@chemx/starter-kit

v26.9.20-408

Published

12 hours ago

Chemical X Protocol: Private drop-in architecture starter kit and capsule generator

0High
0Medium
0Low

Chemical X Protocol: Starter Kit

Modular architecture blueprints, production hooks, and drop-in crystalline component capsule generators for high-velocity AI coding.

Live Interactive Portal

Access the interactive book, prompt generator, and asset vault at https://chemicalx.xophz.com.

Structure

starter-kit/
├── blueprints/
│   ├── view-template.tsx       # < 20 line Table-of-Contents view blueprint
│   ├── molecule-capsule/       # Isolated crystalline molecule blueprint
│   └── composable-template.ts  # Standardized 3-to-5 return state composable
├── hooks/
│   ├── useAsyncData.ts         # 3-state async pipeline with toResult
│   ├── useSelfCleaningTimer.ts # Unmount-safe timer and RAF hook
│   └── useTwoStageDecision.ts  # Concept to Decision composition
└── cli/
    ├── index.js                # CLI router & capsule generator
    ├── verify.js               # Zero-token-burn verification engine
    ├── audit.js                # 7-Pillar static AST audit
    └── mcp/                    # Model Context Protocol stdio server

Zero-Token-Burn Verification Pipeline

Running raw, unthrottled npm test, tsc --noEmit, or build tools dumps thousands of lines of passing checkmarks, compiler noise, and bundle asset tables into an AI agent's context window. This burns tokens prematurely and degrades context quality.

Chemical X wraps tests, typechecks, and builds into silent, failure-focused verification tools available via CLI and native MCP tools:

Side-by-Side Benchmark Reports

1. Test Suite: `npm test` vs `chemx test`

Ran across the starter-kit test suite (143 test cases across 8 spec suites):

# Raw npm test: Floods context with ~13,000 tokens of passing checkmarks
✔ resolveTargetDir: returns custom directory if provided as first argument (1.64ms)
✔ search-db: indexes symbols with line ranges and finds definition (56.65ms)
✔ Verify: parseTestOutput strips passing checkmarks and extracts only failing tests (1.01ms)
... [940 MORE LINES OF PASSING CHECKMARKS & TIMINGS] ...
ℹ tests 143 | pass 143 | fail 0 | duration_ms 3002.57ms

# Chemical X: Pinpoint single-line summary
$ npx chemx test
  ✔ All tests passed (143 tests in 3500ms)

2. TypeScript Typecheck: `npm run typecheck` vs `chemx typecheck`

# Clean, banner-free terminal verification
$ npx chemx typecheck
  ✔ TypeScript typecheck clean (1820ms)

# Machine-readable output for AI agents
$ npx chemx typecheck --json
{
  "success": true,
  "exitCode": 0,
  "command": "npm run typecheck",
  "durationMs": 1820,
  "errorCount": 0,
  "errors": []
}

3. Production Build: Raw Build vs `chemx build`

$ npx chemx build
Auditing build: npx tsc --noEmit
✔ Build Succeeded (5.20s)

4. Full Pipeline: `chemx verify` Grand Total

When an AI agent runs a complete pre-commit or post-refactor verification pass:

$ npx chemx verify --dir=blueprints

  ⚡ Chemical X: Token-Conserving Project Verification

  ✔ AST Architecture:  A+ (100/100, 0 violations)
  ✔ TypeScript:        Clean (0 errors)
  ✔ Test Suite:        Passed (143/143)

  All verification checks passed with zero context burn!

Model Context Protocol (MCP) Server

Chemical X includes a high-performance, zero-dependency JSON-RPC 2.0 Stdio MCP server that connects directly to AI agent hosts (Cursor, Claude Desktop, Windsurf, Antigravity, VS Code).

Automatic 1-Step Installation

Run the interactive installer in your workspace root:

npx chemx install-mcp

This automatically registers the Chemical X server in:

.cursor/mcp.json (Cursor IDE)
.vscode/mcp.json (VS Code)
~/.gemini/config/mcp_config.json (Antigravity)
Injects chemx:mcp, chemx:verify, chemx:test, and chemx:typecheck into your package.json scripts

Manual MCP Server Configuration

To configure manually in your MCP client settings (e.g. claude_desktop_config.json or .cursor/mcp.json):

{
  "mcpServers": {
    "chemical-x": {
      "command": "npx",
      "args": ["-y", "chemx", "mcp"]
    }
  }
}

Available MCP Tools (14 Tools)

Living Resources & Prompts

Resources:
- chemx://directives: Mandatory Chemical X Molecular Architecture directives (AGENTS.md).
- chemx://scorecard: Live Molecular Health Index (MHI) grade, score, metrics, and active hazards.
- chemx://blueprints/molecule: Compliant molecule blueprint adhering to zero raw DOM standards.
- chemx://blueprints/view-template: Declarative 10-20 line Table-of-Contents view blueprint.
Prompts:
- chemx_remediate_hotspot: Dynamically inspects candidate file AST metrics and generates targeted decomposition instructions.
- chemx_harmonize_patterns: Generates Pre-Split Pattern Discovery instructions to extract shared capsules.

Release Versioning: Minute-Precision CalVer

This package adheres to Minute-Precision Calendar Versioning (YY.MM.DD-MMMM):

YY.MM.DD: Release date (e.g. 26.9.17 for Sept 17, 2026).
MMMM: Minute of the day (0 to 1439).

Check installed version at any time:

npx chemx --version
# create-chemx v26.9.17-606

Because autonomous coding agent models update frequently, this package is continuously integrated and deployed via automated CI whenever new agent directives, AST checks, or framework rules are tuned. Rapid version iterations reflect active, daily alignment rather than breaking SemVer shifts.

[!NOTE] Download statistics on npm reflect continuous automated test matrix verification and test runner execution across automated environments.

License

Core CLI tools and capsule generators are distributed under the MIT License.
Private production monorepos and extended starter suites are unlocked for verified GitHub Sponsors.
Explore sponsorship details at https://chemicalx.xophz.com.

Published

Vulnerabilities

Links

Maintainers

Keywords

Readme