@itz4blitz/agentful 0.5.1 → 1.0.0

package/README.md

@@ -4,29 +4,24 @@ A carrot on a stick for Claude Code
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![npm version](https://badge.fury.io/js/%40itz4blitz%2Fagentful.svg)](https://www.npmjs.com/package/@itz4blitz/agentful)
-[![Tests](https://img.shields.io/badge/tests-370%20passing-brightgreen)](https://github.com/itz4blitz/agentful)
-[![Coverage](https://img.shields.io/badge/coverage-98.26%25-brightgreen)](https://github.com/itz4blitz/agentful)
+[![CI Status](https://github.com/itz4blitz/agentful/actions/workflows/pipeline.yml/badge.svg)](https://github.com/itz4blitz/agentful/actions)
 
 ## Overview
 
-agentful is a production-ready Claude Code configuration that provides structured development through specialized AI agents. It coordinates multiple agents to implement features, write tests, and validate code quality according to a defined product specification, with human checkpoints for key decisions.
-
-**Production Quality**: Enterprise-grade testing (370 tests), 98.26% code coverage, comprehensive error handling, and lifecycle hooks for validation and metrics.
+agentful is a Claude Code configuration that provides structured development through specialized AI agents. It coordinates multiple agents to implement features, write tests, and validate code quality according to a defined product specification.
 
 ## Web Configurator
 
 Configure your agentful installation with an interactive web interface:
 
-**[agentful.app/configure](https://agentful.app/configure)**
+**[agentful.app](https://agentful.app)**
 
 - Visual component selection
-- 5 optimized presets
+- 2 optimized presets
 - Custom configurations
 - Shareable setup URLs
 - No CLI required
 
-See the [Web Configurator Guide](https://agentful.app/getting-started/configurator) for details.
-
 ## Installation
 
 ### Default Installation (Recommended)
@@ -40,7 +35,6 @@ npx @itz4blitz/agentful init
 This installs:
 - **8 agents**: orchestrator, architect, backend, frontend, tester, reviewer, fixer, product-analyzer
 - **6 skills**: product-tracking, validation, testing, conversation, product-planning, deployment
-- **Hooks**: health-check (configurable)
 - **Quality gates**: types, tests, coverage, lint, security, dead-code
 
 **Tech stack is auto-detected** on first run (TypeScript, Python, React, etc.) - no need to specify.
@@ -71,17 +65,16 @@ npx @itz4blitz/agentful presets
 
 ### Shareable Configurations
 
-Use a configuration from [agentful.app/configure](https://agentful.app/configure):
+Use a configuration from the web configurator:
 
 ```bash
-npx @itz4blitz/agentful init --config=https://agentful.app/c/abc12345
+npx @itz4blitz/agentful init --config=<shareable-url>
 ```
 
 **Available Flags:**
 - `--preset=<name>` - Use a preset configuration
 - `--agents=<list>` - Comma-separated list of agents (orchestrator, backend, frontend, tester, reviewer, fixer, architect, product-analyzer)
 - `--skills=<list>` - Comma-separated list of skills (validation, testing, product-tracking, conversation, product-planning, deployment)
-- `--hooks=<list>` - Comma-separated list of hooks (health-check, typescript-validation, notifications, format-on-save)
 - `--gates=<list>` - Comma-separated list of quality gates (types, tests, coverage, lint, security, dead-code)
 
 Flags override preset values when both are specified.
@@ -196,7 +189,7 @@ For projects with existing code:
 
 ### Agent System
 
-agentful uses seven specialized agents:
+agentful uses eight specialized agents:
 
 | Agent | Responsibility |
 |-------|---------------|
@@ -207,15 +200,16 @@ agentful uses seven specialized agents:
 | tester | Writes unit, integration, and end-to-end tests |
 | reviewer | Validates code quality, security, and standards |
 | fixer | Resolves validation failures and test errors |
+| product-analyzer | Analyzes product specs for gaps, ambiguities, and readiness scoring |
 
 ### Quality Gates
 
-Code changes are validated against 6 core automated quality gates:
+Code changes are validated against 6 automated quality gates:
 
 - Type checking (TypeScript, Flow, etc.)
 - Linting (ESLint, Biome, etc.)
-- Test execution (all tests must pass)
-- Code coverage (minimum 80%)
+- Test execution
+- Code coverage
 - Security scanning
 - Dead code detection
 
@@ -230,13 +224,11 @@ Runtime state is stored in `.agentful/` (gitignored, managed by npm package):
   - New projects: Starts with declared stack (`confidence: 0.4`)
   - Existing projects: Detected from code (`confidence: 0.8-1.0`)
   - Re-analyzed after first implementation in new projects
-- `last-validation.json` - Latest test/lint results
 - `conversation-history.json` - Session tracking
-- `product-analysis.json` - Readiness analysis (generated by `/agentful-product`)
 
 User configuration is stored in `.claude/` (version controlled):
 
-- `agents/` - Agent definitions (core + custom + ephemeral)
+- `agents/` - Agent definitions
 - `commands/` - Slash commands
 - `product/` - Product specifications
   - `index.md` - Main product spec (user editable)
@@ -246,20 +238,23 @@ User configuration is stored in `.claude/` (version controlled):
   - `product-tracking/` - Progress calculation and state tracking
   - `product-planning/` - Product specification guidance
   - `validation/` - Quality gate checks and tool detection
+  - `testing/` - Test strategy and coverage
+  - `deployment/` - Deployment preparation and validation
 - `settings.json` - Project configuration
 
-**See [ARCHITECTURE.md](./ARCHITECTURE.md) for detailed explanation of file organization.**
-
 ## Commands
 
 | Command | Description |
 |---------|-------------|
+| `/agentful` | Main agentful command - shows help and available commands |
 | `/agentful-product` | Smart product planning: create, analyze, and refine requirements |
 | `/agentful-start` | Start or resume structured development |
 | `/agentful-status` | Display progress and current state |
 | `/agentful-validate` | Run all quality checks |
 | `/agentful-decide` | Answer pending decisions |
 | `/agentful-update` | Smart update mechanism - fetches latest templates and gracefully migrates changes |
+| `/agentful-analyze` | Analyze architecture and generate specialized agents for your tech stack |
+| `/agentful-generate` | Generate specialized agents from architecture analysis |
 
 ## CI/CD Integration
 
@@ -273,7 +268,7 @@ agentful ci --generate-workflow
 agentful ci
 ```
 
-See `examples/` for sample workflow configurations ([GitHub Actions](examples/github-actions.yml), [GitLab CI](examples/gitlab-ci.yml), [Jenkins](examples/jenkins.groovy)).
+See `examples/` for sample workflow configurations ([GitHub Actions](examples/github-actions-pipeline.yml), [GitLab CI](examples/gitlab-ci-cd.yml)).
 
 ## Remote Execution
 
@@ -290,7 +285,7 @@ agentful serve --auth=hmac --secret=$SECRET --https --cert=cert.pem --key=key.pe
 agentful serve --auth=none
 ```
 
-Three authentication modes: **Tailscale** (WireGuard encryption), **HMAC** (signature-based with replay protection), **SSH tunnel** (localhost-only). See `examples/server-deployment.sh` for complete deployment examples including Oracle Cloud Free Tier, Let's Encrypt SSL, and systemd service configuration.
+Three authentication modes: **Tailscale** (WireGuard encryption), **HMAC** (signature-based with replay protection), **SSH tunnel** (localhost-only).
 
 ## Technology Support
 
@@ -311,13 +306,7 @@ agentful detects and adapts to your technology stack automatically:
 
 ## Documentation
 
-Full documentation: [agentful.app](https://agentful.app)
-
-Key guides:
-- [CI/CD Integration](https://agentful.app/ci-integration) - Deploy agents to production
-- [Quick Start](https://agentful.app/getting-started/quick-start) - Get started in 5 minutes
-- [Agent Architecture](https://agentful.app/concepts/architecture) - How agents work
-- [Commands Reference](https://agentful.app/commands) - All available commands
+Documentation: [agentful.app](https://agentful.app)
 
 ## Project Structure
 
@@ -337,7 +326,6 @@ your-project/
 │   ├── completion.json
 │   ├── decisions.json
 │   ├── architecture.json
-│   ├── last-validation.json
 │   └── conversation-history.json
 └── src/                            # Source code
 ```
@@ -350,5 +338,4 @@ MIT
 
 - GitHub: [github.com/itz4blitz/agentful](https://github.com/itz4blitz/agentful)
 - Issues: [github.com/itz4blitz/agentful/issues](https://github.com/itz4blitz/agentful/issues)
-- Documentation: [agentful.app](https://agentful.app)
-- NPM: [npmjs.com/@itz4blitz/agentful](https://www.npmjs.com/package/@itz4blitz/agentful)
+- NPM: [npmjs.com/package/@itz4blitz/agentful](https://www.npmjs.com/package/@itz4blitz/agentful)

package/lib/init.js

@@ -91,32 +91,40 @@ export async function initProject(targetDir, config = null) {
     await fs.mkdir(agentfulDir, { recursive: true });
     createdFiles.push('.agentful/');
 
-    // Create state.json
+    // Create state.json (runtime state for orchestrator)
     const stateFile = path.join(agentfulDir, 'state.json');
     const initialState = {
-      initialized: new Date().toISOString(),
-      version: '1.0.0',
-      agents: [],
-      skills: []
+      version: '1.0',
+      current_task: null,
+      current_phase: 'idle',
+      iterations: 0,
+      last_updated: new Date().toISOString(),
+      blocked_on: []
     };
     await fs.writeFile(stateFile, JSON.stringify(initialState, null, 2));
     createdFiles.push('.agentful/state.json');
 
-    // Create completion.json
+    // Create completion.json (feature progress tracking)
     const completionFile = path.join(agentfulDir, 'completion.json');
     const initialCompletion = {
-      agents: {},
-      skills: {},
-      lastUpdated: new Date().toISOString()
+      features: {},
+      gates: {
+        tests_passing: false,
+        no_type_errors: false,
+        no_dead_code: false,
+        coverage_80: false,
+        security_clean: false
+      },
+      overall_progress: 0
     };
     await fs.writeFile(completionFile, JSON.stringify(initialCompletion, null, 2));
     createdFiles.push('.agentful/completion.json');
 
-    // Create decisions.json
+    // Create decisions.json (pending and resolved decisions)
     const decisionsFile = path.join(agentfulDir, 'decisions.json');
     const initialDecisions = {
-      decisions: [],
-      lastUpdated: new Date().toISOString()
+      pending: [],
+      resolved: []
     };
     await fs.writeFile(decisionsFile, JSON.stringify(initialDecisions, null, 2));
     createdFiles.push('.agentful/decisions.json');

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@itz4blitz/agentful",
-  "version": "0.5.1",
+  "version": "1.0.0",
   "description": "Human-in-the-loop development kit for Claude Code with smart product analysis and natural conversation",
   "type": "module",
   "bin": {

package/version.json

@@ -1,3 +1,3 @@
 {
-  "version": "0.5.0"
+  "version": "0.5.1"
 }