anthropic for Claude Code

16,365 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 · Localization · Rust · nextjs · bun · PostgreSQL

profile

289

Flemma-Dev/flemma.nvim

Skill Claude Code

Use when asked to profile Flemma performance, compare keystroke latency between branches, or run the profiling harness. Trigger on "profile", "perf", "benchmark", "keystroke latency", or "InsertCharPre".

not rated 57 1mo ago C 48 tokens AGPL-3.0

wrap

290

ViryaZheng/wrap-skill

Plugin Claude Code

Bundles 1 skill · 187 tokens together

Consolidate scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at the top.

not rated 56 3mo ago A tokens not measured original MIT

standards-kotlin

291

b33eep/claude-code-setup

Skill Claude CodeCodex

Kotlin coding standards for modern applications. Includes naming conventions, coroutines, flows, modern Kotlin 2.3.0 features, and recommended tooling.

not rated 56 3mo ago A 36 tokens original MIT

webfetch

292

firish/webfetch

Plugin Claude Code

Bundles 1 MCP server

Own your LLM's web search: websearch, fetchurl, and savefinding tools backed by a local search -> fetch -> rank pipeline with semantic caching - up to 8x fewer input tokens and 3x lower cost than hosted web search.

not rated 55 1mo ago A tokens not measured original MIT

smart-connections-mcp

294

msdanyg/smart-connections-mcp

MCP server Claude CodeCodexCursor +2

Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private. Runs locally from the smart-connections-mcp npm package. Needs 1 environment variable to run.

not rated 55 18d ago A tokens not measured original MIT

byok-relay

295

avikalpg/byok-relay

Skill Claude CodeCodex

OpenAI-compatible LLM gateway for any client-side application (browser, mobile, React Native, Flutter, VS Code extensions, browser extensions, Electron, smart TV, and more). Routes requests to OpenAI, Anthropic, Gemini, Groq, Mistral, and 200+ models, handling CORS, key encryption, and streaming without a dedicated…

not rated 55 +1 yesterday A SkillSpector: warn 131 tokens original Apache-2.0

cubepi-trace

297

cubeplexai/cubepi

Skill Claude CodeCodex

Use when debugging a cubepi/cubebox agent run — a missing final reply, a tool that misbehaved, a 4xx from the model, wrong token/cache numbers, or "why did the agent do that?". Reads the JSONL traces cubepi writes per run via the cubepi trace CLI (ls / view / follow / stats) to inspect the span tree, errors, tool…

not rated 53 +10 4d ago A SkillSpector: warn 129 tokens original MIT

council-review

298

SamJHudson01/Carmack-Council

Skill Claude CodeCodex

Perform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review", "carmack review", or invoke /council-review. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js)…

not rated 52 5mo ago A 166 tokens original MIT

ruflo-token-audit

299

pacphi/agentic-kit

Skill Claude Code

Use when the user asks where their Claude Code usage/tokens are going, is burning through their plan unexpectedly fast, hitting limits, or wants a breakdown of their Claude Code activity. Produces a COMPREHENSIVE usage report from local session transcripts: tokens by day/model/project, tool usage, MCP usage, subagent…

not rated 52 today A SkillSpector: pass 105 tokens original MIT

fable-native-code

300

DizzyMii/fable-skills

Skill Claude CodeCodex

Use when writing or editing code in an existing codebase — before adding comments, docstrings, try/catch blocks, validation, logging, or TODOs the surrounding file doesn't have, and before explaining your style choices in the reply.

not rated 51 1mo ago A SkillSpector: pass 52 tokens original MIT

huntkit

302

assafkip/huntkit

Plugin Claude Code

Bundles 3 skills, 22 commands, 2 hooks · 400 tokens together

Investigation toolkit for Claude Code. Case management, OSINT, structured analytic techniques (Heuer / CIA tradecraft primer), chain-of-custody evidence capture, and bundled MCP servers for infrastructure recon and threat intel.

not rated 51 4d ago A tokens not measured original MIT

rubber-duck-tutor

303

LeeJuOh/claude-code-zero

Plugin Claude Code

Bundles 6 skills · 458 tokens together

Rubber duck tutor that keeps you sharp across the whole AI-coding lifecycle, not just after code lands: /duck-prebuild before you ask AI to build, /duck-verify and /duck-review once it's written and before you ship, /duck-orient when you're new to a codebase, plus /duck for auto-detect. /coach is its teaching sibling…

not rated 51 3d ago A tokens not measured original MIT

wps-ai

304

lewis-hui1202/WPS-AI

Skill Claude CodeCodex needs its repo

A connection between an AI agent and WPS Office, the Chinese office suite, for reading, writing, and formatting documents. It runs through the WPS-AI plugin and can be controlled remotely from a Windows computer, including from an agent on a NAS.

not rated 51 +1 29d ago A SkillSpector: pass 50 tokens original MIT

cc-best

306

xiaobei930/cc-best

Plugin Claude Code

Bundles 19 skills, 44 commands, 8 agents, 20 hooks · 1,793 tokens together

Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 20 events, auto-learning pipeline, hook profiles, and multi-language coding standards.

not rated 50 2mo ago A tokens not measured original MIT

lazy-cat

307

albertobarnabo/lazy-cat

Plugin Claude Code

Bundles 2 skills, 2 commands · 328 tokens together

Two skills that eliminate the two biggest sources of token waste: think-twice (pick the cheaper approach before starting) and surgical (build only what was asked, nothing more). The best tokens are the ones you didn't spend.

not rated 50 2mo ago A tokens not measured original MIT

codex-delegate

308

congmnguyen/claude-code-wsl2-setup

Agent Claude Code

Delegate a well-specified implementation, refactor, migration, or bulk-mechanical coding task to the configured Codex CLI model and return ONLY a compact summary. Keeps Codex's large transcript out of the orchestrator's context. Use for multi-step tasks; not for tiny one-shot edits.

not rated 50 +2 yesterday A 64 tokens original MIT

claude-docs

309

costiash/claude-code-docs

Plugin Claude Code

Bundles 5 skills, 1 hook · 567 tokens together

Searchable local index of Claude documentation. Provides the /docs command for instant access to API references, guides, and tutorials. Auto-discovery Skill reads docs automatically when you ask Claude-related questions. Docs auto-update via SessionStart hook.

not rated 49 today A tokens not measured

knoxhub-blog

310

rediumvex/seo-blog-writer-claude

Skill Claude Code

Transform any research material into SEO+GEO-optimized blog posts for Knox Hub. Takes any input (URL, article text, notes, video transcript, competitor post, topic idea) and rewrites it as natural human-sounding content, then fills in all fields for the Knox Hub post editor: title, excerpt, SEO settings, FAQ schema…

not rated 49 28d ago A 151 tokens original MIT

odoo-rpc

311

rosenvladimirov/odoo-claude-mcp

MCP server Claude CodeCodexCursor +2

One of 4 in .mcp.json

MCP server "odoo-rpc", hosted remotely at odoo-rpc-mcp, as configured in rosenvladimirov/odoo-claude-mcp.

not rated 49 5d ago A tokens not measured AGPL-3.0

perplexity-comet-mcp

312

RapierCraft/Perplexity-Comet-MCP

MCP server Claude CodeCodexCursor +2

Bridge Claude Code with Perplexity Comet for autonomous browsing and tab management. Runs locally from the perplexity-comet-mcp npm package. Needs 2 environment variables to run.

not rated 48 +1 2mo ago A tokens not measured 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: