Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 435,098 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.

org

13273

vincitamore/claude-org-template

Skill Claude CodeCodex

Copy this folder to /.claude/skills/org/ for global availability, or .claude/skills/org/ for project-specific.

not rated 41 1mo ago A 0 tokens original MIT

ashtanko/kotlin-app-template

Skill Claude CodeCodex

Use when writing or reviewing Kotlin code that stores CoroutineScope, launches from init/non-suspending APIs, calls runBlocking, or catches broad exceptions around suspend calls.

not rated 41 yesterday A SkillSpector: pass 42 tokens original Apache-2.0

korean-law

13275

lowtidebuild/consolidated-legal-research

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

A local MCP server for researching Korean law through 42 government APIs. It covers statutes, court decisions, local ordinances, treaties, tax interpretations, time-based comparisons, and guided legal research.

not rated 41 4mo ago A tokens not measured

iceberg-mcp

13277

ryft-io/iceberg-mcp

MCP server Claude CodeCodexCursor +2

An MCP server that interacts with Iceberg tables. Runs locally from the iceberg-mcp Python package.

not rated 41 1y ago A tokens not measured original Apache-2.0

general-project-rule

13278

yujiosaka/knowhub

Cursor rule Cursor

General project rules that applies to all file types. Should be most general.

not rated 41 1y ago A 0 tokens original MIT

mastering-langgraph

13279

SpillwaveSolutions/mastering-langgraph-agent-skill

Skill Claude CodeCodex

Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step…

not rated 41 3mo ago A 149 tokens

tdd-methodology-expert

13280

rawveg/skillsforge-marketplace

Skill Claude CodeCodex

Use proactively when you need to implement features or fix bugs using strict Test-Driven Development (TDD) methodology. This agent should be activated for any coding task that requires writing new functionality, refactoring existing code, or ensuring comprehensive test coverage, but should not be used for any…

not rated 41 9mo ago A 113 tokens

source-of-truth

13281

ngocquang/source-of-truth

Plugin Claude Code

Bundles 1 skill · 92 tokens together

A self-maintaining Spec-Driven Development (SDD) catalog skill that keeps a docs/ folder as the project's source of truth — read before touching code, sync after a feature ships.

not rated 41 changed 1mo ago A tokens not measured original MIT

canvas-cowork

13283

flowith-ai/canvas-cowork

Skill Claude CodeCodex

Work directly on the user's Flowith 3.0 canvas (画布): generate and edit images, videos, text, speech and music as cards, extend and vary them, upscale / cut out / expand, place uploads, and organise the canvas (group, arrange, link, rename) — the same way Flo, Flowith's in-app agent, does. Use for any Flowith / canvas…

not rated 41 changed today A 135 tokens original MIT

swing-skills

13284

TheStack-ai/swing-skills

Plugin Claude Code

Bundles 6 skills · 613 tokens together

6 cognitive firewalls for AI coding agents. Defends against premature closure, hallucination, anchoring bias, confirmation bias, black-box reasoning, and optimism bias.

not rated 41 6mo ago A tokens not measured original MIT

forge-foundation

13285

pan94u/forge

Plugin Claude Code

Bundles 16 skills, 6 commands, 4 agents, 2 MCP servers · 536 tokens together

Foundation plugin for the Forge platform providing Java/Kotlin conventions, Spring Boot patterns, testing standards, API design, security practices, and domain-specific guidance for enterprise application development.

not rated 41 +1 19d ago A tokens not measured

agentgem-miniapp

13286

ninemindai/agentgem

Skill Claude CodeCodex needs its repo

Use when building or editing an AgentGem miniapp / mini-game — the sealed, single-file HTML app under /.agentgem/miniapps/. Covers the seal, the host capability protocol, consent, privacy, and the sizing traps. Also read before changing the miniapp platform itself (packages/play, the host, the Play console surfaces) …

not rated 41 9d ago A SkillSpector: warn 85 tokens original MIT

skill-creator

13287

levante-hub/levante

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 41 6mo ago A 64 tokens

binder-modeling

13288

mpazik/Binder

Skill Claude Code

Binder data modeling — define entity types, fields, relations, constraints, views, and navigation. Use when asked to "create a type", "add a field", "define a schema", "set up relations", "model entities", "create a view", "set up navigation", "render entities as files", or design a binder workspace schema.

not rated 41 +1 changed 2mo ago A SkillSpector: pass 74 tokens original MIT

autumn

13289

yellow-hammer/skills-onescript

Skill Claude CodeCodex

A framework for building component-based OneScript applications, a scripting language related to 1C, with automatic dependency setup and annotations. It creates objects and supplies their required constructor values.

not rated 41 changed 1mo ago A 145 tokens original MIT

plan-execution-loop

13290

golid-ai/golid

Cursor rule Cursor needs its repo

Execute a docs/plans/.md slice with subagent implement → evidence-based audit → fix until 90+ — invoke manually when running a plan.

not rated 41 4mo ago A 29 tokens original MIT

README

13291

chrstian6/contractor

Agent Claude Code

One folder per agent. Claude Code loads .claude/agents//.md recursively, so the nesting is free; a file is only treated as an agent definition if its frontmatter carries a name:. Everything else in the folder is a co-located doc.

not rated 41 2mo ago A 0 tokens original MIT

skill-sanitizer

13292

cyberxuan-XBX/skill-sanitizer

Skill Claude CodeCodex

Skill "skill-sanitizer" from cyberxuan-XBX/skill-sanitizer, covering skill sanitizer, why you need this, the 7 layers, usage and in python.

not rated 41 4mo ago A ✓ AI review 0 tokens original MIT

cost

13293

maxvaega/awesome-skills

Skill Claude Code

Estimate what Claude Cowork / Claude Code conversations would cost if run on the pay-per-token Claude API instead of the subscription. Reports token counts and cache-aware API cost in USD and EUR, for the current conversation or for the whole history (cost per conversation). Trigger when the user asks things like "how…

not rated 41 changed 2mo ago A SkillSpector: warn 105 tokens original MIT

hermes-weixin-setup

13294

RongleCat/hermes-wechat

Skill Claude CodeCodex

A setup guide for connecting a personal WeChat account to Hermes Agent through WeChat's iLink Bot API, the interface used to exchange messages with the account.

not rated 41 7mo ago A 44 tokens original MIT

hand-compute

13295

gbasin/hand-compute

Skill Claude CodeCodex

Hand-computes a system's execution with explicit state at each step. Use when debugging races, state machines, async bugs, regressions; stress-testing a fix; scoping features on existing state; or approaching unfamiliar code. Especially useful for bugs involving client/server sequencing, background refreshes, recovery…

not rated 41 7mo ago A 108 tokens

tasks

13296

taoeffect/tasks

Skill Claude CodeCodex

Whenever the user says something like: 'Begin task: ' - always read this skill to understand how to proceed.

not rated 41 changed 7d ago B 28 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: