Skill Claude CodeCodex
A structured business-problem-solving method based on McKinsey-style analysis, including issue trees, hypotheses, and research reports or presentations.
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.
Skill Claude CodeCodex
A structured business-problem-solving method based on McKinsey-style analysis, including issue trees, hypotheses, and research reports or presentations.
reshadat/first-principles-destructor
Skill Claude CodeCodex
First principles destructor — strips any statement, business model, product idea, process, or industry belief down to its physics/math/logic floor. Calculates the convention tax (what you pay because of habit vs necessity). Rebuilds from reality. Use when evaluating pricing, hiring timelines, product approaches, team…
Skill Claude CodeCodex
A Chinese-language framework for judging decisions through practical constraints, evidence, returns, risks, and ordinary people's circumstances. It is associated with the direct analytical style of Hu Chenfeng.
1killermouse/vibe-coding-prd-skill
Skill Codex
A guide for turning product requirements, competitor research, ideas, or documents into a short Markdown plan that coding agents can follow.
Cursor rule Cursor
Cursor rule "dev_workflow" from snarktank/code-editing-agent, covering taskmaster development workflow, the basic loop, standard development workflow process, simple workflow (default starting point) and leveling up: agent-led multi-context workflows.
Skill Codex
Route work to the correct Pretty Good Prompts (PGP) document and execute terminal-first implementation workflows. Use when operating in this repository (or a repo consuming these prompts) for modernization, code review, refactoring, infrastructure, database, Python, Ruby, frontend, HTML/CSS, or AI/LLM tasks that need…
Skill Claude CodeCodex
An interactive assistant for creating a product requirements document, or PRD—a structured description of what a product should do and how it should be built. It gathers information through questions and produces organised PRD content.
Skill Claude CodeCodex
Autonomous Codex workflow that implements codex-loop/prd.json with one fresh Codex subagent per story. Use when the user asks to run Codex Loop, run the loop, work through a PRD, process prd.json, implement all stories, iterate through user stories autonomously, or complete a feature broken into PRD stories.…
Skill Claude CodeCodex
Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.
Skill Claude CodeCodex
Draft safe MoonClaw job proposals with the exact proposal JSON schema and execution-oriented step decomposition. Use when planning or repairing a job proposal.
Skill Claude CodeCodex
Persistent long-term memory via memini. Use to remember durable facts, decisions, and preferences, and to recall relevant context before acting. Triggers when the user says "remember", "what do you know about", or when starting a task that may have prior context.
Agent Claude Code
Primary orchestrator agent. Controls the entire 8-phase pipeline. Never writes code — delegates all implementation to specialist agents. Manages GitHub issues, quality gates, and escalation.
Plugin Claude Code
Bundles 7 skills · 468 tokens together
Harness-agnostic idea-to-merged-PR pipeline — runs on any coding agent: groundwork, make-guidelines, create-product, create-tasks, do-task, watch-pr, chaos-engineering.
Skill Claude CodeCodex
Periodically lint the full OpenSpec archive for cross-change decision drift, index/spec reconciliation, and structural over-coupling, the gap nothing else in the QRSPI/OpenSpec stack covers, since every other drift check (accelint-onboard-openspec, accelint-architecture-doc, accelint-qrspi-apply Phase 4) only looks…
Plugin Claude Code
Bundles 26 skills, 10 commands, 5 agents, 2 hooks · 3,997 tokens together
Comprehensive Phaser 4 game development toolkit — 21 skills, 7 commands, 5 agents, 9 archetypes. Plan with GDDs and architecture, build scenes/physics/UI, then verify the game actually runs with the headless playtest harness.
Skill Claude CodeCodex
A review framework for deciding whether an engineering idea or technical commitment is necessary, too broad, or premature. It examines the real problem, complexity, evidence, non-goals, and ease of reversal.
conorbronsdon/agent-context-os
Command Claude Code needs its repo
Validate a dream artifact, review each proposal, and apply only individually accepted changes.
Skill Claude CodeCodex
Inspect a codebase, a stack the user describes, or a description of what they want to build; map what is there to agents-inc catalog skills — or intent to candidate built-in stacks the user picks from — and emit a SeedPayload plus a human-readable proposal report. Use when seeding a configuration for a project that…
idoforgod/Vibe-learning-AgenticWorkflow
Cursor rule Cursor
A project-wide AgenticWorkflow method that applies the same working rules to every task.
Skill Claude CodeCodex
A thinking and communication framework based on the public talks, interviews, books, and university-building work of Shi Yigong, a Chinese scientist and founder of Westlake University. It provides mental models, decision guidelines, and a distinct way of explaining ideas.
Skill Claude CodeCodex
Use when a task needs connected MCP servers, external services, dynamic MCP tool discovery, schema inspection, sandboxed MCP execution, or routing across many possible MCP tools.
Cursor rule Cursor
📂 = ".ai/memory-bank/" 📦 = ".ai/memory-bank/backups/".
Skill Claude CodeCodex
Working-style skill that makes Opus (or Sonnet) agents work like a Fable agent. BINDING FROM THE MOMENT YOU LOAD THIS - visible top-level messages are short status summaries only (conclusion + next step, ≤2 lines); ALL deliberation goes in reasoning or a thoughts file via tool call, never visible text. Top-level agent…
Skill Claude Code
Explicitly start and drive Slipway's interruptible soft autopilot one structured Action at a time.
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: