Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 435,263 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.

xhs-publish

1513

autoclaw-cc/xiaohongshu-skills

Skill Claude CodeCodex needs its repo

A Xiaohongshu publishing workflow for preparing and publishing image posts, videos, or long articles through a project-specific command-line script. Xiaohongshu is a Chinese social media and lifestyle platform.

not rated 2.0k +20 5mo ago A SkillSpector: pass 59 tokens original MIT

setup

1514

nimbalyst/nimbalyst

Skill Claude CodeCodex

Create a project wiki with a useful Home, starter pages, and a writing guide.

not rated 2.0k +18 changed 22d ago A 19 tokens original MIT

debugger

1515

Doorman11991/smallcode

Agent Claude Code

Systematic root-cause diagnosis — reproduce, hypothesize, test, fix, verify.

not rated 2.0k +1 2mo ago A 21 tokens original MIT

weft-node-authoring

1516

WeaveMindAI/weft

Skill Claude Code

Read before dispatching a node-smith (the brief and the review) and when an expert writes a node by hand: the node authoring manual, the test tiers, and the shapes half-done work takes. The node-smith reads this same file as its manual.

not rated 2.0k +9 changed 3d ago A 62 tokens

timoni

1517

stefanprodan/timoni

Skill Claude CodeCodex

Use when deploying applications to Kubernetes with Timoni. Covers installing and upgrading module instances from OCI registries, composing multi-app deployments with bundles, injecting values from clusters or CI with runtimes, targeting multiple clusters, and authoring, testing, signing and publishing modules with CUE.

not rated 2.0k +1 changed 2mo ago A SkillSpector: warn 59 tokens original Apache-2.0

natural-japanese

1519

coji/natural-japanese

Plugin Claude Code

Bundles 2 skills · 746 tokens together

A Japanese-language writing and editing skill for business documents, reports, guides, research notes, slides, blogs, and essays.

not rated 2.0k +19 changed yesterday A tokens not measured original MIT

release-plugin

1520

flutter/flutter-intellij

Skill Claude CodeCodex

Prepare and execute a new release for the flutter-intellij plugin, including updating dependencies, compatibility bounds, changelogs, and verification.

not rated 2.0k yesterday A SkillSpector: pass 30 tokens original BSD-3-Clause

harbor

1521

AntigmaLabs/ante

Skill Claude CodeCodex

Run Terminal-Bench or any Harbor dataset with Ante as the agent, using the Harbor adapter in the ante repo's ante-harbor/ directory. Use when the user wants to benchmark Ante on Harbor or reproduce Ante's published eval results.

not rated 2.0k +6 yesterday A SkillSpector: pass 51 tokens original Apache-2.0

aipoch/medical-research-skills

Skill Claude CodeCodex

Generate structured SOAP notes from clinical narratives, transcripts, or existing notes; use when the user needs de-identified clinical documentation organized into Subjective, Objective, Assessment, and Plan sections, with clear assumptions and review points.

not rated 2.0k +16 1mo ago A SkillSpector: pass 51 tokens original MIT

dmmulroy/better-result

Skill Claude CodeCodex

Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.

not rated 2.0k +2 2mo ago A SkillSpector: pass 52 tokens original MIT

skill-creator

1525

openakita/openakita

Skill Codex

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 2.0k +3 1mo ago A SkillSpector: warn 64 tokens AGPL-3.0

baml

1526

ai-that-works/ai-that-works

Cursor rule Cursor

A set of rules for setting up BAML and help with syntax guidance.

not rated 2.0k +2 11d ago A 2,551 tokens

memorax-code

1527

memorax-ai/memorax-code

Skill Codex

Use this skill as the single router for persistent coding, repository-local, and user-global personal memory. Invoke it whenever a request may involve prior-work knowledge, repository memory, reusable procedures or rules, durable profile or interaction preferences, or information worth retaining beyond the current…

not rated 2.0k +3 changed 17d ago A SkillSpector: pass 178 tokens original MIT

kotlin-footguns

1528

maxrave-dev/kotlin-footguns

Plugin Claude Code

Bundles 11 skills · 638 tokens together

228 battle-tested traps mapping the footguns of Kotlin, Compose Multiplatform and desktop JVM development, in ten area skills plus a scanner that checks a change against them. Mined from SimpMusic, a production cross-platform app shipping since 2023; traps-first, with verification commands that were executed against…

not rated 2.0k +162 changed 19d ago A tokens not measured GPL-3.0

start9-frontend

1529

Start9Labs/start-technologies

Skill Claude Code

Start9 house style for every Angular + Taiga UI web frontend (StartOS ui/setup-wizard, StartWRT, StartTunnel, brochure-marketplace, start9-store, ops-server, support-server, start-equity). Use BEFORE writing or reviewing any frontend code in these apps — components, templates, styles/CSS, forms, dialogs/toasts…

not rated 2.0k +1 changed 7d ago A SkillSpector: warn 133 tokens original MIT

stock-api

1530

zhangxiangliang/stock-api

Skill Claude CodeCodex

Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets. Use when the user asks for a stock price, a quote, market data, candlestick/K-line data, or to look up a stock code by company name.

not rated 2.0k +7 yesterday A 66 tokens original MIT

telegram-mcp

1531

chigwell/telegram-mcp

MCP server Claude CodeCodexCursor +2

MCP server "telegram-mcp" as configured in chigwell/telegram-mcp. Launched with /PATH-TO/uv --directory /PATH-TO/telegram-mcp run main.py.

not rated 2.0k +51 7d ago A tokens not measured original Apache-2.0

codebase-memory-mcp

1532

jeffbski/wait-on

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server "codebase-memory-mcp" as configured in jeffbski/wait-on. Launched with mise exec -- codebase-memory-mcp.

not rated 2.0k 5d ago A tokens not measured original MIT

Sentry

1534

reactnativecn/react-native-update

MCP server Claude CodeCodexCursor +2

Sentry's hosted MCP server: lets the agent search and read issues, errors and traces. Remote server at mcp.sentry.dev.

not rated 2.0k +1 today A tokens not measured

test-writer-fixer

1536

composio-community/awesome-claude-plugins

Plugin Claude Code

Bundles 1 agent · 0 tokens together

Use this agent when code changes have been made and you need to write new tests, run existing tests, analyze failures, and fix them while maintaining test integrity. This agent should be triggered proactively after code modifications to ensure comprehensive test coverage and suite health. Examples:\n\n \nContex.

not rated 2.0k +6 2d ago A tokens not measured

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: