Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 432,992 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.

mcp

4801

Snowflake-Labs/mcp

MCP server Claude CodeCodexCursor +2

MCP server for Snowflake. Runs locally from the snowflake-labs-mcp Python package. Needs 13 environment variables to run.

not rated 303 5mo ago A tokens not measured original Apache-2.0

Meet-Miyani/compose-skill

Cursor rule Cursor

Token-optimized writing standards for skill reference files. Apply when creating or editing reference .md files in a skill's references/ directory.

not rated 303 +1 changed 23d ago A 0 tokens original MIT

runtm-ai/runtm

Instructions file GitHub Copilot

Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.

not rated 303 +1 today A ✓ AI review 297 tokens

claude-canvas

4804

AgriciDaniel/claude-canvas

Plugin Claude Code

Bundles 8 skills, 1 command, 3 agents · 1,223 tokens together

AI-orchestrated visual production for Obsidian Canvas. Create presentations, flowcharts, mood boards, knowledge graphs, and galleries with intelligent layout and AI-generated content.

not rated 303 +1 7mo ago A tokens not measured original MIT

context-management

4806

ttttmr/pi-context

Skill Claude CodeCodex

Use this skill for multi-turn, phased, or noisy work: research/reading, debugging, plan-then-execute, retries/pivots, background or asynchronous work, handoffs, user decisions, task switching, repeated items, or repeated progress checks. It keeps the conversation as a clean working set with checkpoints, timeline…

not rated 303 +1 changed 24d ago A 112 tokens

nopus

4807

Vistyy/nopus

Plugin Claude Code

Bundles 2 skills, 1 hook · 52 tokens together

Uses deterministic prose checks to flag overly complex coding-agent responses and ask for one clearer rewrite.

not rated 303 +3 2mo ago A tokens not measured original MIT

tare

4808

kelviq/tare

Plugin Claude Code

Bundles 1 skill, 1 command · 284 tokens together

Ask Claude Code where your usage went: diagnose 5-hour and weekly limits, find which tool, model or project eats your quota, and detect background automation — all from the session logs already on disk.

not rated 304 2mo ago A tokens not measured original MIT

filescope-mcp

4809

admica/FileScopeMCP

Skill Claude CodeCodex

Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search. Use when navigating unfamiliar code, planning refactors, assessing change impact, or finding entry points in a large project.

not rated 302 6mo ago A 50 tokens

prp-mcp-create

4810

coleam00/remote-mcp-server-with-auth

Command Claude Code

This command is designed to create a comprehensive Product Requirement Prompt (PRP) for building Model Context Protocol (MCP) servers referencing this codebase patterns mirroring tool setups for the users specific requirements.

not rated 302 1y ago A 46 tokens copy · 86% MIT

emulo

4812

ohad6k/emulo

Plugin Claude Code

Bundles 8 skills, 1 MCP server · 489 tokens together

Mine real AI coding sessions into a bounded, evidence-backed personal layer.

not rated 302 +1 changed 1mo ago A tokens not measured original MIT

moq-kit

4813

software-mansion-labs/skills

Skill Claude CodeCodex

Software Mansion's moq-kit — native Swift (iOS) and Kotlin (Android) SDKs for Media over QUIC (moq-lite) live streaming: sub-second-latency playback, camera/microphone/screen publishing, and realtime data tracks over a MoQ relay. MUST USE before writing, reviewing, or debugging ANY code that imports MoQKit (Swift) or…

not rated 302 +4 4d ago A 200 tokens

rag-index-decisions

4815

lyonzin/knowledge-rag

Skill Claude CodeCodex

After making a non-obvious architectural decision, solving a novel bug, agreeing on a coding standard, or reaching a conclusion worth remembering, index it back into the knowledge base so the next occurrence is one search away. Uses adddocument or addfromurl. Closes the feedback loop that makes a RAG-backed team…

not rated 303 +3 changed yesterday A SkillSpector: pass 72 tokens original MIT

bloom

4816

Li-Evan/Bloom

Plugin Claude Code

Bundles 7 skills · 994 tokens together

A personal AI tutor based on Bloom's 2-sigma research: it generates a structured syllabus, teaches one adaptive lesson at a time, and tailors each next lesson to the learner's highlights and feedback. Bundles the bloom-tutor tutoring skill plus six learn- learning-method skills.

not rated 302 +8 19d ago A tokens not measured original MIT

content-planner

4817

bradautomates/head-of-content

Skill Claude Code

Orchestrate comprehensive content research across X, Instagram, YouTube, and TikTok platforms. Runs all research skills in parallel via subagents, then aggregates findings into actionable content plans and platform-specific intelligence playbooks. Use when asked to: Create a content plan for social media Research…

not rated 305 +10 9mo ago A 150 tokens original MIT

qiaomu-blog-publish

4818

joeseesun/qiaomu-blog-opensource

Skill Claude Code

A publishing workflow for sending Markdown, text, or a web page to a Qiaomu Blog, with category and draft or published status controls.

not rated 302 +1 changed 1mo ago A 37 tokens original MIT

decoupler

4820

scverse/decoupler

Skill Claude CodeCodex

Read before any task that mentions decoupler, one of its bundled example datasets, or asks which transcription factors (TFs), pathways, or gene sets are most active, enriched, up or down in expression data - bulk RNA-seq treated vs control, single-cell cell types or clusters, condition contrasts across donors…

not rated 301 +1 changed 12d ago A SkillSpector: pass 192 tokens original BSD-3-Clause

test-scripts

4821

ivo-toby/mcp-openapi-server

Cursor rule Cursor

Never try to run a test-script from commandline using node -e. This will always fail, you'll need to write a typescript test file, build that and execute that.

not rated 301 +1 2d ago A 49 tokens original MIT

leanspec

4822

codervisor/leanspec

Skill Claude CodeCodex

The spec-coding methodology for AI-assisted development. Use when planning features, creating/refining/implementing/verifying specs, or organising a project. Works with whatever spec backend your team already uses — local markdown, GitHub Issues, Azure DevOps, Jira — by delegating platform-specific details to a…

not rated 301 +1 5mo ago A Socket: passSnyk: warnSkillSpector: pass 68 tokens original MIT

pavel-molyanov/molyanov-ai-dev

Agent Claude Code

Reviews user-spec document quality: structure, interview coverage, behavioral clarity, verification, edge-case presence, contradictions, and template compliance. Use when: the user-spec is ready for pre-approval document review; solution adequacy and factual codebase claims are out of scope.

not rated 301 +1 changed 18d ago A 60 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: