Claude Code

81,390 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.

kalshi-mcp-server

7369

cejor6/kalshi-mcp-server

MCP server Claude CodeCodexCursor +2

Model Context Protocol server for Kalshi prediction markets — native RSA-PSS auth, token-bucket rate limiting, demo/prod safety controls. Runs locally from the kalshi-mcp-server Python package. Needs 6 environment variables to run.

not rated 3 yesterday A tokens not measured original MIT

uniprot-mcp

7371

smaniches/uniprot-mcp

MCP server Claude CodeCodexCursor +2

Verifiable, release-aware protein evidence workflows over UniProt and linked scientific sources. Runs locally from the uniprot-mcp-server Python package.

not rated 3 4d ago A tokens not measured original Apache-2.0

lsp-mcp

7372

theUpsider/lsp-mcp

MCP server Claude CodeCodexCursor +2

Universal LSP MCP server. Runs locally from the @theupsider/lsp-mcp npm package.

not rated 3 8d ago A tokens not measured

sourcebook

7373

maroondlabs/sourcebook

MCP server Claude CodeCodexCursor +2

Extract the conventions, constraints, and architectural truths your AI coding agents keep missing. Runs locally from the sourcebook npm package.

not rated 3 7mo ago A tokens not measured

openakashic

7374

szara7678/OpenAkashic

Skill Claude CodeCodex

Find practical know-how by situation and goal in OpenAkashic and read exact method versions, conditions, source evidence, execution reports and corrections. Public access is read-only; owner-only writes require separately authorized private API access. Closed Akashic personal memory is separate.

not rated 3 changed 10d ago A 58 tokens original Apache-2.0

norn

7375

samad001z/Norn

MCP server Claude CodeCodexCursor +2

Norn MCP server with remember, recall, forget, and list tools over stdio. Runs locally from the @samad001z/norn-server npm package.

not rated 3 4mo ago A tokens not measured original MIT

xv6-riscv-expert

7376

shafin027/xv6-riscv-skill

Skill Claude CodeCodex

Expert assistant for solving, implementing, debugging, and explaining xv6-riscv / SNU xv6-riscv-snu operating-system assignments. Use when the task mentions xv6, RISC-V xv6, SNU OS projects, kernel files, syscalls, traps, virtual memory, page tables, scheduler, locks, file system, user programs, make qemu, make…

not rated 3 6mo ago A 100 tokens original MIT

coach

7377

gelanchez/software-coach

Skill Claude CodeCodex

Programming mentor with four selectable modes — hardcore (pure Socratic, zero code from the AI), standard (Socratic + pseudo-code/generic examples), architect (AI writes boilerplate, user writes core logic), pair (AI writes the real, complete solution directly, no coaching gate, logs a Learning Log entry only when…

not rated 3 3mo ago A 237 tokens original MIT

ppt

7378

reskfa/skill_doc2ppt

Skill Claude Code

A presentation generator that turns Markdown or Word documents into a single HTML slide show, with an optional PowerPoint output.

not rated 3 8mo ago A 71 tokens original MIT

review-loop

7379

NYTC69/review-loop

Plugin Claude Code

Bundles 6 skills, 12 agents · 1,270 tokens together

Take a change from plan to your acceptance: an independent reviewer checks the plan and the code, an adversarial gate tests the result, then quality polish, docs and a security review. Also reviews PRs and existing code.

not rated 3 changed 5d ago A tokens not measured original Apache-2.0

globalize-guide

7380

globalize-now/globalize-skills

Skill Claude CodeCodex

Drive the full internationalization journey for a project — detect the stack, recommend a library, set up the chosen library, wrap existing strings, and connect a translation platform (Globalize.now, default-on). Use when the user asks to add or configure i18n, internationalization, localization, multi-language…

not rated 3 changed yesterday A 270 tokens original MIT

morning-briefing

7382

roeibh/morning-briefing-claude-plugin

Plugin Claude Code

Bundles 8 skills, 1 MCP server · 367 tokens together

AI-powered morning routine that triages your email (and cleans up the inbox), Slack, calendar, GitHub, competitor news, and industry trends into a unified briefing dashboard with draft responses and actionable priorities.

not rated 3 7mo ago A tokens not measured original MIT

build-discipline

7383

rohansx/build-discipline

Skill Claude CodeCodex

A language- and domain-agnostic engineering discipline for building non-trivial software that actually survives real use — services, parsers, CLIs, data pipelines, simulators, interactive tools, agents, compilers, anything with state, logic, or behavior beyond a toy. Use this skill WHENEVER a task involves writing or…

not rated 3 4mo ago A 170 tokens original MIT

linkedin

7384

tekgrlpdx/linkedin-autoposter

Skill Claude Code

This skill should be used whenever the user wants to create, schedule, generate, review, or publish LinkedIn posts. Also triggers for content calendars, writing personas, post analytics, image creation for social media, or repurposing content for LinkedIn. Activate on any mention of LinkedIn posting, social media…

not rated 3 6mo ago A 95 tokens

ai-feedback-loops

7385

varunk130/ai-ux-skill-library

Skill Claude CodeCodex

Design feedback mechanisms that help AI systems learn from users - thumbs up/down, preference ranking, corrections, and human-in-the-loop escalation. Use when: RLHF UX, user feedback for AI, thumbs up down design, AI correction flow, human in the loop, feedback signal design, AI improvement loops.

not rated 3 8d ago A 66 tokens original MIT

diagram

7386

shahzadahmadv1/ExcaliClaude

Command Claude Code

Generate an Excalidraw architecture or flow diagram using the ExcaliClaude skill.

not rated 3 7mo ago A 0 tokens original MIT

trackly

7387

trackly-app/trackly-cli

Skill Codex

Search trackly for current jobs and companies, inspect job briefs and preferences, save only the jobs the user chooses, request trackly Apply (cloud) for a job the user names, and mark a job applied. Use when the user asks to find, compare, inspect, or track job openings, asks trackly to apply to a job for them, or…

not rated 3 changed 4d ago A 79 tokens original MIT

mavericks-mvi

7388

ujffdi/mavericks-mvi-skills

Skill Claude CodeCodex

Use when creating or modifying Mavericks 3.x State, MavericksState, MavericksViewModel, AssistedViewModelFactory, hiltMavericksViewModelFactory, ViewModelModule binding, initial args, Compose mavericksViewModel, collectAsStateWithLifecycle, Fragment MavericksView subscriptions, Async execute, setState, withState…

not rated 3 5mo ago A 83 tokens original MIT

realtimeforge

7389

sebs/ruleforge

Command Claude Code

You are RealTimeForge — a service that transforms a RuleForge extraction bundle into a production-ready real-time interactive game design package (2D or 3D). You find the board game's real-time soul, then engineer its body.

not rated 3 7mo ago A 0 tokens

crisis-catalyst

7390

sohaibt/founder-mode

Skill Claude Code

Reframe a crisis, constraint, or setback as a forcing function for founder-mode decisions that were previously politically blocked. Based on Chesky's pandemic transformation and Andy Grove's "great companies are defined by their crises." Use when facing a serious challenge and want to use it as fuel, not just survive…

not rated 3 6mo ago A 68 tokens original MIT

smartbrainactivity/electron-desktop-builds

Skill Claude CodeCodex

Expert helper for planning, configuring and troubleshooting Electron desktop builds. Use when packaging or distributing a desktop app with Electron, when an electron-builder or electron-forge build fails, when there are errors related to Electron versions, Node versions, native modules, code signing, installer…

not rated 3 7mo ago A 104 tokens original MIT

gauntlet-loop

7392

trilwu/gauntlet-loop-skills

Plugin Claude Code

Bundles 2 skills · 423 tokens together

Skills packaging the Gauntlet Loop — build → blind-critic → revise → repeat against a hard bar — for coding, writing, design, data, research, prompt evaluation, detection engineering, and authorized security testing.

not rated 3 3mo 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: