anthropic for Claude Code

16,144 mods tagged anthropic that install into Claude Code, measured the same four ways as everything else here: what each costs in tokens on every session, what a security scan found and why, whether it is the original, and what changed.

Also for Claude Code: Git and workflow · Web3 and blockchain · Python · React · TypeScript · docker · Go · Rust · Localization · nextjs · bun · PostgreSQL

indesign

986

LevyBytes/AI-SKILL-adobe-products

Skill Claude CodeCodex

Use when a task specifically concerns Adobe InDesign: InDesign documents, layouts, pages, spreads, frames, styles, publishing, UXP, or layout scripting; this is the product subskill routed from adobe-products.

not rated 5 +1 2mo ago A 0 tokens AGPL-3.0

TeamManagementPlugin/claude-plugin

Skill Claude CodeCodex

Systematic debugging — a four-phase root-cause methodology, boundary instrumentation for multi-component systems, the 3-fix escalation rule, and a verification gate to run before claiming anything is fixed. Use on any test failure, production bug, build failure, performance regression, or integration glitch, and…

not rated 5 1mo ago A 95 tokens original MIT

travel

988

tanayshah11/travel-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server "travel" as configured in tanayshah11/travel-mcp-server. Launched with travel-mcp serve.

not rated 5 4mo ago A tokens not measured

gia-mcp-server

989

knowledgepa3/gia-mcp-server

MCP server Claude CodeCodexCursor +2

Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping. Runs locally from the gia-mcp-server npm package.

not rated 5 17d ago A tokens not measured

harnessay

990

nks0614/harnessay

Plugin Claude Code

Bundles 1 skill · 58 tokens together

Profile your Claude Code transcripts: context budget report, skill-promotion candidates, and a skill regression test harness. Local-only, stdlib-only.

not rated 5 18d ago A tokens not measured original MIT

read-aloud

991

MichaelPGifford/claude-read-aloud

Plugin Claude Code

Bundles 6 skills, 1 hook · 58 tokens together

Read Claude's replies aloud — free system voices out of the box, premium voices (Speechify, ElevenLabs, OpenAI) with your own API key. Chunked playback starts speaking in seconds, even on long replies.

not rated 5 +2 yesterday A tokens not measured original MIT

llmprobe

992

Jwrede/llmprobe

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 51 tokens together

Synthetic monitoring for LLM inference endpoints. Measure TTFT, latency, throughput, and errors.

not rated 5 3mo ago A tokens not measured original MIT

cosmos-mcp

993

mrmos/cosmos-mcp

MCP server Claude CodeCodexCursor +2

Unofficial MCP server for cosmos.so. Search, browse and build visual moodboards with Claude, Cursor or any MCP client. Runs locally from the cosmos-mcp npm package.

not rated 5 +1 1mo ago A tokens not measured original MIT

cowork-starter-pack

994

TheCraigHewitt/cowork-starter-pack

Plugin Claude Code

Bundles 7 skills · 516 tokens together

Seven universal skills, context file templates, global instructions, and a curated prompt library for Claude Co-work. Built for knowledge workers across roles — EAs, marketers, operators, founders, analysts.

not rated 5 +2 4mo ago A tokens not measured original MIT

trailhead

995

ToRvaLDz/trailhead

Plugin Claude Code

Bundles 6 skills, 21 commands, 8 agents, 3 hooks · 1,258 tokens together

Start and drive large projects as a map of tickets on GitHub Issues, resolving one at a time. Map-based onboarding + a discuss→plan→execute→verify engine with atomic commits, all on the Issues. Ships as a dispatcher plus cohesion-clustered skills over a shared core; depends on nothing beyond an authenticated gh CLI.

not rated 5 changed 4d ago A tokens not measured original MIT

documentation-guide

996

ValorVie/custom-skills

Skill Claude CodeCodex needs its repo

A guide for organizing project documentation such as README files, architecture notes, API references, and deployment instructions. It covers what different kinds of projects should document.

not rated 5 5d ago A 66 tokens original MIT

drawio-skill

997

tuoxie2046/claude-code-research-skills

Skill Claude CodeCodex

Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, network topology, ML/DL model figures (Transformer/CNN/LSTM), mind maps, or any visualization. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that…

not rated 5 2mo ago A 120 tokens

yellow-sheet-corpus

998

shawnclybor/clybor-claude-tooling

Skill Claude CodeCodex

Run the Yellow Sheet chain end to end against ANY matter, from the original PDFs, and read the result honestly. Use whenever someone asks what has been tested end to end, whether a matter produces a usable sheet, how to onboard a NEW matter, or asks to re-run after a code change. Carries the intake mechanism that…

not rated 5 8d ago A 173 tokens

finance-oracle

999

vignesh2027/Claude-Agentic-Skills2.0-version

Skill Claude CodeCodex

Activates FinanceOracle — the most comprehensive institutional finance intelligence agent ever built for Claude. Use when you need Goldman Sachs + Bridgewater + Citadel-level analysis: Black-Scholes options pricing, Black-Litterman portfolio construction, fixed income duration/ convexity, hedge fund strategy design…

not rated 4 +2 15d ago A 102 tokens original MIT

tokenscope

1000

wartzar-bee/tokenscope

MCP server Claude CodeCodexCursor +2

Analyze Claude Code session cost & context attribution: output, cached re-reads, cache writes. Runs locally from the @wartzar-bee/tokenscope-mcp npm package.

not rated 4 1mo ago A tokens not measured original MIT

burnd-analyze-spend

1002

garvitsurana271/burnd

Skill Claude CodeCodex

Analyze your OpenClaw API spend — total cost, cost last 7 days, top cost leaks by model and provider, and concrete steps to reduce your bill. Use when the user asks about their AI spending, costs, budget, or which models are costing the most.

not rated 4 1mo ago A 62 tokens original MIT

boostu-teamleader-mcp

1003

boostuagency/boostu-teamleader-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Teamleader Focus CRM. Use Teamleader in Claude and other AI assistants. Runs locally from the boostu-teamleader-mcp npm package. Needs 5 environment variables to run.

not rated 4 10d ago A tokens not measured original MIT

mcp-relay

1004

mhcoen/mcp-relay

MCP server Claude CodeCodexCursor +2

MCP relay server for Claude Desktop Claude Code communication. Runs locally from the mcp-server-relay Python package.

not rated 4 7mo ago A tokens not measured original MIT

five46

1005

sekharsdet/five46

MCP server Claude CodeCodexCursor +2

BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success. Runs locally from the five46 npm package. Needs 5 environment variables to run.

not rated 4 15d ago A tokens not measured original MIT

memory

1006

SomeStay07/claude-memory-skill

Skill Claude Code

Unified project memory management: update, prune, reflect, and maintain knowledge. Combines conversation scanning, deduplication, contradiction detection, confidence scoring, and consistency checks in a single skill. Usage: /memory update [topic] — scan conversation, persist learnings /memory prune [type] — find…

not rated 4 6mo ago A 130 tokens original MIT

caliber

1007

JordanGrothentic/caliber

Skill Claude Code

Recommends which Claude model and effort level to fit a task, using cost of error as the deciding signal. Use when asked which Claude model or effort to use, or a task feels over or underpowered.

not rated 4 2mo ago A 46 tokens original MIT

build-dna

1008

Sudiddii/build-DNA

Skill Claude Code

Build-DNA is a Claude skill that turns your skills, experiences, and unfair advantages into a business. Not another idea generator — your personal business brain. Use when someone wants to find a business idea, validate a startup concept, brainstorm products during a hackathon, figure out what to build as a side…

not rated 4 3mo ago A 199 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: