mason-context 0.2.1 → 0.2.3

package/README.md

@@ -1,5 +1,11 @@
 # Mason – the context builder for LLMs 👷
 
+[![npm version](https://img.shields.io/npm/v/mason-context)](https://www.npmjs.com/package/mason-context)
+[![CI](https://img.shields.io/github/actions/workflow/status/adrianczuczka/mason/ci.yml?branch=main)](https://github.com/adrianczuczka/mason/actions/workflows/ci.yml)
+[![npm downloads](https://img.shields.io/npm/dm/mason-context)](https://www.npmjs.com/package/mason-context)
+[![license](https://img.shields.io/github/license/adrianczuczka/mason)](https://github.com/adrianczuczka/mason/blob/main/LICENSE)
+[![issues](https://img.shields.io/github/issues/adrianczuczka/mason)](https://github.com/adrianczuczka/mason/issues)
+
 Mason gives LLMs a persistent map of your codebase so they stop exploring from scratch every session.
 
 **The problem:** Every time an LLM starts a new conversation about your code, it greps, reads files, and pieces together the architecture — burning tokens on context it already understood yesterday. On a 164-file project, answering "what features does this app have?" requires reading 8+ files across multiple tool calls.
@@ -21,7 +27,7 @@ Same answer quality (0.9/1.0 on all tests, both paths). Reproduce: [bench/](benc
 ## Quick start
 
 ```bash
-claude mcp add mason --scope user -- npx mason-context mcp
+claude mcp add mason --scope user -- npx -p mason-context mason-mcp
 ```
 
 Restart Claude Code, then ask: *"use mason to analyze this project and create a snapshot."*

package/dist/bin/mason-mcp.js

@@ -1235,7 +1235,7 @@ function createMcpServer() {
   const server = new McpServer(
     {
       name: "mason",
-      version: "0.2.1"
+      version: "0.2.3"
     },
     {
       instructions: "Mason is a context engineering tool. Always call get_snapshot before using Explore agents, Glob, or Grep to understand the codebase. The snapshot is a concept map that maps features and flows to their implementing files \u2014 it eliminates the need to search. This applies to ANY question about architecture, features, flows, how things work, cross-feature interactions, or bug investigation. Workflow: 1) Call get_snapshot first. 2) If no snapshot, call full_analysis and then save_snapshot to create one. 3) If the snapshot is stale, tell the user and offer to update it. 4) Use your native file reading tool to read files the snapshot points to. 5) Before modifying a file, call get_impact to check what else might be affected. 6) After making significant changes (new features, refactors, architecture changes), call save_snapshot to update the concept map."

package/dist/bin/mason.js

@@ -1786,7 +1786,7 @@ function createMcpServer() {
   const server = new McpServer(
     {
       name: "mason",
-      version: "0.2.1"
+      version: "0.2.3"
     },
     {
       instructions: "Mason is a context engineering tool. Always call get_snapshot before using Explore agents, Glob, or Grep to understand the codebase. The snapshot is a concept map that maps features and flows to their implementing files \u2014 it eliminates the need to search. This applies to ANY question about architecture, features, flows, how things work, cross-feature interactions, or bug investigation. Workflow: 1) Call get_snapshot first. 2) If no snapshot, call full_analysis and then save_snapshot to create one. 3) If the snapshot is stale, tell the user and offer to update it. 4) Use your native file reading tool to read files the snapshot points to. 5) Before modifying a file, call get_impact to check what else might be affected. 6) After making significant changes (new features, refactors, architecture changes), call save_snapshot to update the concept map."
@@ -1970,7 +1970,7 @@ function createCLI() {
   const program2 = new Command();
   program2.name("mason").description(
     "Context engineering CLI & MCP server \u2014 generates intelligent CLAUDE.md files"
-  ).version("0.1.0");
+  ).version("0.2.3");
   program2.command("setup").description("Register Mason as an MCP server with Claude Code").option("--scope <scope>", "Config scope: user or project", "user").action(async (opts) => {
     const { execFile: execFile9 } = await import("child_process");
     const { promisify: promisify9 } = await import("util");