37,058 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.
Cursor rule Cursor
Executes WorkRail workflows step by step using the WorkRail MCP tools. Use when the user wants to run a workflow, follow a structured process, or resume a previous workflow session. Handles start, continue, checkpoint, and resume operations, interpreting each step's instructions faithfully and advancing only when the…
Skill Claude Code
Retrofit Ma'at documentation onto an existing repository — inventory gaps, interview the developer, derive AGENTS.md content and retrospective ADRs.
Zenobia0000/ai-agentic-coding-template_unified
Cursor rule Cursor needs its repo
This project uses the Universal AI Workflow System with Memory Bank for phased development workflow.
Cursor rule Cursor
Hackathon curriculum agent behavior — loaded when the user mentions /scope, /prd, /spec, /checklist, /build, /iterate, or /evaluate.
Skill Claude CodeCodex
Route active and completed artifacts into lifecycle-first exec-plans folders.
Skill Claude CodeCodex
Intake de material aportado en proyectos nuevos (modo nuevo-con-material). Recibe el contexto del usuario (docs de APIs, flujos, lógica, resultado esperado), lo normaliza en un SYSTEM-MAP.md con referencias al material, deriva la Visión y siembra la sesión para que la entrevista solo cubra los huecos. Úsala cuando el…
Cursor rule Cursor
DO NOT make any changes until you have 95% confidence that you know what to build. Use progressive questioning to achieve the required confidence level.
Cursor rule Cursor
Agentic workflow patterns for worktrees, multi-agent work, research, and visual verification.
Skill Codex
Create standardized Recursive Loop Orchestration projects for autonomous or semi-autonomous agents. Use when the user asks to create, scaffold, initialize, package, harden, or standardize an agent loop, recursive task loop, multi-agent workflow, self-running agent, Ralph-style loop, auto-fixer, monitor, browser-based…
LiveTrack-X/spec-driven-ai-development
Skill Codex
Install or upgrade SDAD; migrate an existing SDAD project; recover or repair sdad-state.yaml, INDEX, ledger, or handoff consistency; run or interpret SDAD Doctor; or diagnose the SDAD control plane. Use only for SDAD-specific bootstrap, migration, repair, and Doctor operations.
Skill Claude CodeCodex
THE single command for Tech Leads and Staff Engineers. Orchestrates the full sdd toolkit automatically — you never invoke other skills directly. Drives project and feature work through 4 adaptive phases (Specify, Plan, Tasks, Implement), auto-sizing depth by complexity. Activates the right tool at the right moment…
CUHK-Business-School-AI-Hub/coding_agent_constitution
Skill Codex
Turn unclear intent into an observable task contract and useful working context. Use Flash for lightweight daily work, research, documents, software, and reusable capabilities; use Standard or Retrofit for project governance. Skip already-scoped code changes and other clear small tasks unless context or governance…
Plugin Claude Code
Bundles 5 skills, 7 commands, 1 hook · 214 tokens together
Recursive Language Model Agent for PRD-driven development with iterative loops.
Plugin Claude Code
Bundles 1 skill, 7 commands, 2 agents · 458 tokens together
Seven structured decision-making techniques (tribunal, adversarial, red-team, pre-mortem, council, ladder-of-abstraction, calibration) that exploit the subagent architecture to produce verdicts plan steps can branch on. Includes a routing skill and two custom subagent types (Advocate, Lens).
Skill Codex
Cross-agent full-stack startup kit for building skill UIs and shippable products. ALWAYS run onboarding FIRST — never scaffold or build until you have interviewed the user (product, scope, style, theme, background animations, architecture, data, auth, payments, launch, deploy) or loaded their stored answers, and…
Command Claude Code
A command that expands an existing implementation plan into small, concrete coding steps with file paths and code examples.
Cursor rule Cursor
You are an AI delivery partner using the Maestro framework. Follow MAESTRO.md for full behavior specification. This file provides essential rules for Cursor.
kolesar/strategic-thinker-claude-plugin
Plugin Claude Code
Bundles 6 skills, 9 commands, 1 agent · 1,294 tokens together
A workflow for Claude Code that combines structured planning with building, testing, and reviewing software. TDD, or test-driven development, means writing tests as part of the development process.
Plugin Claude Code
Bundles 16 skills, 6 commands, 5 agents, 1 hook, 3 MCP servers · 2,497 tokens together
Chip vendor SE (System Engineer / Application Architect) workflow skills — 16 skills, 6 commands, 3 MCP servers, SessionStart hook. Full lifecycle: requirements decomposition → architecture design (system/SW/HW) → specification authoring → cross-department review (6 types) → traceability validation. Plus document…
JularDepick/user-thoughts.SKILL
Skill Claude Code
A skill that stores a user's project decisions and constraints in mdbase, a persistent project knowledge store. The records can be reused across sessions and by different coding assistants.
luis-at-safebase/luism-claude-plugins
Plugin Claude Code
Bundles 2 skills, 1 agent · 152 tokens together
Investigate → propose → gate → execute → verify. A guided workflow drawn from OODA, Socratic inquiry, QRSPI, and Polya's How to Solve It.
Plugin Claude Code
Bundles 4 skills, 6 commands · 102 tokens together
Feature-Sliced Design architecture assistant that analyzes, validates, and scaffolds FSD-compliant project structures.
Plugin Claude Code
Bundles 3 skills, 13 commands, 3 agents · 601 tokens together
A plugin to facilitate a task based development workflow comprised of steps to investigate, design, spec out and implement code changes.
Plugin Claude Code
Bundles 1 skill, 1 command, 4 agents · 210 tokens together
Architecture-first design workflow using StarUML MCP. Creates layered UML (package diagrams + class diagrams) with interface segregation, enforces no circular dependencies, and keeps diagrams in sync with code.
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: