Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 436,613 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.

fortune

12961

ai-freer/fortune-skill

Skill Claude CodeCodex

A conversational tool for Chinese traditional fortune analysis using Bazi and Zi Wei Dou Shu, systems based on birth details and astrological charts.

not rated 44 changed 16d ago A 144 tokens

performance-monitor

12962

SoundDocs/sounddocs

Agent Claude Code

Use this agent when you need to monitor, analyze, or optimize system performance metrics. This includes:\n\n \nContext: User wants to track performance metrics after implementing a new feature.\nuser: "I just added a new real-time audio processing feature. Can you monitor its performance impact?"\nassistant: "I'll use…

not rated 44 5mo ago A 0 tokens

frameplanner

12963

jonigata/FramePlanner2

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "frameplanner", hosted remotely at localhost, as configured in jonigata/FramePlanner2.

not rated 44 5d ago A tokens not measured original MIT

tl

12964

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 44 changed 14d ago A 39 tokens original MIT

plan-decision

12965

juliusz-cwiakalski/agentic-delivery-os

Command Claude CodeOpenCode

Interactive decision planning session to prepare canonical context, classification, rigor, and decision rights for /write-decision. Supports all decision types (ADR/PDR/TDR/BDR/ODR).

not rated 44 +1 today A 39 tokens original MIT

junbolian/AdmitOR

Skill Claude CodeCodex

Model and solve traveling salesman problems using binary assignment and Miller-Tucker-Zemlin subtour elimination, with workflows for both integer programming and specialized routing solvers.

not rated 44 3d ago A 41 tokens original MIT

context-harness-agents

12968

parallax-labs/context-harness

Skill Codex

Set up and configure Context Harness standalone local agents, declarative tool bindings, and reusable agent workflows. Use when creating, validating, running, or debugging project agents; do not use for legacy MCP prompt-only personas unless migrating them.

not rated 44 +1 1mo ago A 52 tokens AGPL-3.0

shisan-xinuo-single

12969

zxc663/shisan-xinuo-workflow

Skill Claude CodeCodex

A single-file workflow that injects a set of rules and checks into coding-agent sessions. It covers task classification, required questions, approval gates, session memory, and routing across several agent platforms.

not rated 44 changed 1mo ago A 211 tokens original MIT

agent-verifier

12970

Aurite-ai/agent-verifier

Plugin Claude Code

Bundles 5 skills · 218 tokens together

Verifies AI agent code before it ships: hardcoded secrets, unbounded loops and retries, hallucinated tool references, oversized prompts, and language-specific quality checks. No telemetry.

not rated 44 changed 1mo ago A tokens not measured original MIT

e2e

12971

BlockedPath/pi-xai-oauth

MCP server Claude CodeCodexCursor +2

SDK, runner, and CLI for agentic end-to-end testing. Runs locally from the e2e npm package.

not rated 44 today A Socket: pass tokens not measured copy · 100% MIT

contract

12972

AbyssCN/oh-my-dag

Skill Claude CodeCodex

A way to turn agreed design decisions into a formal software design document. The document gives coding agents or other implementers goals, decisions, rules, dependencies, non-goals, and open questions.

not rated 44 1mo ago A 102 tokens original MIT

smartbear

12973

SmartBear/smartbear-mcp

Plugin Claude Code

Bundles 1 MCP server

Connects Claude to SmartBear tools, including BearQ, BugSnag, Collaborator, PactFlow, QMetry, QTM4J, Reflect, Swagger and Zephyr, through the SmartBear MCP server.

not rated 44 changed 7d ago A tokens not measured original MIT

branch-naming

12974

kprompt/kprompt

Cursor rule Cursor

Git branch naming convention for kprompt (type/kebab-summary[-issue]).

not rated 44 6d ago A 410 tokens original Apache-2.0

mcp-flight-search

12975

arjunprabhulal/mcp-flight-search

MCP server Claude CodeCodexCursor +2

MCP server that searches Google Flights through SerpApi. Runs locally from the mcp-flight-search Python package. Needs 1 environment variable to run.

not rated 44 yesterday A Socket: warn tokens not measured original MIT

molview-spec

12976

PDBeurope/PDBe-MCP-Servers

Skill Claude CodeCodex

Build or replace custom molecular views and guided molecular stories from provider-supplied structure sources with MolViewSpec, or explore PDBe-reported ligand interactions in the Molecular Workspace. Use for explicit visualization, representation, coloring, highlighting, ligand-contact, or story requests.

not rated 45 changed 5d ago A 57 tokens original Apache-2.0

mercury-is-agentic

12979

fiberfx/mercury

Skill Codex

Improve a website's agent readiness toward a verified Is Agentic 100/100 using structured PTE: audit evidence, prioritize justified changes, implement, test, publish within authorization, and rescan. Use for agent-readiness remediation, llms.txt discovery, agent-facing documentation and API contracts. Works with any…

not rated 44 12d ago A 84 tokens original MIT

niubiskill

12980

nathanskill/niubiskill

Skill Codex

Find the most valuable commercial insight and the monetization point closest to lawful revenue for a project, product, service, website, community, content account, open-source tool, or business idea. Use when a user asks how to monetize, who pays, why people do not buy, what to charge, whether to keep building, what…

not rated 43 26d ago A SkillSpector: pass 161 tokens original Apache-2.0

state-memory-mcp

12981

putervision/state-memory-mcp

Cursor rule Cursor

This project tracks workflow state, tasks, design decisions, and blockers using state-memory-mcp with project slug "state-memory-mcp".

not rated 43 +2 1mo ago A 883 tokens original MIT

PostToolUse

12982

aleclindz/seo-skill-bench

Hook Claude Code

One of 3 in settings.json

Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From aleclindz/seo-skill-bench.

not rated 43 1mo ago A tokens not measured original MIT

lean-memory

12983

Wuesteon/lean-memory

Plugin Claude Code

Bundles 5 commands, 1 MCP server · 82 tokens together

Local-first agent memory for Claude Code: an observing MCP that stores and searches memories, plus a read-only console to verify the supersession spine, score breakdown, and provenance episodes.

not rated 43 3mo ago A tokens not measured original Apache-2.0

monitoring-observability

12984

0xranx/agentbrief

Skill Claude CodeCodex

Set up monitoring, logging, and observability for applications and infrastructure. Use when implementing health checks, metrics collection, log aggregation, or alerting systems. Handles Prometheus, Grafana, ELK Stack, Datadog, and monitoring best practices.

not rated 43 7mo ago A 57 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: