kodelyth-ecc 1.2.2 → 1.3.0

package/README.md

@@ -4,57 +4,69 @@
 
 [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 ![Claude Code](https://img.shields.io/badge/Claude%20Code-Ready-8A2BE2)
+![Windsurf](https://img.shields.io/badge/Windsurf-Ready-06b6d4)
 ![Antigravity](https://img.shields.io/badge/Antigravity-Ready-00ADD8)
-![Version](https://img.shields.io/badge/version-1.2.0-orange)
-![Agents](https://img.shields.io/badge/Agents-53-brightgreen)
-![Skills](https://img.shields.io/badge/Skills-185-brightgreen)
+![Cursor](https://img.shields.io/badge/Cursor-Ready-3b82f6)
+![Codex](https://img.shields.io/badge/Codex-Ready-10b981)
+![Version](https://img.shields.io/badge/version-1.3.0-orange)
+![Agents](https://img.shields.io/badge/Agents-58-brightgreen)
+![Skills](https://img.shields.io/badge/Skills-187-brightgreen)
 
 </div>
 
-**Kodelyth ECC** is a battle-tested, production-ready AI coding toolkit — 53 specialist agents, 185 skills, 79 commands, automated quality gates, and a real-time usage dashboard built in. Built and maintained by **Kodelyth**.
+**Kodelyth ECC** is a production-grade AI coding toolkit — **58 specialist agents, 187 skills, 79 commands**, and a god-tier **intent-routing system** that auto-detects what you need and hands you the right specialist before you finish typing.
 
-Works with **Claude Code**, **Google Antigravity**, **Cursor**, **Codex CLI**, and **OpenCode**.
+Works with **Claude Code**, **Windsurf**, **Cursor**, **Codex CLI**, **Google Antigravity**, and **OpenCode**.
+
+> No dashboard. No telemetry. No cloud. Just rules, agents, and skills your AI loads on every session.
 
 ---
 
-## Install
+## What Makes ECC Different
 
-### Option 1 — npx from npm (Node.js 18+, any platform)
+Most "AI agent kits" are folders of markdown files you have to remember the names of. ECC has **intent routing** baked into the rules layer — you describe your problem in plain words, the AI announces which specialist is taking over, and you get senior-grade help without memorizing a directory.
 
-The simplest install. Node.js is the only requirement.
+```
+You:   "I've been staring at this NullPointerException for two hours,
+        I'm losing my mind."
 
-```bash
-npx kodelyth-ecc
+AI:    → Routing to debug-detective (your error + frustration matches the bug-tracking signal)
+
+       That kind of bug is exhausting — let's trace it properly so we
+       fix the root cause, not the symptom.
+
+       First, can you share the full stack trace and...
 ```
 
-Install for a specific platform:
+You never typed `use debug-detective`. You didn't have to.
+
+---
+
+## Install
+
+### Option 1 — npx from npm (recommended, any platform)
 
 ```bash
-npx kodelyth-ecc --target windsurf-project    # Windsurf (project)
+npx kodelyth-ecc                              # Claude Code (default)
+npx kodelyth-ecc --target windsurf-project    # Windsurf (per-project)
 npx kodelyth-ecc --target windsurf-home       # Windsurf (global)
-npx kodelyth-ecc --target antigravity         # Google Antigravity
 npx kodelyth-ecc --target cursor-project      # Cursor IDE
 npx kodelyth-ecc --target codex-home          # Codex CLI
+npx kodelyth-ecc --target antigravity         # Google Antigravity
 npx kodelyth-ecc --target opencode            # OpenCode
 ```
 
-> Node.js not installed? Download it from [nodejs.org](https://nodejs.org) — LTS version recommended.
-
----
+Node.js 18+ required. [Download Node](https://nodejs.org) if you don't have it.
 
 ### Option 2 — npx from GitHub (always latest commit)
 
-Use this if you want the very latest unreleased version directly from the main branch.
-
 ```bash
 npx github:sifxprime/kodelyth-ecc
 ```
 
-Same `--target` flags apply.
-
----
+Same `--target` flags work.
 
-### Option 3 — curl (macOS / Linux)
+### Option 3 — curl (macOS / Linux only)
 
 ```bash
 curl -fsSL https://raw.githubusercontent.com/sifxprime/kodelyth-ecc/main/install.sh | bash
@@ -66,81 +78,76 @@ With a target:
 curl -fsSL https://raw.githubusercontent.com/sifxprime/kodelyth-ecc/main/install.sh | bash -s -- --target windsurf-project
 ```
 
----
-
-### Option 4 — clone and run (all platforms)
+### Option 4 — Clone and run
 
 ```bash
 git clone https://github.com/sifxprime/kodelyth-ecc.git
 cd kodelyth-ecc
 
 # macOS / Linux
-./install.sh                             # Claude Code (default)
-./install.sh --target windsurf-project  # Windsurf
-./install.sh --target antigravity       # Google Antigravity
+./install.sh                              # Claude Code (default)
+./install.sh --target windsurf-project    # Windsurf
 
 # Windows (PowerShell)
 .\install.ps1
 .\install.ps1 -Target windsurf-project
-.\install.ps1 -Target codex-home
 ```
 
 ---
 
-The installer automatically starts **Kodelyth Lens** and opens your browser when done (Claude Code target only).
-
----
-
-## Kodelyth Lens — AI Usage Dashboard
+## How Intent Routing Works
 
-<img src="social/readme-lens.svg" alt="Kodelyth Lens Dashboard" width="900"/>
+The toolkit ships with a single rule file (`rules/common/agent-intent-routing.md`) that the AI loads automatically on every session. It maps **what you say** to **the right specialist agent** across 10 priority tiers.
 
-**Kodelyth Lens** is a zero-dependency real-time dashboard included with every ECC install. It reads directly from your AI coding platform data files — no cloud, no account, no npm install.
+### Two activation paths
 
-<img src="social/readme-savings.svg" alt="ECC Cost Savings" width="900"/>
+**1. Explicit** — type it directly:
+```
+use debug-detective
+@code-reviewer
+invoke security-reviewer
+```
 
-### What Lens tracks
+**2. Implicit** — just describe your problem; the AI routes you:
 
-| Signal | How it works |
+| What you write | Auto-routed to |
 |---|---|
-| Agent invocations | Explicit: `use <agent>`, `@agent`, `invoke agent` |
-| Agent intent | 12 intent categories — "bug" → debug-detective, "slow" → performance-optimizer |
-| Token usage | Reads session JSONL files per platform |
-| Cache savings | Cache read tokens cost 10% — ECC prompt structure maximizes hits |
-| Platform breakdown | Per-platform session count, tokens, and cost |
-| Cost comparison | Actual paid vs. estimated without-ECC cost |
-
-### Supported platforms
+| "I'm stuck, no idea where to start" | `kodelyth-advisor` |
+| "I've been debugging this for hours" | `debug-detective` |
+| "Should I use Context or Zustand?" | `pair-programmer` |
+| "Build failed on Vercel" | `build-error-resolver` |
+| "Is this JWT signing secure?" | `security-reviewer` |
+| "Why is this so slow?" | `performance-optimizer` |
+| "Plan the v2 migration" | `planner` + `migration-guide` |
+| "Tests pass locally but fail on CI" | `flake-hunter` + `env-debugger` |
+| "I lost my commits after `reset --hard`" | `git-rescue` |
+| "npm install is failing" | `dependency-doctor` |
+| "Cut a 1.4 release" | `release-captain` |
+| "Add accessibility to this form" | `ux-reviewer` |
+| "Open-source this project" | `opensource-forker` (chain) |
+
+The AI **always announces** which agent is taking over (`→ Routing to <agent>`) and **always teaches** you the explicit form for next time (`Tip: type "use <agent>"`). No silent personality changes.
+
+### Multi-agent chains
+
+Real problems span multiple specialties. ECC ships standard handoff chains:
 
-| Platform | Data source | Sessions |
-|---|---|---|
-| Claude Code | `~/.claude/projects/**/*.jsonl` | Full local logs |
-| Codex CLI | `~/.codex/state_5.sqlite` | SQLite threads table |
-| Windsurf | `~/Library/Application Support/Windsurf/` | Cloud AI (server-side) |
-| Antigravity | `~/Library/Application Support/Antigravity/` | Cloud AI (server-side) |
-| Cursor | `~/.cursor/` | Local workspace data |
-| OpenCode | `~/.opencode/` | Local session files |
-
-Only installed platforms appear in the dashboard — nothing shown for platforms you don't have.
-
-### Manual start
-
-```bash
-node ~/.kodelyth/lens/server.js
-# → http://localhost:3456
+```
+pair-programmer  →  tdd-guide  →  code-reviewer  →  security-reviewer
+(approach)         (write tests)  (review impl)     (auth, validation)
 ```
 
-### Environment overrides
+```
+debug-detective  →  tdd-guide        →  refactor-cleaner
+(root cause)        (regression test)   (cleanup)
+```
 
-```bash
-CLAUDE_DIR=~/.claude          # Custom Claude Code data dir
-CURSOR_DIR=...                # Custom Cursor data dir
-WINDSURF_DIR=...              # Custom Windsurf data dir
-CODEX_DIR=~/.codex            # Custom Codex data dir
-OPENCODE_DIR=~/.opencode      # Custom OpenCode data dir
-ANTIGRAVITY_DIR=...           # Custom Antigravity data dir
-PORT=3456                     # Dashboard port (default: 3456)
 ```
+opensource-forker  →  opensource-sanitizer  →  opensource-packager  →  release-captain
+(clean fork)          (strip secrets)            (README, license)        (cut v0.1.0)
+```
+
+See `skills/agent-handoff/SKILL.md` for the full handoff protocol and standard chains.
 
 ---
 
@@ -148,116 +155,55 @@ PORT=3456                     # Dashboard port (default: 3456)
 
 | Component | Count | Description |
 |---|---|---|
-| Agents | **53** | Specialist subagents — reviewers, planners, debuggers, architects |
-| Skills | **185** | Domain knowledge — patterns, testing, security, DevOps |
+| Agents | **58** | Specialist subagents — reviewers, planners, debuggers, architects, doctors |
+| Skills | **187** | Domain knowledge — patterns, testing, security, DevOps, intent routing |
 | Commands | **79** | Slash command workflows (`/tdd`, `/plan`, `/code-review`, etc.) |
-| Hooks | **15+** | Automated lifecycle triggers — quality gates, session memory, cost tracking |
-| Rules | **15** | Language-specific coding standards |
+| Hooks | **15+** | Quality gates, session memory, secret scanning, branch checks |
+| Rules | **15** | Always-on coding standards + the intent routing rule |
 
 ---
 
 ## Agent Arsenal
 
-<img src="social/readme-agents.svg" alt="53 Specialist Agents" width="900"/>
-
-### Kodelyth Exclusives
-
-### `kodelyth-advisor` — The Master Guide
-A decade-seasoned principal engineer who reads your emotional state, understands what you're struggling with, and gives you the exact tool or approach needed. No hand-holding, no noise — direct senior-grade direction.
-
-```
-use kodelyth-advisor
-```
-
-### `debug-detective` — The Root Cause Hunter
-Never guesses. Traces every bug to its exact origin through a structured hypothesis protocol. Covers JS/TS, Python, Go, Rust, SQL — with advanced techniques like binary search debug, git bisect, and minimal reproducers.
-
-```
-use debug-detective
-```
-
-### `ux-reviewer` — The Interface Guardian
-Reviews frontend code for usability, interaction logic, and WCAG 2.1 AA accessibility. Never touches design aesthetic — only behavior. Catches what real users will feel before they feel it.
-
-```
-use ux-reviewer
-```
-
-### `api-guardian` — The API Contract Protector
-Detects breaking API changes before they ship. Classifies every change as BREAKING / SAFE / WARN, generates a consumer impact report, and enforces versioning, deprecation headers, and idempotency.
-
-```
-use api-guardian
-```
-
-### `pair-programmer` — The Pre-Code Thinking Partner
-The engineer who sits next to you before you start coding. Catches the wrong approach, over-engineered solutions, and missed edge cases — before a single line is written.
+### Kodelyth Exclusives — The 11 Agents That Make ECC
 
-```
-use pair-programmer
-```
-
-### `migration-guide` — The Framework Migration Specialist
-Full migration playbooks for React 18→19, Next.js 12→15, Python 2→3, Node.js 14→22, TypeScript 4→5, Java 8→21. Phase-by-phase: audit → blast radius → phased plan → execute → validate.
-
-```
-use migration-guide
-```
-
----
+| Agent | One-line job |
+|---|---|
+| `kodelyth-advisor` | Master guide — picks the right tool when you don't know where to start |
+| `pair-programmer` | The engineer who sits next to you **before** you write the code |
+| `debug-detective` | Never guesses — traces every bug to root cause |
+| `silent-failure-hunter` | Finds bugs that don't throw errors |
+| `ux-reviewer` | Reviews UX behavior + WCAG 2.1 AA accessibility (never touches design) |
+| `api-guardian` | Detects breaking API changes before they ship |
+| `migration-guide` | Framework / language version upgrades, phase by phase |
+| `dependency-doctor` | npm/pip/cargo/maven hell — CVE triage, lockfile diagnosis |
+| `git-rescue` | Recovers from broken git states without destroying history |
+| `release-captain` | Owns the release ritual — semver, tagging, publishing, rollback |
+| `env-debugger` | "Works on my machine" hunter — env, config, secrets, layers |
+| `flake-hunter` | Stabilizes flaky tests — never adds blind retries |
 
 ### Agent Categories
 
 | Category | Agents |
 |---|---|
-| Guidance | `kodelyth-advisor`, `pair-programmer`, `planner`, `architect`, `code-architect`, `chief-of-staff`, `migration-guide` |
-| Code Review | `code-reviewer`, `typescript-reviewer`, `python-reviewer`, `go-reviewer`, `rust-reviewer`, `java-reviewer`, `kotlin-reviewer`, `cpp-reviewer`, `csharp-reviewer`, `flutter-reviewer` |
-| Build Fixing | `build-error-resolver`, `go-build-resolver`, `rust-build-resolver`, `java-build-resolver`, `kotlin-build-resolver`, `cpp-build-resolver`, `dart-build-resolver`, `pytorch-build-resolver` |
-| Debugging | `debug-detective`, `silent-failure-hunter` |
-| UX & Design | `ux-reviewer` |
-| Security | `security-reviewer`, `healthcare-reviewer`, `api-guardian` |
-| Quality | `refactor-cleaner`, `code-simplifier`, `performance-optimizer`, `type-design-analyzer` |
-| Testing | `tdd-guide`, `e2e-runner`, `pr-test-analyzer` |
-| Documentation | `doc-updater`, `docs-lookup`, `comment-analyzer` |
-| Open Source | `opensource-forker`, `opensource-packager`, `opensource-sanitizer` |
-
----
-
-## How Agent Detection Works
-
-Agents activate in two ways — you do not always need to type `use agent-name`.
-
-**1. Explicit** — type it directly in your conversation:
-```
-use debug-detective
-@code-reviewer
-invoke security-reviewer
-```
-
-**2. Automatic intent detection** — Kodelyth Lens reads your prompts and infers which agent matches:
-
-| What you write | Agent triggered |
-|---|---|
-| "this bug won't fix", "I'm getting an error", "it's broken" | `debug-detective` |
-| "review this", "check my code", "LGTM?" | `code-reviewer` |
-| "it's slow", "taking too long", "optimize" | `performance-optimizer` |
-| "is this secure", "SQL injection", "auth" | `security-reviewer` |
-| "the build failed", "compile error", "type error" | `build-error-resolver` |
-| "write a test", "TDD", "coverage" | `tdd-guide` |
-| "the UI feels off", "accessibility", "WCAG" | `ux-reviewer` |
-| "plan this feature", "architecture", "design" | `planner` / `architect` |
-| "I'm not sure where to start", "what should I do" | `kodelyth-advisor` |
-| "refactor", "clean up", "dead code" | `refactor-cleaner` |
-| "document this", "add comments" | `doc-updater` |
-| "migrate", "upgrade framework", "breaking change" | `migration-guide` |
-
-Intent detection runs across all platforms — Claude Code, Windsurf, Cursor, Codex — anywhere Kodelyth Lens can read conversation logs. The dashboard shows both explicit and auto-detected agent activations in the leaderboard.
+| **Guidance** | `kodelyth-advisor`, `pair-programmer`, `planner`, `architect`, `code-architect`, `chief-of-staff`, `migration-guide` |
+| **Code Review** | `code-reviewer`, `typescript-reviewer`, `python-reviewer`, `go-reviewer`, `rust-reviewer`, `java-reviewer`, `kotlin-reviewer`, `cpp-reviewer`, `csharp-reviewer`, `flutter-reviewer`, `database-reviewer`, `healthcare-reviewer` |
+| **Build Fixers** | `build-error-resolver`, `go-build-resolver`, `rust-build-resolver`, `java-build-resolver`, `kotlin-build-resolver`, `cpp-build-resolver`, `dart-build-resolver`, `pytorch-build-resolver`, `dependency-doctor`, `env-debugger` |
+| **Debugging** | `debug-detective`, `silent-failure-hunter`, `flake-hunter` |
+| **Security & API** | `security-reviewer`, `api-guardian` |
+| **Performance** | `performance-optimizer` |
+| **Quality** | `refactor-cleaner`, `code-simplifier`, `type-design-analyzer` |
+| **Testing** | `tdd-guide`, `e2e-runner`, `pr-test-analyzer`, `flake-hunter` |
+| **Documentation** | `doc-updater`, `docs-lookup`, `comment-analyzer` |
+| **Release & Ops** | `release-captain`, `git-rescue` |
+| **Open Source** | `opensource-forker`, `opensource-packager`, `opensource-sanitizer` |
+| **Specialized** | `seo-specialist`, `ux-reviewer`, `code-explorer` |
 
 ---
 
 ## Hooks — Always Running in Background
 
-Once installed, these hooks run automatically with zero configuration:
+Once installed (Claude Code target), these hooks run automatically with zero configuration:
 
 | Hook | What it does |
 |---|---|
@@ -266,8 +212,7 @@ Once installed, these hooks run automatically with zero configuration:
 | Quality gate | Runs type checks and formatting after edits |
 | Git push reminder | Prompts review before pushing |
 | Config protection | Blocks weakening of linter/formatter configs |
-| Cost tracker | Logs token usage per session |
-| Desktop notify | macOS notification when Claude finishes a long task |
+| Desktop notify | macOS notification when a long task finishes |
 | MCP health check | Validates MCP servers before calling them |
 | Test reminder | Prompts to write tests when code is edited without tests |
 | Smart suggest | After each response, suggests the next logical agent |
@@ -278,11 +223,13 @@ Once installed, these hooks run automatically with zero configuration:
 ## Usage After Install
 
 ### Start here (new users)
+
 ```
 /kodelyth-quickstart
 ```
 
-### Core workflows
+### Core workflows — explicit invocation
+
 ```bash
 use kodelyth-advisor      # Not sure what to do? Start here
 use pair-programmer       # Think through approach before writing code
@@ -295,9 +242,19 @@ use ux-reviewer           # Review frontend UX and accessibility
 use migration-guide       # Upgrading a framework or language version
 use tdd-guide             # Write tests the right way
 use performance-optimizer # Diagnose and fix slowness
+use dependency-doctor     # npm/pip/cargo dep hell
+use git-rescue            # Broken git state, lost commits, bad rebase
+use release-captain       # Cut a clean release with rollback plan
+use env-debugger          # "Works on my machine" — env/config/secrets
+use flake-hunter          # Stabilize flaky tests
 ```
 
-### Load language patterns
+### Or just describe your problem
+
+The intent router will route you to the right one. The AI announces who's taking over, helps you, and tells you the explicit name for next time.
+
+### Load language patterns (skills)
+
 ```bash
 /typescript-patterns    # TypeScript + React + Next.js
 /python-patterns        # Python best practices
@@ -308,54 +265,55 @@ use performance-optimizer # Diagnose and fix slowness
 ```
 
 ### Advanced skills
+
 ```bash
 /git-mastery            # Trunk-based dev, rebase, bisect, monorepos
 /observability          # Structured logging, metrics, OpenTelemetry, SLOs
 /smart-debug            # Systematic debugging framework
+/intent-routing         # How the auto-routing system works
+/agent-handoff          # Standard multi-agent handoff chains
 ```
 
 ---
 
 ## What Gets Installed
 
-### Claude Code (`~/.claude/`)
+### Claude Code — `~/.claude/`
 
 | Source | Destination | What it does |
 |---|---|---|
-| `agents/` | `~/.claude/agents/` | All 53 subagents available globally |
-| `skills/` | `~/.claude/skills/` | All 185 skills loadable via commands |
-| `hooks/hooks.json` | `~/.claude/hooks/` | Automated quality gates and session memory |
-| `rules/` | `~/.claude/rules/` | Always-on coding standards |
+| `agents/` | `~/.claude/agents/` | All 58 subagents available globally |
+| `skills/` | `~/.claude/skills/` | All 187 skills loadable via commands |
+| `hooks/hooks.json` | `~/.claude/hooks/` | Automated quality gates |
+| `rules/` | `~/.claude/rules/` | Always-on standards + intent routing |
 | `commands/` | `~/.claude/commands/` | Slash commands (`/tdd`, `/plan`, etc.) |
-| `dashboard/` | `~/.kodelyth/lens/` | Kodelyth Lens usage dashboard |
 
-### Windsurf (project: `.windsurf/` · global: `~/.codeium/windsurf/`)
+### Windsurf — `.windsurf/` (project) or `~/.codeium/windsurf/` (global)
 
 | Source | Destination | Notes |
 |---|---|---|
 | `agents/` | `.windsurf/agents/` | Call with `use <agent-name>` in Cascade |
 | `skills/` | `.windsurf/skills/` | Domain knowledge, loadable via chat |
 | `rules/` | `.windsurf/rules/` | Flattened rule files |
-| `rules/common/` | `.windsurfrules` | Concatenated — Windsurf reads this automatically |
-
-The `.windsurfrules` file is auto-generated from all common rules and loaded by Windsurf Cascade on every session. No manual setup needed.
+| `rules/common/` | `.windsurfrules` | Concatenated — Windsurf reads this automatically every session |
 
-### Codex CLI (`~/.codex/`)
+### Cursor — `.cursor/` in project root
 
-| Source | Destination | What it does |
-|---|---|---|
-| `agents/` | `~/.codex/agents/` | All 53 agents available globally |
-| `skills/` | `~/.codex/skills/` | All 185 skills loadable in chat |
-| `commands/` | `~/.codex/commands/` | Slash commands |
-| `rules/` | `~/.codex/rules/` | Coding standards (flattened) |
+| Source | Destination |
+|---|---|
+| `rules/` | `.cursor/rules/` |
+| `skills/` | `.cursor/skills/` |
 
-### OpenCode (`.opencode/` in project root)
+### Codex CLI — `~/.codex/`
 
-| Source | Destination | What it does |
-|---|---|---|
-| `rules/` | `.opencode/rules/` | Coding standards (flattened) |
+| Source | Destination |
+|---|---|
+| `agents/` | `~/.codex/agents/` |
+| `skills/` | `~/.codex/skills/` |
+| `commands/` | `~/.codex/commands/` |
+| `rules/` | `~/.codex/rules/` |
 
-### Antigravity (`.agent/` in project root)
+### Antigravity — `.agent/` in project root
 
 | Source | Destination |
 |---|---|
@@ -363,6 +321,12 @@ The `.windsurfrules` file is auto-generated from all common rules and loaded by
 | `commands/` | `.agent/workflows/` |
 | `rules/` | `.agent/rules/` |
 
+### OpenCode — `.opencode/` in project root
+
+| Source | Destination |
+|---|---|
+| `rules/` | `.opencode/rules/` |
+
 ---
 
 ## Install Profiles — Language Bundles
@@ -370,15 +334,9 @@ The `.windsurfrules` file is auto-generated from all common rules and loaded by
 Works with any target:
 
 ```bash
-# Claude Code
-./install.sh --profile nextjs
-npx github:sifxprime/kodelyth-ecc --profile nextjs
-
-# Windsurf
-npx github:sifxprime/kodelyth-ecc --target windsurf-project --profile nextjs
-
-# Antigravity
-npx github:sifxprime/kodelyth-ecc --target antigravity --profile python-api
+npx kodelyth-ecc --profile nextjs                              # Claude Code
+npx kodelyth-ecc --target windsurf-project --profile nextjs    # Windsurf
+npx kodelyth-ecc --target antigravity --profile python-api     # Antigravity
 ```
 
 Available profiles:
@@ -391,9 +349,10 @@ Available profiles:
 | `mobile` | Kotlin + Swift rules |
 | `backend` | Go + Python + Java rules |
 
-Individual languages:
+Or specify languages directly:
+
 ```bash
-npx github:sifxprime/kodelyth-ecc typescript python golang rust java kotlin php swift cpp dart
+npx kodelyth-ecc typescript python golang rust java kotlin php swift cpp dart
 ```
 
 ---
@@ -404,21 +363,47 @@ npx github:sifxprime/kodelyth-ecc typescript python golang rust java kotlin php
 |---|---|---|---|
 | Claude Code | Full | `claude-home` (default) | Agents, skills, commands, hooks, rules |
 | Windsurf | Full | `windsurf-project` / `windsurf-home` | Agents, skills, rules, `.windsurfrules` |
-| Google Antigravity | Full | `antigravity` | Agents → skills, commands → workflows, rules |
 | Cursor | Full | `cursor-project` | Rules, skills |
 | Codex CLI | Full | `codex-home` | Agents, skills, commands, rules |
+| Google Antigravity | Full | `antigravity` | Agents → skills, commands → workflows, rules |
 | OpenCode | Full | `opencode` | Rules |
 
+**OS support:** macOS, Linux (`install.sh`), Windows (`install.ps1`), or any OS with Node.js 18+ (`npx`).
+
+---
+
+## Privacy & Philosophy
+
+ECC is **100% local files**. No telemetry, no cloud, no account, no tracking. Everything is markdown your AI reads on every session.
+
+- **No dashboard** — we removed it in v1.3.0 because it wasn't giving accurate cross-platform data and added confusion. The toolkit is now leaner.
+- **No phoning home** — install scripts copy files and exit. That's it.
+- **You own everything** — fork the repo, edit any agent, write your own.
+
 ---
 
 ## Contributing
 
-We welcome new agents, skills, and hooks that meet the **Kodelyth Standard** — specialist personas, model-agnostic, production-grade examples.
+We welcome new agents, skills, hooks, and intent routing patterns that meet the **Kodelyth Standard** — specialist personas, model-agnostic, production-grade examples.
+
+When adding a new agent, also update `rules/common/agent-intent-routing.md` with your trigger patterns so the intent router knows when to call you.
 
 See [CONTRIBUTING.md](CONTRIBUTING.md) for templates, checklists, and the full Kodelyth Standard.
 
 ---
 
+## Changelog
+
+See [CHANGELOG.md](CHANGELOG.md). v1.3.0 highlights:
+
+- **Removed:** Lens dashboard (was inaccurate across cloud-AI platforms)
+- **Added:** God-tier `agent-intent-routing` rule — 10 priority tiers, 50+ patterns
+- **Added:** 5 new agents — `dependency-doctor`, `git-rescue`, `release-captain`, `env-debugger`, `flake-hunter`
+- **Added:** 2 new skills — `intent-routing` (routing system docs), `agent-handoff` (chain protocol)
+- **Improved:** Cross-platform install parity — full Windows support for all targets
+
+---
+
 <div align="center">
 
 Built and maintained by **Kodelyth** — [@sifxprime](https://github.com/sifxprime)

package/VERSION

@@ -1 +1 @@
-1.2.2
+1.3.0