35,429 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.
Plugin Claude Code
Bundles 37 skills, 18 agents · 9,643 tokens together
Structured, artifact-driven development pipeline for Claude Code — plan, implement, review, and ship features with three ceremony tiers. Also includes arn-code-batch-cve-scan and arn-code-batch-cve-fix for CVE discovery, triage, and batch resolution. 37 pipeline skills, 18 specialist agents.
Connectry-io/connectrylab-architect-cert-mcp
Command Claude Code
Collaboratively refine a specification, prompt, or code pattern through structured conversation rounds.
tosin2013/mcp-adr-analysis-server
MCP server Claude CodeCodexCursor +2
AI-powered MCP server for analyzing Architectural Decision Records (ADRs). Runs locally from the mcp-adr-analysis-server npm package. Needs 4 environment variables to run.
Impertio-Studio/QGIS-Claude-Skill-Package
Skill Claude CodeCodex
Use when planning a spatial analysis workflow, choosing between analysis approaches, or chaining multiple operations. Prevents wrong analysis method selection and suboptimal workflow ordering. Covers vector vs raster decision trees, processing algorithm selection, workflow chaining, CRS/format guidance, and MCP server…
Plugin Claude Code
Bundles 1 skill, 1 command · 278 tokens together
ES: Vuelve a Claude en tu contra para criticar a fondo una idea, un plan o un proyecto entero — sin validar ni suavizar — por ocho ángulos, con investigación de fracasos reales y un veredicto priorizado de qué arreglar. EN: Turn Claude against you to harshly critique an idea, plan, or whole project across eight angles.
Skill Claude CodeCodex
Refine an Original Goal into an acceptance-testable Overall Goal for Ultra-Goal through read-only exploration and user alignment. Manual invocation only.
Skill Claude CodeCodex
A 100-day action plan for an early-stage one-person AI company, meaning an AI business run mainly by one person. It provides daily actions, milestones, progress tracking, and a timeline toward first revenue.
Cursor rule Cursor
A set of coding rules and a work process for planning tasks, writing code, testing it, and reviewing the result. It also defines roles such as application expert, product expert, and chief technology officer.
Skill Claude CodeCodex
Multi-phase delivery framework that MUST preserve session continuity and SHOULD support SHA-based rollback.
Skill Claude CodeCodex
Write comprehensive business plans — executive summary, market analysis, financial projections, and competitive positioning.
Plugin Claude Code
Multi-stack AI-assisted SDLC pipelines for Claude Code. Stack Provider Pattern: core owns the pipeline, framework plugins register themselves via stack.md profiles.
RafaelGorski/Problem-Based-SRS
Plugin Claude Code
Bundles 2 skills · 230 tokens together
Problem-Based Software Requirements Specification methodology for AI-assisted requirements engineering. Provides structured approach to capture Customer Problems (WHY), Customer Needs (WHAT), and Functional Requirements (HOW) with full traceability.
yutongcai0628/career-planning-skill
Cursor rule Cursor
Use when the user asks about their own career direction, strengths, long-term professional development, role or industry choice, resignation or joining decisions, offers, JD fit, career changes, promotion, freelancing, entrepreneurship, layoffs, organizational changes, or industry decline. Do not use for routine…
evan966890/openclaw-bestroll-skills
Skill Claude CodeCodex
A tool that turns customer conversations, meeting notes, and other Feishu records into structured requirement documents. BRD means business requirements document, and PRD means product requirements document.
Plugin Claude Code
Bundles 1 skill, 3 commands · 89 tokens together
Long-horizon project goals for Claude Code: an attended /goal loop that advances one increment at a time, delegating through the codex and cursor plugins.
Skill Codex
Operate as a technical product manager — turn vague ideas and feature requests into clear specs, scoped MVPs, prioritized backlogs, estimates, success metrics, and stakeholder-ready writeups. Use this WHENEVER the user is deciding what to build or why (not just how): writing a PRD or spec, breaking an idea into epics…
Skill Claude Code
2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injection.
Skill Claude CodeCodex
Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: 'premortem this', 'premortem my', 'run a premortem', 'what could kill this'…
PolicyEngine/policyengine-claude
Command Claude Code
Orchestrates multi-agent workflow to backdate and quality-improve existing state program parameters.
julianoczkowski/product-manager
Plugin Claude Code
Bundles 18 skills · 1,943 tokens together
A product-management copilot based on the Pragmatic Institute Framework (Foundations, Focus, Build). Guides PMs from a raw idea through market research, positioning, strategy, requirements, roadmap and launch — and produces a client-ready artifact (Markdown or Word .docx) at every stage.
MCP server Claude CodeCodexCursor +2
MCP server for OpenSpec - spec-driven development with real-time dashboard and approval workflow. Runs locally from the openspec-mcp npm package.
cyanheads/workflows-mcp-server
Plugin Claude Code
Bundles 34 skills, 1 MCP server · 2,317 tokens together
Store, query, and create YAML workflow playbooks for LLM agents via MCP. STDIO or Streamable HTTP.
Skill Claude CodeCodex
Before starting a Ralph RLM loop, interview the user to sharpen the goal, stress-test the design, and write an authored PLAN.md (goal, definition of done, milestones, open questions, invariants) that the loop can follow. Use when a user wants to plan, scope, or stress-test work before delegating it to the supervisor /…
pepeladeira/cursor-prd-task-rules
Cursor rule Cursor
Orientar um assistente de IA na criação de um Documento de Requisitos do Produto (PRD) detalhado em formato Markdown, baseado em um prompt inicial do usuário. O PRD deve ser claro, acionável e adequado para um desenvolvedor júnior entender e implementar a funcionalidade.
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: