81,609 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.
Skill Claude CodeCodex
A personal health-tracking system for logging habits, reviewing biological measurements, and running N-of-1 trials—structured self-experiments on one person.
Plugin Claude Code
Bundles 8 skills, 5 agents, 10 hooks · 335 tokens together
Multi-agent tmux dashboard with skills, hooks, and workflow automation.
Plugin Claude Code
Bundles 2 skills, 1 hook · 73 tokens together
DDG-powered WebSearch and WebFetch replacement for Claude Code.
Skill Claude CodeCodex
Host and observe Claude Code agent teams in herdr via the herdmates plugin. Use when the user mentions herdmates, teammux, the recorder, or asks to launch, record, or hook a Claude Code team running in herdr panes — or when YOU are a team lead wondering why a teammate is stuck, whether anything is deadlocked, or who's…
upex-galaxy/agentic-qa-boilerplate
Skill Claude Code
Analyze, prioritize, and document test cases in TMS (Jira/Xray), repair an existing Story-ATS-ATP-ATR-TC cascade through a sealed explicit mode, or run the sealed post-promotion merged pass once automated tests land on the production branch. Use for Test/ATP/ATR artifacts, ROI and automation verdicts, maintaining…
Skill Claude Code
The antidote to vibe coding: a full software engineering team. Create or reverse-engineer PRDs, TRDs, personas, epics and user stories with acceptance criteria; plan, implement, test and verify code against them; run an autonomous Goal-Driven sprint; audit, status, reconcile, change requests, RFCs, test specs, test…
Plugin Claude Code
Bundles 21 skills, 2 agents, 3 hooks · 329 tokens together
Background music for your coding sessions — lofi, jazz, classical, ambient, electronic, and more.
Skill Claude CodeCodex
Delegate analytical, sandboxed, or long-running work to the Google Antigravity (agy) CLI through a JSON-bridge wrapper. Use when you need a second opinion, want to isolate side effects in a worktree, or need to run a long agent loop without blocking the main conversation.
Plugin Claude Code
Bundles 45 skills, 2 commands · 4,082 tokens together
45 skills: a clean-prose engine with an offline linter, wrappers for viral posts, essays, cold email and landing copy, and orchestrators that carry a job from research question to published carousel or reel.
MCP server Claude CodeCodexCursor +2
MCP server "fiction-context" as configured in geobond13/fiction-forge. Runs tools/fiction_mcp.py with python.
gquthier/autonomous-cold-email
Skill Claude CodeCodex
Build your own in-house cold email / outbound infrastructure instead of renting Smartlead, Instantly or Lemlist. Use when someone wants to set up self-hosted cold outreach: connecting their own SMTP/IMAP inboxes, sourcing and segmenting B2B leads, writing multi-step sequences, sending at scale with deliverability-safe…
MCP server Claude CodeCodexCursor +2
MCP server for DeepSeek AI with chat, reasoning, sessions, function calling, and cost tracking. Runs locally from the @arikusi/deepseek-mcp-server npm package. Needs 1 environment variable to run.
Skill Claude CodeCodex
A Python software development kit for sending large-model training and inference work to the remote TRIO service. Your local code prepares data and controls the process while the service performs model calculations and saves weights.
Plugin Claude Code
Bundles 4 skills, 1 command, 4 hooks, 1 MCP server · 111 tokens together
Local MCP memory for AI agents — MLX on Apple Silicon or CPU sentence-transformers on Linux/Ubuntu, sqlite-vec store, markdown-on-disk in your Obsidian vault. Zero Ollama, zero cloud APIs.
MCP server Claude CodeCodexCursor +2
MCP server for Avito: chats, listings, orders and analytics, with previews and confirmations. Runs locally from the avito-mcp npm package. Needs 4 environment variables to run.
product-on-purpose/thinking-framework-skills
Plugin Claude Code
Bundles 68 skills, 10 commands, 3 agents · 7,866 tokens together
An evidence-graded library of agent-executable thinking-method skills (premortem, problem restatement, and more). Each skill is reduced to its working mechanism, graded honestly on how strong its evidence actually is, and produces a concrete artifact rather than prose. Use to reframe a problem, challenge assumptions…
Plugin Claude Code
Bundles 62 skills, 4 commands, 7 agents · 4,683 tokens together
A broad collection of 45+ Claude Code skills spanning development, design, marketing, AI, security, and infrastructure. See cdd.dev/skills.
Skill Claude CodeCodex
A Chinese-language guide to creating RimWorld mods, including game definitions, C# code, Harmony patches, assets, and Steam Workshop publishing.
ericluo04/claude-academic-workflow
Skill Claude CodeCodex
Design, estimate, validate, and write up a difference-in-differences analysis, using the post-2018 heterogeneity-robust toolkit with an explicit statement of which parallel-trends assumption is imposed. TRIGGER on "difference-in-differences", "DiD", "TWFE", "event study", "staggered adoption", "staggered rollout"…
Skill Claude Code
AI system for game entities including behavior trees, finite state machines, steering behaviors, and decision making.
Unknown-333/awesome-data-engineering-skills
Plugin Claude Code
Bundles 37 skills · 2,932 tokens together
Curated, portable Agent Skills for data engineers.
Skill Claude Code
Build frontend interfaces; craft designs, teach project context, or extract components and tokens. Use when creating pages, apps, posters, or design systems.
Skill Claude CodeCodex
Audit a company's website from a buyer's perspective — positioning, funnel, proof, and differentiation. Use when user says 'audit this site', 'review my website', 'marketing audit', 'homepage critique', 'site teardown', 'why isn't my site converting', 'what does my site say about us', or 'what does a visitor see in 5…
Plugin Claude Code
Bundles 4 skills, 7 hooks · 220 tokens together
Hands the small judgments in a session to TypeSafe's Jev, a System One model that returns typed answers instead of generating text: what kind of request each prompt is, which model tier a subagent needs, whether an edit breaks a rule already written in your CLAUDE.md or AGENTS.md, and which transcript blocks survive…
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: