axiom-coding-agent-setup 1.0.9 → 1.0.11

package/.agents/skills/ui-ux-pro-max/data

@@ -0,0 +1 @@
+../../../src/ui-ux-pro-max/data

package/.agents/skills/ui-ux-pro-max/scripts

@@ -0,0 +1 @@
+../../../src/ui-ux-pro-max/scripts

package/.agents/stack.md

@@ -1,188 +1,188 @@
-# Tech Stack
-
-Current knowledge as of 2026. I know what's production-proven, what's hype, and what tradeoffs each choice carries.
-
----
-
-## Languages
-
-| Language | Strength | When I Reach For It |
-|---|---|---|
-| **TypeScript** | Type safety, ecosystem, tooling | Frontend, Node backends, full-stack |
-| **Python** | ML/AI ecosystem, scripting, data | ML pipelines, APIs, automation |
-| **Go** | Performance, concurrency, simple deployment | High-throughput services, CLIs, platform tooling |
-| **Rust** | Memory safety, systems performance | Performance-critical components, WebAssembly targets |
-| **SQL** | Relational data, analytics | Anytime a relational DB is in the stack |
-
----
-
-## Frontend
-
-### Core
-- **React 19 / Next.js 15** — Default choice for production web apps; App Router, Server Components, streaming
-- **TypeScript** — Non-negotiable for any production frontend
-- **Tailwind CSS v4** — Utility-first; fast iteration; pairs well with component libraries
-- **shadcn/ui** — Accessible, unstyled-first components; copy-paste model beats black-box libs
-
-### State & Data
-- **Zustand** — Lightweight client state; prefer over Redux for most apps
-- **TanStack Query (React Query v5)** — Server state, caching, background sync
-- **Zod** — Runtime schema validation; use at API boundaries and form inputs
-
-### Testing
-- **Vitest** — Fast unit/integration testing; Vite-native
-- **Playwright** — E2E testing; cross-browser; better than Cypress for modern apps
-- **React Testing Library** — Component testing focused on user behavior, not internals
-
-### Build / Tooling
-- **Vite** — Dev server and bundling for non-Next projects
-- **Biome** — Fast linter + formatter (replaces ESLint + Prettier in many setups)
-- **Turborepo** — Monorepo build orchestration
-
----
-
-## Backend
-
-### Node.js / TypeScript
-- **Hono** — Lightweight, edge-compatible, fast; preferred over Express for new projects
-- **Fastify** — High-performance Node HTTP framework when more features needed
-- **tRPC** — End-to-end type-safe APIs in full-stack TypeScript monorepos
-- **Prisma / Drizzle ORM** — Prisma for developer ergonomics; Drizzle for performance/edge
-
-### Python
-- **FastAPI** — Default Python API framework; async, type-annotated, auto-docs
-- **Pydantic v2** — Data validation and settings management; use throughout
-- **SQLAlchemy 2.x** — ORM for complex relational data access
-- **uv** — Fast Python package manager; preferred over pip/poetry in 2026
-- **Ruff** — Python linter + formatter; replaces flake8, black, isort
-
-### Authentication
-- **Clerk / Auth.js (NextAuth v5)** — For hosted auth in web apps
-- **JWT + refresh tokens** — For custom auth in API-first architectures
-- **OAuth 2.0 / OIDC** — Standard; know the flows, don't roll your own
-
----
-
-## Databases
-
-### Relational
-- **PostgreSQL** — Default relational database; battle-tested, extensions ecosystem
-- **Neon** — Serverless Postgres; preferred for projects needing scale-to-zero (avoids Supabase pausing)
-- **PlanetScale / Turso** — MySQL-compatible (PlanetScale) or SQLite-edge (Turso) alternatives
-
-### Caching & Queues
-- **Redis / Valkey** — Caching, pub/sub, session storage, rate limiting
-- **BullMQ** — Job queue on top of Redis for Node.js
-
-### Document / NoSQL
-- **MongoDB** — When document model genuinely fits; don't use as a schema-free escape hatch
-- **DynamoDB** — When you need AWS-native key-value at massive scale
-
-### Vector Databases (AI workloads)
-- **pgvector** — Start here: Postgres extension for embeddings; zero new infra
-- **Pinecone** — Managed, production-grade; when pgvector hits limits
-- **Weaviate** — Self-hostable, good for hybrid search (keyword + semantic)
-- **Qdrant** — High-performance, Rust-native; strong for on-prem deployments
-
----
-
-## AI / ML Stack
-
-### LLM APIs & SDKs
-- **Anthropic Claude API** — claude-opus-4, claude-sonnet-4 (flagship reasoning and speed)
-- **OpenAI API** — GPT-4o, o3/o4-mini for reasoning tasks
-- **Google Gemini** — gemini-2.5-pro for long context and multimodal
-- **Vercel AI SDK** — Unified SDK for streaming, tool use, multi-provider support in JS/TS
-- **LiteLLM** — Provider-agnostic proxy; enables model switching without code changes
-
-### Orchestration & Agents
-- **LangChain (LCEL v0.9+)** — Pipeline orchestration; use for composability
-- **LlamaIndex v1.2** — Knowledge retrieval layer; RAG pipelines, document parsing
-- **LangGraph** — Stateful multi-agent workflows; preferred for complex agent loops
-- **MCP (Model Context Protocol)** — De facto standard for agent ↔ tool connectivity; Anthropic-originated, now Linux Foundation; 97M monthly SDK downloads as of Feb 2026
-
-### Embeddings & Retrieval
-- **text-embedding-3-large** (OpenAI) or **voyage-3** (Anthropic) — Production embedding models
-- **Hybrid search** — BM25 (keyword) + dense vector; almost always outperforms pure semantic
-
-### Document Parsing (for RAG)
-- **Docling** — Strong structured doc parsing (PDF, DOCX, tables)
-- **MinerU** — PDF extraction with layout understanding
-- **Unstructured.io** — General-purpose document ingestion pipeline
-
-### LLM Observability
-- **Langfuse** — Open-source LLM observability; traces, evals, cost tracking; self-hostable
-- **LangSmith** — LangChain-native tracing and eval platform
-- **OpenTelemetry** — Standard instrumentation; use for integrating LLM traces into existing observability stack
-
-### MLOps / Training
-- **MLflow** — Experiment tracking, model registry, deployment; most widely adopted open-source
-- **Weights & Biases** — Richer experiment tracking for deep learning workflows
-- **Hugging Face Hub** — Model hosting, datasets, Spaces for demos
-- **Gradio** — Fastest path to an ML demo UI; pairs with HF Inference API
-- **PyTorch 2.x** — Default framework for ML model work; 55%+ production share
-- **vLLM** — High-throughput LLM inference server; PagedAttention; production serving
-- **Airflow / Prefect** — Pipeline orchestration for ML workflows; Airflow for proven stability, Prefect for modern DX
-
----
-
-## Infrastructure & DevOps
-
-### Containers & Orchestration
-- **Docker** — Standard containerization; multi-stage builds; use `uv` for Python images
-- **Kubernetes (K8s)** — Production orchestration at scale; know Deployments, Services, Ingress, HPA
-- **Docker Compose** — Local dev environments and simpler self-hosted production deployments
-
-### Cloud Providers
-- **AWS** — Broadest services; ECS/EKS, Lambda, S3, RDS, SageMaker
-- **GCP** — Strong for ML/data workloads; Vertex AI, BigQuery, Cloud Run
-- **Azure** — Enterprise environments; Azure OpenAI for compliance-sensitive LLM use cases
-- **Vercel / Railway / Fly.io** — Deployment platforms for faster iteration cycles
-
-### Infrastructure as Code
-- **Terraform** — Standard IaC; provider ecosystem; remote state in S3/GCS
-- **Pulumi** — IaC with real programming languages (TypeScript/Python) — good for complex infra logic
-- **CDK (AWS)** — AWS-native; prefer if already deep in AWS ecosystem
-
-### CI/CD
-- **GitHub Actions** — Default choice; broad ecosystem; free for OSS
-- **GitLab CI** — When using GitLab; strong built-in container registry
-- Know: artifact caching, matrix builds, environment protection rules, OIDC for cloud auth (no long-lived secrets)
-
-### Observability
-- **OpenTelemetry** — Vendor-neutral instrumentation standard; traces, metrics, logs
-- **Grafana + Prometheus** — Open-source metrics and dashboards; standard for self-hosted
-- **Datadog / New Relic** — Managed observability when budget allows; faster to set up
-- **Sentry** — Error tracking; essential for production frontend and backend
-
-### Networking & Security
-- **Cloudflare** — CDN, DDoS protection, Workers for edge compute, Zero Trust
-- **Nginx / Caddy** — Reverse proxy; Caddy for automatic TLS
-- Secrets management: **Vault (HashiCorp)**, AWS Secrets Manager, or Doppler — never hardcode secrets, never commit `.env` to git
-
----
-
-## Architectural Patterns I Know Well
-
-| Pattern | When It Fits |
-|---|---|
-| Monolith | Early-stage products; teams under ~8 engineers; fast iteration priority |
-| Modular Monolith | Monolith with clear internal boundaries; prepare for extraction later |
-| Microservices | Independent deployment needed; team ownership per service; clear domain boundaries |
-| Event-driven (Kafka/SQS) | Async processing; decoupled services; audit trails |
-| CQRS + Event Sourcing | Complex domains; full audit history required; high read/write asymmetry |
-| RAG Pipeline | LLM apps needing domain knowledge; reduces hallucination; more controllable than fine-tuning |
-| Agentic Loops (ReAct/MCP) | Multi-step autonomous tasks; tool use; planning required |
-| BFF (Backend for Frontend) | When frontend needs aggregated/transformed data; mobile vs. web diverge |
-
----
-
-## What I Watch Out For (2026 Landscape)
-
-- **MCP adoption** is accelerating; evaluate it before building custom tool-integration layers
-- **pgvector first** for new RAG projects; only migrate to a dedicated vector DB when you hit real limits
-- **vLLM + self-hosted inference** is viable at mid-scale; evaluate against API costs at ~$500/month
-- **LangGraph > LangChain** for anything involving agent state, branching, or loops
-- **Biome over ESLint+Prettier** for new TS projects — same rules, 50–100x faster
-- **uv over pip/poetry** for Python projects — significantly faster, better lockfiles
+# Tech Stack
+
+Current knowledge as of 2026. I know what's production-proven, what's hype, and what tradeoffs each choice carries.
+
+---
+
+## Languages
+
+| Language | Strength | When I Reach For It |
+|---|---|---|
+| **TypeScript** | Type safety, ecosystem, tooling | Frontend, Node backends, full-stack |
+| **Python** | ML/AI ecosystem, scripting, data | ML pipelines, APIs, automation |
+| **Go** | Performance, concurrency, simple deployment | High-throughput services, CLIs, platform tooling |
+| **Rust** | Memory safety, systems performance | Performance-critical components, WebAssembly targets |
+| **SQL** | Relational data, analytics | Anytime a relational DB is in the stack |
+
+---
+
+## Frontend
+
+### Core
+- **React 19 / Next.js 15** — Default choice for production web apps; App Router, Server Components, streaming
+- **TypeScript** — Non-negotiable for any production frontend
+- **Tailwind CSS v4** — Utility-first; fast iteration; pairs well with component libraries
+- **shadcn/ui** — Accessible, unstyled-first components; copy-paste model beats black-box libs
+
+### State & Data
+- **Zustand** — Lightweight client state; prefer over Redux for most apps
+- **TanStack Query (React Query v5)** — Server state, caching, background sync
+- **Zod** — Runtime schema validation; use at API boundaries and form inputs
+
+### Testing
+- **Vitest** — Fast unit/integration testing; Vite-native
+- **Playwright** — E2E testing; cross-browser; better than Cypress for modern apps
+- **React Testing Library** — Component testing focused on user behavior, not internals
+
+### Build / Tooling
+- **Vite** — Dev server and bundling for non-Next projects
+- **Biome** — Fast linter + formatter (replaces ESLint + Prettier in many setups)
+- **Turborepo** — Monorepo build orchestration
+
+---
+
+## Backend
+
+### Node.js / TypeScript
+- **Hono** — Lightweight, edge-compatible, fast; preferred over Express for new projects
+- **Fastify** — High-performance Node HTTP framework when more features needed
+- **tRPC** — End-to-end type-safe APIs in full-stack TypeScript monorepos
+- **Prisma / Drizzle ORM** — Prisma for developer ergonomics; Drizzle for performance/edge
+
+### Python
+- **FastAPI** — Default Python API framework; async, type-annotated, auto-docs
+- **Pydantic v2** — Data validation and settings management; use throughout
+- **SQLAlchemy 2.x** — ORM for complex relational data access
+- **uv** — Fast Python package manager; preferred over pip/poetry in 2026
+- **Ruff** — Python linter + formatter; replaces flake8, black, isort
+
+### Authentication
+- **Clerk / Auth.js (NextAuth v5)** — For hosted auth in web apps
+- **JWT + refresh tokens** — For custom auth in API-first architectures
+- **OAuth 2.0 / OIDC** — Standard; know the flows, don't roll your own
+
+---
+
+## Databases
+
+### Relational
+- **PostgreSQL** — Default relational database; battle-tested, extensions ecosystem
+- **Neon** — Serverless Postgres; preferred for projects needing scale-to-zero (avoids Supabase pausing)
+- **PlanetScale / Turso** — MySQL-compatible (PlanetScale) or SQLite-edge (Turso) alternatives
+
+### Caching & Queues
+- **Redis / Valkey** — Caching, pub/sub, session storage, rate limiting
+- **BullMQ** — Job queue on top of Redis for Node.js
+
+### Document / NoSQL
+- **MongoDB** — When document model genuinely fits; don't use as a schema-free escape hatch
+- **DynamoDB** — When you need AWS-native key-value at massive scale
+
+### Vector Databases (AI workloads)
+- **pgvector** — Start here: Postgres extension for embeddings; zero new infra
+- **Pinecone** — Managed, production-grade; when pgvector hits limits
+- **Weaviate** — Self-hostable, good for hybrid search (keyword + semantic)
+- **Qdrant** — High-performance, Rust-native; strong for on-prem deployments
+
+---
+
+## AI / ML Stack
+
+### LLM APIs & SDKs
+- **Anthropic Claude API** — claude-opus-4, claude-sonnet-4 (flagship reasoning and speed)
+- **OpenAI API** — GPT-4o, o3/o4-mini for reasoning tasks
+- **Google Gemini** — gemini-2.5-pro for long context and multimodal
+- **Vercel AI SDK** — Unified SDK for streaming, tool use, multi-provider support in JS/TS
+- **LiteLLM** — Provider-agnostic proxy; enables model switching without code changes
+
+### Orchestration & Agents
+- **LangChain (LCEL v0.9+)** — Pipeline orchestration; use for composability
+- **LlamaIndex v1.2** — Knowledge retrieval layer; RAG pipelines, document parsing
+- **LangGraph** — Stateful multi-agent workflows; preferred for complex agent loops
+- **MCP (Model Context Protocol)** — De facto standard for agent ↔ tool connectivity; Anthropic-originated, now Linux Foundation; 97M monthly SDK downloads as of Feb 2026
+
+### Embeddings & Retrieval
+- **text-embedding-3-large** (OpenAI) or **voyage-3** (Anthropic) — Production embedding models
+- **Hybrid search** — BM25 (keyword) + dense vector; almost always outperforms pure semantic
+
+### Document Parsing (for RAG)
+- **Docling** — Strong structured doc parsing (PDF, DOCX, tables)
+- **MinerU** — PDF extraction with layout understanding
+- **Unstructured.io** — General-purpose document ingestion pipeline
+
+### LLM Observability
+- **Langfuse** — Open-source LLM observability; traces, evals, cost tracking; self-hostable
+- **LangSmith** — LangChain-native tracing and eval platform
+- **OpenTelemetry** — Standard instrumentation; use for integrating LLM traces into existing observability stack
+
+### MLOps / Training
+- **MLflow** — Experiment tracking, model registry, deployment; most widely adopted open-source
+- **Weights & Biases** — Richer experiment tracking for deep learning workflows
+- **Hugging Face Hub** — Model hosting, datasets, Spaces for demos
+- **Gradio** — Fastest path to an ML demo UI; pairs with HF Inference API
+- **PyTorch 2.x** — Default framework for ML model work; 55%+ production share
+- **vLLM** — High-throughput LLM inference server; PagedAttention; production serving
+- **Airflow / Prefect** — Pipeline orchestration for ML workflows; Airflow for proven stability, Prefect for modern DX
+
+---
+
+## Infrastructure & DevOps
+
+### Containers & Orchestration
+- **Docker** — Standard containerization; multi-stage builds; use `uv` for Python images
+- **Kubernetes (K8s)** — Production orchestration at scale; know Deployments, Services, Ingress, HPA
+- **Docker Compose** — Local dev environments and simpler self-hosted production deployments
+
+### Cloud Providers
+- **AWS** — Broadest services; ECS/EKS, Lambda, S3, RDS, SageMaker
+- **GCP** — Strong for ML/data workloads; Vertex AI, BigQuery, Cloud Run
+- **Azure** — Enterprise environments; Azure OpenAI for compliance-sensitive LLM use cases
+- **Vercel / Railway / Fly.io** — Deployment platforms for faster iteration cycles
+
+### Infrastructure as Code
+- **Terraform** — Standard IaC; provider ecosystem; remote state in S3/GCS
+- **Pulumi** — IaC with real programming languages (TypeScript/Python) — good for complex infra logic
+- **CDK (AWS)** — AWS-native; prefer if already deep in AWS ecosystem
+
+### CI/CD
+- **GitHub Actions** — Default choice; broad ecosystem; free for OSS
+- **GitLab CI** — When using GitLab; strong built-in container registry
+- Know: artifact caching, matrix builds, environment protection rules, OIDC for cloud auth (no long-lived secrets)
+
+### Observability
+- **OpenTelemetry** — Vendor-neutral instrumentation standard; traces, metrics, logs
+- **Grafana + Prometheus** — Open-source metrics and dashboards; standard for self-hosted
+- **Datadog / New Relic** — Managed observability when budget allows; faster to set up
+- **Sentry** — Error tracking; essential for production frontend and backend
+
+### Networking & Security
+- **Cloudflare** — CDN, DDoS protection, Workers for edge compute, Zero Trust
+- **Nginx / Caddy** — Reverse proxy; Caddy for automatic TLS
+- Secrets management: **Vault (HashiCorp)**, AWS Secrets Manager, or Doppler — never hardcode secrets, never commit `.env` to git
+
+---
+
+## Architectural Patterns I Know Well
+
+| Pattern | When It Fits |
+|---|---|
+| Monolith | Early-stage products; teams under ~8 engineers; fast iteration priority |
+| Modular Monolith | Monolith with clear internal boundaries; prepare for extraction later |
+| Microservices | Independent deployment needed; team ownership per service; clear domain boundaries |
+| Event-driven (Kafka/SQS) | Async processing; decoupled services; audit trails |
+| CQRS + Event Sourcing | Complex domains; full audit history required; high read/write asymmetry |
+| RAG Pipeline | LLM apps needing domain knowledge; reduces hallucination; more controllable than fine-tuning |
+| Agentic Loops (ReAct/MCP) | Multi-step autonomous tasks; tool use; planning required |
+| BFF (Backend for Frontend) | When frontend needs aggregated/transformed data; mobile vs. web diverge |
+
+---
+
+## What I Watch Out For (2026 Landscape)
+
+- **MCP adoption** is accelerating; evaluate it before building custom tool-integration layers
+- **pgvector first** for new RAG projects; only migrate to a dedicated vector DB when you hit real limits
+- **vLLM + self-hosted inference** is viable at mid-scale; evaluate against API costs at ~$500/month
+- **LangGraph > LangChain** for anything involving agent state, branching, or loops
+- **Biome over ESLint+Prettier** for new TS projects — same rules, 50–100x faster
+- **uv over pip/poetry** for Python projects — significantly faster, better lockfiles
 - **Neon over Supabase** when inactivity pausing is a problem (portfolio projects, low-traffic apps)

package/.env.axiom

@@ -0,0 +1,8 @@
+# npm security key for cikal
+npm-security-key-cikal=your_npm_security_key_here
+
+# MCP Server Credentials
+N8N_MCP_TOKEN=your_n8n_mcp_token_here
+NEON_API_KEY=your_neon_api_key_here
+
+# Add other environment variables as needed

package/AGENTS.md

@@ -36,4 +36,5 @@ I write code that survives contact with reality.
 - NEVER declare "it works" without verification
 - NEVER add dependencies without checking if built-ins suffice
 - NEVER over-engineer for a scale that doesn't exist yet
-- ALWAYS ask: "Does this solve the actual problem?"
+- ALWAYS ask: "Does this solve the actual problem?"
+- **ALWAYS reference the current date/time**: Today is {Month} {Year}. You search the current date in your operations and always remember that. When performing web searches or any time-sensitive queries, explicitly use the current year to avoid retrieving outdated results from previous years like 2024 or 2025.

package/README.md

@@ -21,6 +21,8 @@ npx axiom-setup
 This command downloads the following files from the [axiom-coding-agent-setup](https://github.com/mcikalmerdeka/axiom-coding-agent-setup) repository into your current project directory:
 
 - `AGENTS.md` — Main agent instructions
+- `opencode.json` — OpenCode IDE configuration (MCP servers, plugins)
+- `.env.axiom` — Environment variables template for AXIOM credentials
 - `.agents/engineering.md` — Engineering principles & code standards
 - `.agents/stack.md` — Technology stack knowledge
 - `.agents/workflow.md` — Workflow guidelines & verification protocol
@@ -30,7 +32,13 @@ This command downloads the following files from the [axiom-coding-agent-setup](h
 ## Files Included
 
 ### AGENTS.md
-The main instruction file that coding agents (Claude, Cursor, etc.) read first when working on your project.
+The main instruction file that coding agents (Claude, Cursor, OpenCode, etc.) read first when working on your project.
+
+### opencode.json
+OpenCode IDE configuration including:
+- MCP server definitions (remote tools like n8n, Neon, Gradio, etc.)
+- Plugin configuration
+- Environment variable references for secure credential management
 
 ### .agents/engineering.md
 Core engineering principles including:
@@ -64,10 +72,18 @@ Project-type specific convention files:
 
 ### .agents/skills/
 Domain-specific skills that can be loaded on-demand:
-- `mcp-builder/` — MCP server development guide
-- `n8n-patterns/` — n8n workflow automation patterns
+- `agent-browser/` — Web browser automation skill
 - `ai-integration/` — LLM/AI integration patterns
 - `deployment-patterns/` — Deployment and infrastructure guide
+- `developing-with-streamlit/` — Streamlit app development guides
+- `fastapi/` — FastAPI best practices and patterns
+- `fastapi-templates/` — FastAPI project templates
+- `frontend-design/` — Frontend UI/UX design patterns
+- `git-commit/` — Conventional commit message generation
+- `gradio/` — Gradio UI framework guides
+- `mcp-builder/` — MCP server development guide
+- `n8n-patterns/` — n8n workflow automation patterns
+- `ui-ux-pro-max/` — Advanced UI/UX design skill
 
 ## Development
 

package/bin/cli.js

@@ -20,6 +20,8 @@ const FILES_TO_DOWNLOAD = [
   'AGENTS.md',
   // OpenCode configuration
   'opencode.json',
+  // Environment variables template
+  '.env.axiom',
   // Core agent documents
   '.agents/engineering.md',
   '.agents/stack.md',
@@ -28,12 +30,18 @@ const FILES_TO_DOWNLOAD = [
   '.agents/templates/ai-engineering-python.md',
   '.agents/templates/fullstack-ai-nextjs.md',
   // Skills (domain-specific guides)
+  '.agents/skills/agent-browser/SKILL.md',
   '.agents/skills/ai-integration/SKILL.md',
   '.agents/skills/deployment-patterns/SKILL.md',
+  '.agents/skills/developing-with-streamlit/SKILL.md',
+  '.agents/skills/fastapi/SKILL.md',
   '.agents/skills/fastapi-templates/SKILL.md',
+  '.agents/skills/frontend-design/SKILL.md',
   '.agents/skills/git-commit/SKILL.md',
+  '.agents/skills/gradio/SKILL.md',
   '.agents/skills/mcp-builder/SKILL.md',
-  '.agents/skills/n8n-patterns/SKILL.md'
+  '.agents/skills/n8n-patterns/SKILL.md',
+  '.agents/skills/ui-ux-pro-max/SKILL.md'
 ];
 
 const GITHUB_RAW_URL = `https://raw.githubusercontent.com/${REPO_OWNER}/${REPO_NAME}/${BRANCH}`;
@@ -127,6 +135,8 @@ async function main() {
   if (successCount > 0) {
     log('Your project now has AXIOM coding agent instructions:', 'bold');
     log('  - AGENTS.md                          → Main agent instructions', 'cyan');
+    log('  - opencode.json                      → OpenCode IDE configuration', 'cyan');
+    log('  - .env.axiom                         → Environment variables template', 'cyan');
     log('  - .agents/engineering.md             → Engineering principles', 'cyan');
     log('  - .agents/stack.md                   → Tech stack knowledge', 'cyan');
     log('  - .agents/workflow.md                → Workflow guidelines', 'cyan');

package/opencode.json

@@ -32,11 +32,14 @@
       "enabled": true,
       "headers": {}
     },
-    "n8n-docs": {
+    "n8n-mcp": {
       "type": "remote",
-      "url": "https://n8n.mcp.kapa.ai/",
+      "url": "http://localhost:5678/mcp-server/http",
       "enabled": true,
-      "headers": {}
+      "headers": {
+        "Authorization": "Bearer {env:N8N_MCP_TOKEN}"
+      },
+      "oauth": false
     },
     "exa": {
       "type": "remote",
@@ -49,8 +52,13 @@
       "url": "https://mcp.neon.tech/mcp",
       "enabled": true,
       "headers": {
-        "Authorization": "Bearer napi_8jp6kt4ci2ob5lz0jzgv5wivdov439h72if6hg4zqyy2w1krw8f0thwmzl0e5dpz"
+        "Authorization": "Bearer {env:NEON_API_KEY}"
       }
+    },
+    "eraser": {
+      "type": "remote",
+      "url": "https://app.eraser.io/api/mcp",
+      "enabled": true
     }
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axiom-coding-agent-setup",
-  "version": "1.0.9",
+  "version": "1.0.11",
   "description": "CLI tool to download AXIOM coding agent setup files into your project",
   "main": "bin/cli.js",
   "bin": {

package/skills-lock.json

@@ -1,15 +1,51 @@
 {
   "version": 1,
   "skills": {
+    "agent-browser": {
+      "source": "vercel-labs/agent-browser",
+      "sourceType": "github",
+      "skillPath": "skills/agent-browser/SKILL.md",
+      "computedHash": "228f87d57035100d9dc6efcfc05aafd4b6e3962adacaa04b8217ab2fadb15dc8"
+    },
+    "developing-with-streamlit": {
+      "source": "streamlit/agent-skills",
+      "sourceType": "github",
+      "skillPath": "developing-with-streamlit/SKILL.md",
+      "computedHash": "51823384978f738f76ff8f601e11c1343aebea03d2ad782dc73fc22d3f129812"
+    },
+    "fastapi": {
+      "source": "fastapi/fastapi",
+      "sourceType": "github",
+      "skillPath": "fastapi/.agents/skills/fastapi/SKILL.md",
+      "computedHash": "9feb517089c269af4fdab5031dea1100a92fd50081e906ccfaf8a971858e39f9"
+    },
     "fastapi-templates": {
       "source": "wshobson/agents",
       "sourceType": "github",
       "computedHash": "1a5fe66bd2683afd1db9afdf37a25cd8b9195c369c98489333badf0406fc91b3"
     },
+    "frontend-design": {
+      "source": "anthropics/skills",
+      "sourceType": "github",
+      "skillPath": "skills/frontend-design/SKILL.md",
+      "computedHash": "516bd2154eb843a8240e43d5b285229129853114ad7075a5e141e1c08e408c84"
+    },
     "git-commit": {
       "source": "github/awesome-copilot",
       "sourceType": "github",
       "computedHash": "2607fc60629b82b257136dd2a7a373f0a4466c0b49df7746d845d59313c99b21"
+    },
+    "gradio": {
+      "source": "gradio-app/gradio",
+      "sourceType": "github",
+      "skillPath": ".agents/skills/gradio/SKILL.md",
+      "computedHash": "5078d8a4cc2b562731620f36f5f0d3ad054bd51f7a98baa547b04b893744823b"
+    },
+    "ui-ux-pro-max": {
+      "source": "nextlevelbuilder/ui-ux-pro-max-skill",
+      "sourceType": "github",
+      "skillPath": ".claude/skills/ui-ux-pro-max/SKILL.md",
+      "computedHash": "6337038fe1fe6bbe1b9f252ab678ee575859190bab6f0f246f4061824eb40875"
     }
   }
 }