Claude Code

81,493 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

vdesign

3385

phamcuong21478/rtl-skills

Skill Claude Code

Generate a design proposal, documentation, and RTL backbone from a requirement file.

not rated 21 5mo ago A 17 tokens original Apache-2.0

yoonmoon

3386

amondnet/yoonmoon

Plugin Claude Code

Bundles 6 skills · 1,615 tokens together

A collection of tools for editing and checking Korean writing. It can proofread spelling and grammar, improve unnatural or translated-sounding phrasing, change style and tone, and detect signs of AI-written text.

not rated 21 +2 2mo ago A tokens not measured original MIT

engram

3387

rwnalds/engram

MCP server Claude CodeCodexCursor +2

MCP server "engram" as configured in rwnalds/engram. Runs in Docker (ghcr.io/rwnalds/engram:0.1.2).

not rated 21 +1 3mo ago A tokens not measured original MIT

etsy-seo

3388

abutun/etsy-seo-optimizer

Skill Claude Code

Etsy shop SEO optimization toolkit. This skill should be used when the user asks to "analyze my Etsy shop", "optimize my Etsy listings", "check my Etsy SEO", "audit Etsy tags", "improve my Etsy sales", "compare Etsy competitors", "update Etsy listing", or mentions anything related to Etsy shop optimization, listing…

not rated 21 7mo ago A 110 tokens

learn-anything

3389

Nar101/learn-anything

Skill Codex

A source-grounded adaptive tutor that tracks proof of mastery rather than content completion. Use it to learn a topic systematically, build a course from PDFs, webpages, transcripts or notes, practice retrieval and transfer, resume a long-running course, or verify whether the learner can recall and apply what they…

not rated 21 3mo ago A 162 tokens original MIT

concise

3390

o4f6bgpac3/concise

Plugin Claude Code

Bundles 1 skill · 92 tokens together

Concise communication mode. Cuts 60-70% of tokens while keeping natural, readable English.

not rated 21 +1 7mo ago A tokens not measured original MIT

mcp-microsoft-todo

3391

MAG-Cie/mcp-microsoft-todo

MCP server Claude CodeCodexCursor +2

MCP server for Microsoft To Do via Microsoft Graph. MSAL device code flow, no client secret needed. Runs locally from the @mag-cie/mcp-microsoft-todo npm package. Needs 2 environment variables to run.

not rated 21 +2 6mo ago A tokens not measured original MIT

crucible

3392

smshahbaj/crucible

Plugin Claude Code

Bundles 1 skill, 1 command, 14 agents · 560 tokens together

A user-friendly adaptive second-opinion skill for Claude Code. For important decisions, plans, strategies, proposals, architecture, and recommendations: frame the real goal, verify decision-critical evidence, pressure-test the biggest risk, compare alternatives, and stop when more reasoning will not change the action.

not rated 21 +10 2mo ago A tokens not measured original MIT

thinking-toolkit

3393

ponomr/thinking-toolkit

Skill Codex

Apply a named Thinking Toolkit model or audit an argument with /logic. Use only when the user explicitly invokes the toolkit, names an included model or alias, or invokes /logic.

not rated 21 +2 changed 1mo ago A 40 tokens original MIT

omakase-router

3394

rblalock/omakaseagent

Skill Claude Code

Omakase fallback router (plan, init, taste, handoff only). NOT for engineering/critique/archivist — use native agents @omakase-engineer @omakase-critic @omakase-archivist. Never load when user @mentions omakase- (that prefix is reserved for native agents, not this skill).

not rated 21 2mo ago A 79 tokens

windbg-mcp

3395

glslang/windbg-mcp

Plugin Claude Code

Bundles 10 skills, 1 MCP server · 891 tokens together

WinDbg/DbgEng debugging: crash dumps, live user-mode and kernel, Time Travel Debugging (TTD), and Secure Kernel (VTL1) capture inspection and disposable live control — MCP server plus skills that drive it: WinDbg debugging and MSRC patch comparison.

not rated 21 +1 changed 7d ago A tokens not measured original MIT

anti-slop-design

3396

Ferousco-dev/anti-slop-design

Plugin Claude Code

Bundles 1 skill · 138 tokens together

Eliminates generic AI-generated design from any front-end you build or review, web or mobile. 20 reference modules: the slop taxonomy, personality axes and product registers, mobile and app-screen patterns, trust signals, data visualisation, a craft list, a pre-emit checklist and a worked example.

not rated 21 1mo ago A tokens not measured original MIT

research

3397

eddiebelaval/squire

Command Claude Code

You are the orchestrator for the id8Labs Research Lab at /Development/id8/research-lab/.

not rated 21 2mo ago A 0 tokens original MIT

birlesme-devralma-ma

3398

aydincan/turk-hukuku-ve-claude

Plugin Claude Code

Bundles 12 skills · 822 tokens together

Birleşme-devralma işlemleri: hukuki durum tespiti (due diligence), pay/varlık devri yapıları, pay alım satım sözleşmesi (SPA), beyan ve tekeffüller, kapanış şartları ve işlem sonrası entegrasyon; ihtiyaç halinde rekabet izni.

not rated 21 changed 28d ago A tokens not measured original Apache-2.0

security-scan

3399

Ray0907/security-scan

Plugin Claude Code

Bundles 1 skill · 35 tokens together

Use when a user asks to scan a repository for dependency vulnerabilities, insecure code patterns, CVEs, or OWASP Top 10 risks.

not rated 21 +1 changed 2d ago A tokens not measured original MIT

hcom-spawn

3400

ouob-tw/LoopAgentTeams

Skill Claude CodeCodex

An instruction set for starting and coordinating other coding agents through HCOM, a system for agents to communicate and work together. It covers choosing an agent, giving it a task, monitoring it, and ending the collaboration.

not rated 21 +1 today A 80 tokens original MIT

Curate

3401

dean0x/devflow

Agent Claude Code

Background agent that processes the pending curation queue into the decisions ledger. Spawned by the session-start directive when the queue is non-empty.

not rated 21 changed 12d ago A 31 tokens original MIT

wpfvisualtreemcp

3402

faze79/WPFVisualTreeMcp

Skill Claude CodeCodex

Inspect and interact with running Windows WPF applications using the WPF Visual Tree MCP. Use for visual-tree inspection, binding/style diagnosis, diagnostic reports, screenshots, mouse dragging, touch gestures, recording/replaying workflows and exporting xUnit regression tests, or updating this plugin's server/skill.…

not rated 21 changed 19d ago A 85 tokens original MIT

yandex-direct-for-all

3403

nebelov/yandex-direct-for-all

Plugin Claude Code

Bundles 19 skills, 3 MCP servers · 1,212 tokens together

A portable toolkit for Yandex Direct advertising, Yandex Metrika measurement, and Wordstat keyword research, with optional XMLRiver search data, Roistat, and amoCRM connections. Yandex Direct is an ad platform, while Metrika measures website activity and Wordstat shows search demand.

not rated 21 today A tokens not measured original MIT

crow-diagnose

3404

corveil/crow

Skill Claude CodeCodex

Turn one observation into a diagnosed ticket or epic that meets Crow's ticket standard, or into an outcome that isn't a ticket (duplicate, commitment, needs info, won't do). The observation can be a Corveil FollowUp, a meeting and a time, a Slack permalink, a Scratch item, an issue to re-diagnose, or plain text. Reads…

not rated 21 +1 changed yesterday A 168 tokens original Apache-2.0

applied-micro

3405

kennethkhoocy/applied-micro-skills

Plugin Claude Code

Bundles 17 skills · 2,984 tokens together

Claude Code skills for empirical applied-micro research: reproducibility auditing, LLM-pipeline methods, event studies, WRDS, Stata, publication-grade tables.

not rated 20 2mo ago A tokens not measured copy · 86% MIT

sitrep-panel

3406

dbl8005/sitrep-panel

Plugin Claude Code

Bundles 1 skill · 101 tokens together

A live local HTML report Claude keeps updated as it works — status board, running narrative, screenshots, newest-first log — so you can watch progress without reading the transcript.

not rated 20 2mo ago A tokens not measured original MIT

challenge

3408

grainulation/wheat

Command Claude Code

You are stress-testing a specific claim by researching the strongest possible counter-argument with real evidence. Read CLAUDE.md for sprint context and claims.json for existing claims.

not rated 20 6mo ago A 0 tokens original MIT archived

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: