-mcp

Skill Claude Code

Use when user asks "what exists for X?", before implementing custom MCP servers or plugins from scratch, or when browsing available tools — searches 19 sources and 15,000+ skills, plugins, and MCP servers in one query.

not rated 3 6mo ago A 52 tokens original MIT

yggdrasil-mcp

5146

henrychong-ai/yggdrasil-mcp

Plugin Claude Code

Bundles 1 MCP server

Tree of Thoughts reasoning, deep planning, and plan management for Claude. Adds sequentialthinking, deepplanning, listplans, getplan, promoteplan, archiveplans.

not rated 3 changed 7d ago A tokens not measured original MIT

vibecoders

5147

RaedBerjaoui/vibecoders-mcp

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 48 tokens together

An MCP control plane for Claude Code: swallow other MCP servers through one gateway, delegate to Codex/Gemini/Claude on your own CLI subscriptions, plus a RAG memory graph, reference study, and cross-session handoffs. Optional all the way down, secret-free, fail-closed.

not rated 3 1mo ago A tokens not measured original MIT

hive-test

5148

mattmre/EVOKORE-MCP-PUBLIC

Skill Claude CodeCodex

Iterative agent testing with session recovery. Execute, analyze, fix, resume from checkpoints. Use when testing an agent, debugging test failures, or verifying fixes without re-running from scratch.

not rated 3 4mo ago A 41 tokens original MIT

tony/skills

Skill Claude Code

Use when asked to brainstorm then refine, generate ideas then improve, or explore alternatives and synthesize the best one across passes.

not rated 3 +1 changed 5d ago A 34 tokens original MIT

tl

5150

ronaknnathani/relay

Skill Claude CodeCodex

Manage a Relay program as the CEO-facing tech lead: shape goals and contracts, prioritize dependency-aware work, dispatch senior worker agents, and surface every decision without writing production code or merging.

not rated 3 changed 8d ago A 39 tokens original MIT

agy-cli

5151

atharvakalele/Bridge

Skill Claude CodeCodex

Delegate coding work from Grok to Antigravity CLI via MCP agyrun. Grok-AG only. Use whenever the user wants AG, Antigravity, agy, or a detached worker — not Grok writing the files. Not for Cline or Claude.

not rated 3 14d ago A 59 tokens original MIT

mcp

5152

ratevert/mcp

MCP server Claude CodeCodexCursor +2

MCP server "mcp", hosted remotely at ratevert.com, as configured in ratevert/mcp.

not rated 3 13d ago A tokens not measured original MIT

pruvagraph

5153

PRUVALEX-Systems/PruvaGraph

MCP server Cursor

MCP server "pruvagraph" as configured in PRUVALEX-Systems/PruvaGraph. Launched with C:\Users\affan\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Pyth.

not rated 3 12d ago A tokens not measured original MIT

serena

5154

Riko5652/OCD

MCP server Cursor

MCP server "serena" as configured in Riko5652/OCD. Runs locally from the git+https://github.com/oraios/serena.git Python package.

not rated 3 12d ago A tokens not measured

sanction

5155

ericlovold/sanction

Plugin Cursor

Bundles 4 skills · 188 tokens together

Independent authorization plane for AI agents — approve, escalate, or deny spend, tools, credentials, and provisioning. Wires the hosted wallet MCP; the host must ask before acting.

not rated 3 yesterday A tokens not measured

frugal-subagents

5156

ikotelkin/claude-skills

Plugin Claude Code

Bundles 1 skill, 2 agents, 1 hook · 328 tokens together

On Claude Fable 5.1 (or Opus), Claude's helpers (subagents) inherit your expensive model and can start helpers of their own — one web research pass can burn a session's usage limit in minutes, and an instruction to be frugal doesn't survive context compaction. frugal-subagents builds the limits in: helpers run on a…

not rated 3 12d ago A tokens not measured original MIT

controlDesk

5157

dspace-group/ControlDeskMCP

MCP server Claude CodeCodexCursor +2

MCP server "controlDesk" as configured in dspace-group/ControlDeskMCP. Launched with ${workspaceFolder}/ControlDeskMCP.cmd. Needs 1 environment variable to run.

not rated 3 yesterday A tokens not measured original Apache-2.0

forum-route-preflight

5158

HarperZ9/forum

Skill Codex

Use Forum route preview, context preflight, runtime inspection, and prose contracts before continuing, decomposing, or dispatching agent work. Do not use for automatic execution or per-specialist wrappers.

not rated 3 yesterday A 44 tokens

autonomous-work

5159

oleg494/coding-kit

Skill Claude CodeCodex needs its repo

A skill for carrying out useful in-scope work when the user gives broad permission to act independently. It selects work, performs it, verifies the result, records what happened, and stops when no useful work remains.

not rated 3 +1 changed 5d ago A 118 tokens original MIT

phuetz/lm-resizer

Plugin Claude Code

Lists 1 plugin

Tools for AI coding agents by Patrice Huetz: lm-resizer (context budget), Code Explorer (codebase knowledge graph), Code Buddy (agent).

not rated 3 today A tokens not measured 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: