kok-o/koko-contextos-agents

Convenient, ready-to-use engineering skills and best practices for your AI assistant.

This repository also configures its own agents. See what koko-contextos-agents tells them →

2Stars on the repository
79Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

agent-adapters

01

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Generates agent-specific configuration files from the unified ContextOS format. One internal system, multiple output formats for Claude, Gemini, Copilot, Cursor, Aider, Continue, OpenHands, and others.

not rated 2 2d ago A 46 tokens original MIT

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

not rated 2 changed yesterday A 57 tokens copy · 100% MIT

context-manager

03

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Smart context selection engine. Analyzes the current task, consults the Project Graph, and returns only the documents and skills needed. Prevents context window overflow by loading minimum relevant information.

not rated 2 2d ago A 43 tokens original MIT

context-os

04

kok-o/koko-contextos-agents

Skill Claude CodeCodex

AI Project Operating System — Context Compiler that transforms user intent into minimal, relevant context for any AI agent and any task. Manages the full lifecycle: Idea → Requirements → Architecture → Planning → Development → Review → Release.

not rated 2 2d ago A 49 tokens original MIT

database

05

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Database architecture, schema design, Prisma, Drizzle ORM, indexing strategies, migrations, and N+1 query resolution.

not rated 2 changed yesterday A 26 tokens original MIT

decision-engine

07

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Architecture Decision Records (ADR) management. Creates, tracks, and queries decisions so the AI agent understands WHY choices were made, not just WHAT was chosen.

not rated 2 2d ago A 34 tokens original MIT

docker

08

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Docker containerization, multi-stage builds, non-root security, layer caching optimization, and docker-compose standards.

not rated 2 2d ago A 23 tokens original MIT

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Senior engineering workflow skill. Enforces spec → plan → build → test → review → ship. AI never writes code before a spec and plan are approved. Acts like a senior, not a junior. Integrated with gstack-roles for automatic role activation per phase.

not rated 2 changed yesterday A 57 tokens original MIT

document-generator

11

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Generates project documentation from a single idea. Creates PRD, Architecture, Database, API, UI, Roadmap, Tasks, Decision Records, and Project Graph using templates. Supports incremental updates.

not rated 2 2d ago A 42 tokens original MIT

gstack-roles

12

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Role-based AI specialist system. Defines 23 specialist roles and teaches the AI to adopt the correct role before each task phase, like a virtual engineering team.

not rated 2 2d ago A 36 tokens original MIT

impeccable-design

13

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Visual design quality enforcement. 50 deterministic anti-pattern rules preventing AI design slop. Bans generic fonts, pure colors, nested cards, dated animations. Adapted for Tailwind CSS v4, shadcn/ui, and Framer Motion stacks.

not rated 2 2d ago A 57 tokens original MIT

minimalist-ui

15

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

not rated 2 changed yesterday A 34 tokens copy · 100% MIT

Next.js

17

kok-o/koko-contextos-agents

Skill Claude CodeCodex

ContextOS skill for Next.js App Router, Server Components, Server Actions, performance optimization, and Vercel best practices.

not rated 2 changed yesterday A 28 tokens original MIT

Web Performance

19

kok-o/koko-contextos-agents

Skill Claude CodeCodex

ContextOS skill for Web Performance, Core Web Vitals, waterfall elimination, bundle size optimization, and caching strategies.

not rated 2 2d ago A 26 tokens original MIT

ponytail-mindset

20

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Minimalist coding mindset. Write only what is strictly necessary for the task. 7-rung decision ladder before writing any code. Reduces output 54% while keeping all safety, validation, error handling, and security guards intact.

not rated 2 changed yesterday A 54 tokens original MIT

kok-o/koko-contextos-agents

Skill Claude CodeCodex

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…

not rated 2 changed yesterday A 67 tokens copy · 92% MIT

React

22

kok-o/koko-contextos-agents

Skill Claude CodeCodex

ContextOS skill for modern React (v18/v19), component architecture, state colocation, render optimization, and Vercel performance rules.

not rated 2 2d ago A 31 tokens original MIT

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

not rated 2 changed yesterday A 45 tokens copy · 100% MIT

security

24

kok-o/koko-contextos-agents

Skill Claude CodeCodex

Application and AI agent security skill. Enforces zero-trust defense-in-depth, OWASP Top 10 mitigation, prompt injection defense, and secure tool execution.

not rated 2 changed yesterday C 34 tokens 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: