agentinit 1.0.1 → 1.2.0

package/CHANGELOG.md

@@ -1,3 +1,39 @@
+# [1.2.0](https://github.com/agentinit/agentinit/compare/v1.1.0...v1.2.0) (2025-09-20)
+
+
+### Bug Fixes
+
+* pckg lock ([ed4acbb](https://github.com/agentinit/agentinit/commit/ed4acbbc27c6342a109c81b91e6a23f264de1b9f))
+
+
+### Features
+
+* add --header flag support for HTTP MCP custom headers ([45a065f](https://github.com/agentinit/agentinit/commit/45a065f3b3876056acc76df4291db1808b94040a))
+
+# [1.1.1](https://github.com/agentinit/agentinit/compare/v1.1.0...v1.1.1) (TBD)
+
+### Features
+
+* add --header flag support for HTTP MCP custom headers ([COMMIT_HASH](https://github.com/agentinit/agentinit/commit/COMMIT_HASH))
+
+# [1.1.0](https://github.com/agentinit/agentinit/compare/v1.0.1...v1.1.0) (2025-09-19)
+
+
+### Bug Fixes
+
+* resolve all TypeScript compilation errors ([6b8535e](https://github.com/agentinit/agentinit/commit/6b8535e89e5e701587199fce519bd4d449d186e3))
+* tests fix, enhance gitignore ([47ae616](https://github.com/agentinit/agentinit/commit/47ae616559a144ae1c2025060cffeefde494baac))
+
+
+### Features
+
+* add apply cmd ([c813d82](https://github.com/agentinit/agentinit/commit/c813d829aa0ef51029516f9e35af752efbb006e0))
+* add DEBUG=1 flag to show all agents in detect command ([5b6527b](https://github.com/agentinit/agentinit/commit/5b6527bf0174f23be15a9795bb617e303283f5af))
+* add MCP verification with token counting and DEBUG mode support ([b785530](https://github.com/agentinit/agentinit/commit/b78553073756719f40699591f2915190451fa285))
+* add structured config file definitions and Cursor MDC support ([9af939c](https://github.com/agentinit/agentinit/commit/9af939c8102810d8f0a1d562fe5d561cf62af230))
+* enhance MCP verification and project configuration ([8af8a09](https://github.com/agentinit/agentinit/commit/8af8a09a974c2f0f6075fda60e72c120517af13a))
+* less commands ([f5b0795](https://github.com/agentinit/agentinit/commit/f5b07958f3296aa74e1d378d3e66fcf2146a6c00))
+
 ## [1.0.1](https://github.com/agentinit/agentinit/compare/v1.0.0...v1.0.1) (2025-09-06)
 
 

package/README.md

@@ -10,6 +10,7 @@ AgentInit transforms AI agent configuration from a fragmented, manual process in
 - **🔍 Smart Stack Detection**: Automatically detects project language, framework, and tools
 - **🔄 Bidirectional Sync**: Keep agent configurations in sync across Claude, Cursor, Windsurf, and more
 - **📦 MCP Management**: Interactive installation and management of Model Context Protocol tools
+- **📋 Rules Templates**: Apply coding best practices with predefined rule templates (Git, testing, docs, linting)
 - **⚙️ Project Templates**: Pre-built templates for web apps, CLI tools, libraries, and more
 - **🎯 Stack-Aware Guidance**: Customized instructions based on your technology stack
 
@@ -20,9 +21,6 @@ AgentInit transforms AI agent configuration from a fragmented, manual process in
 ```bash
 # Install AgentInit globally
 npm install -g agentinit
-
-# Or use with Bun
-bun install -g agentinit
 ```
 
 ### Basic Usage
@@ -65,10 +63,14 @@ agentinit init --force            # Overwrite existing configuration
 Detect current project stack and existing agent configurations.
 
 ```bash
-agentinit detect           # Basic detection
+agentinit detect           # Basic detection (only shows found agents)
 agentinit detect --verbose # Detailed information
+DEBUG=1 agentinit detect   # Show all supported agents (found and not found)
 ```
 
+**Environment Variables:**
+- `DEBUG=1` - Shows all supported agents, including those not found in the project
+
 ### `agentinit sync`
 
 Sync agents.md with agent-specific configuration files.
@@ -90,6 +92,31 @@ agentinit mcp --search <query>     # Search MCPs
 agentinit mcp --install <name>     # Install specific MCP
 ```
 
+### `agentinit verify_mcp`
+
+Verify MCP server installations and list their capabilities.
+
+```bash
+agentinit verify_mcp --all              # Verify all configured MCP servers
+agentinit verify_mcp --mcp-name <name>  # Verify specific MCP server
+```
+
+**Examples:**
+```bash
+# Verify all MCPs in project
+agentinit verify_mcp --all
+
+# Verify specific server
+agentinit verify_mcp --mcp-name everything
+
+# Test MCP configuration directly
+agentinit verify_mcp --mcp-stdio everything "npx -y @modelcontextprotocol/server-everything"
+
+agentinit verify_mcp --mcp-http
+```
+
+Shows connection status, response time, and available tools/resources/prompts for each MCP server.
+
 ### `agentinit apply`
 
 Apply configurations including MCP server setup.
@@ -98,12 +125,13 @@ Apply configurations including MCP server setup.
 
 
 ```bash
-# Configure STDIO MCP with arguments
+# Configure STDIO MCP with everything server (recommended example)
 npx agentinit apply \
-  --mcp-stdio context7 "npx -y @upstash/context7-mcp" --args "--api-key=YOUR_API_KEY"
+  --mcp-stdio everything "npx -y @modelcontextprotocol/server-everything"
 
 # Configure multiple MCPs in one command
 npx agentinit apply \
+  --mcp-stdio everything "npx -y @modelcontextprotocol/server-everything" \
   --mcp-stdio supabase "npx -y @supabase/mcp-server-supabase@latest" \
     --args "--read-only --project-ref=<project-ref>" \
     --env "SUPABASE_ACCESS_TOKEN=<personal-access-token>" \
@@ -114,14 +142,78 @@ npx agentinit apply \
 npx agentinit apply \
   --mcp-http github "https://api.githubcopilot.com/mcp/" --auth "Bearer YOUR_GITHUB_PAT"
 
+# Configure HTTP MCP with custom headers
+npx agentinit apply \
+  --mcp-http context7 "https://mcp.context7.com/mcp" \
+  --header "CONTEXT7_API_KEY:YOUR_API_KEY"
+
+# Multiple custom headers
+npx agentinit apply \
+  --mcp-http api_server "https://api.example.com/mcp" \
+  --header "X-API-Key:YOUR_API_KEY" \
+  --header "X-Client-ID:YOUR_CLIENT_ID"
+
+# Combine Bearer auth with custom headers
+npx agentinit apply \
+  --mcp-http advanced_api "https://api.example.com/mcp" \
+  --auth "Bearer YOUR_TOKEN" \
+  --header "X-Custom-Header:custom_value"
+
 # Configure Docker-based MCP with environment
 npx agentinit apply \
   --mcp-stdio browserbase "docker run -i --rm ghcr.io/metorial/mcp-container--browserbase--mcp-server-browserbase--browserbase node cli.js" \
   --env "BROWSERBASE_API_KEY=browserbase-api-key"
+
+# Global configuration with custom headers
+npx agentinit apply --global --client claude \
+  --mcp-http context7 "https://mcp.context7.com/mcp" \
+  --header "CONTEXT7_API_KEY:YOUR_API_KEY"
+
+# Verify MCPs immediately after configuration
+npx agentinit apply --verify-mcp \
+  --mcp-stdio everything "npx -y @modelcontextprotocol/server-everything"
 ```
 
 This generates `.agentinit/agentinit.toml` with your MCP configurations.
 
+**MCP Authentication Options**:
+- `--auth "Bearer TOKEN"` - Adds Authorization header for Bearer token authentication
+- `--header "KEY:VALUE"` - Adds custom headers in KEY:VALUE format (can be used multiple times)
+- Both flags can be combined for APIs requiring multiple authentication methods
+
+**MCP Verification**: Use the `--verify-mcp` flag to test MCP servers immediately after configuration. This ensures servers are reachable and shows their available tools, resources, and prompts.
+
+#### Rules Configuration
+
+Apply coding rules and best practices to your AI agents using predefined templates or custom rules.
+
+```bash
+# Apply rule templates (recommended combinations)
+agentinit apply --rules git,write_tests,use_linter
+
+# Mix templates with custom rules
+agentinit apply --rules git,write_docs --rule-raw "Use TypeScript strict mode"
+
+# Load rules from a file
+agentinit apply --rules-file ./project-rules.md
+
+# Apply globally to all projects using Claude
+agentinit apply --global --agent claude --rules git,write_tests
+
+# Combine with MCP configuration
+agentinit apply --rules git,use_linter --mcp-stdio context7 "npx @context7/mcp"
+```
+
+**Available Rule Templates:**
+- `git` - Enforce Git workflows and commit standards
+- `write_docs` - Require comprehensive documentation
+- `use_git_worktrees` - Enable parallel development with worktrees  
+- `use_subagents` - Delegate work to specialized subagents
+- `use_linter` - Enforce code quality and formatting
+- `write_tests` - Implement test-driven development practices
+
+**Token Tracking:** The apply command automatically tracks and displays token usage with color-coded output (🟢 Green ≤5k, 🟡 Yellow 5k-15k, 🔴 Red >15k) and git-style diffs to help manage AI context size. Example: `Rules: 101 tokens (-296)` shows rule tokens with change tracking.
+
 ## 🏗️ Project Structure
 
 AgentInit creates and manages these key files:
@@ -130,7 +222,10 @@ AgentInit creates and manages these key files:
 your-project/
 ├── agents.md                 # Universal agent configuration
 ├── CLAUDE.md                 # Claude-specific config (synced)
-├── .cursorrules              # Cursor-specific config (synced)
+├── .cursor/rules/            # Cursor rules (MDC files)
+│   ├── 001_workspace.mdc
+│   └── 002_frontend.mdc
+├── AGENTS.md                 # Simple agent instructions (alternative)
 └── .windsurfrules           # Windsurf-specific config (synced)
 ```
 
@@ -171,7 +266,7 @@ This is a TypeScript project using Next.js...
 | Agent | Config File | Status |
 |-------|-------------|--------|
 | Claude | `CLAUDE.md` | ✅ |
-| Cursor | `.cursorrules` | ✅ |
+| Cursor | `.cursor/rules/*.mdc` or `AGENTS.md` | ✅ |
 | Windsurf | `.windsurfrules` | ✅ |
 | Copilot | `.github/copilot.yml` | 🚧 |
 | Codeium | `.codeium/config.json` | 🚧 |