kodelyth-ecc 2.23.0 → 2.23.2

package/CHANGELOG.md

@@ -2,6 +2,91 @@
 
 All notable changes to Kodelyth ECC are documented here.
 
+## v2.23.2 — the README leads with the product, not the badges (October 2026)
+
+No change to the toolkit. The README **is** the npm landing page, and npm only
+re-renders it on publish, so this exists to make the rewrite actually reach
+anyone.
+
+### What changed
+
+It opened with a logo, a 900px hero and **21 shields — 35 lines before a single
+word of what this is**. Someone arriving from npm search had to scroll past a
+wall of badges to learn whether they cared.
+
+The strongest thing in the file was buried too: the routing transcript, where
+
+```
+You:   "I've been staring at this NullPointerException for two hours,
+        I'm losing my mind."
+
+AI:    → Routing to debug-detective
+```
+
+explains the product faster than any paragraph could, and sat at line 55.
+
+The first screen is now: logo, one-line claim, that transcript, `npx
+kodelyth-ecc`, and the platform list. Badges and hero follow below a rule.
+
+**Nothing was cut.** All 1,100+ lines and every badge are intact — just no
+longer first.
+
+### Corrected while reading
+
+The comparison tables still claimed 194 skills, 97 slash commands and "22+"
+quality hooks in three places. Actual: 196, 103, 44. Those tables make direct
+claims against other kits, so wrong numbers there cost more than anywhere else.
+
+Verified: 82 code fences balanced, 19 `div`s balanced, zero stale figures left,
+and a line-by-line diff against the previous file confirming no content lost.
+
+**647 tests passing.**
+
+## v2.23.1 — the shop window said the wrong numbers (October 2026)
+
+No change to the toolkit. This exists because npm metadata only refreshes when
+you publish, and three public-facing surfaces had gone stale.
+
+Measured before changing anything: **9,233 npm downloads in the last 30 days
+against 11 GitHub stars** — roughly 840:1, where a healthy project runs 50:1 to
+200:1. Discovery is not the constraint; thousands install this and nothing
+converts them.
+
+### Corrected
+
+| Surface | Said | Actual |
+|---|---|---|
+| `package.json` description | 194 skills, 97 commands | 196, 103 |
+| GitHub repo description | 102 commands, 22+ hooks | 103, **44** |
+| README badges | **373 tests**, Skills-194 | **647 tests**, 196 |
+
+Wrong numbers in the first thing anyone sees read as abandoned. Both
+descriptions now also name Windows, which became a real differentiator in 2.23.0
+and went unmentioned.
+
+### Asked, once
+
+The end of a successful install is the highest-intent moment there is, and an
+all-green `doctor` is the other. Both were silent. Both now print a single line.
+
+It is gated hard, because an ask that repeats is an annoyance:
+
+- shown **once per machine**, via a marker beside the other ECC state
+- never after a failed install
+- never when `doctor` reports a warning or a failure
+- wrapped so it can never break an install
+
+Someone wiring up four IDEs is asked once, not four times.
+
+### Keywords
+
+Strong on the long tail (`devil-mode`, `bm25`, `intent-routing`), missing the
+broad terms people actually type. Added `claude`, `agent`, `agents`, `ai`,
+`subagents`, `prompt-engineering`, `ai-assistant`, `code-review`, `windows`.
+41 to 50.
+
+**647 tests passing.**
+
 ## v2.23.0 — Windows has no manual step left (October 2026)
 
 2.22.0 made the Windows install work but left two components needing a manual

package/README.md

@@ -5,7 +5,38 @@
   <img src="brand/ecc-lockup-light.svg" alt="Kodelyth ECC — Elite Code Crew" width="440"/>
 </picture>
 
-<br><br>
+
+</div>
+
+### Describe your problem in plain words. The right specialist shows up.
+
+No agent names to memorise. No prompt engineering. Nothing leaves your machine.
+
+```
+You:   "I've been staring at this NullPointerException for two hours,
+        I'm losing my mind."
+
+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...
+```
+
+You never typed `use debug-detective`. You did not have to — ECC read the intent,
+picked the specialist out of 70, and told you which one it chose and why.
+
+```bash
+npx kodelyth-ecc
+```
+
+Works on **macOS, Linux and Windows** with Claude Code, Windsurf, Cursor, Codex CLI,
+Google Antigravity, OpenCode, Cline, Roo Code, Aider, Kimi and Gemini CLI.
+
+---
+
+<div align="center">
 
 <img src="social/readme-hero.svg" alt="Kodelyth ECC — AI Agent Toolkit" width="900"/>
 
@@ -13,7 +44,7 @@
 [![npm downloads](https://img.shields.io/npm/dm/kodelyth-ecc.svg)](https://www.npmjs.com/package/kodelyth-ecc)
 [![GitHub Stars](https://img.shields.io/github/stars/sifxprime/kodelyth-ecc?style=social)](https://github.com/sifxprime/kodelyth-ecc/stargazers)
 [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
-![Tests](https://img.shields.io/badge/tests-373%20passing-brightgreen)
+![Tests](https://img.shields.io/badge/tests-647%20passing-brightgreen)
 ![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)
@@ -21,7 +52,7 @@
 ![Codex](https://img.shields.io/badge/Codex-Ready-10b981)
 ![Agents](https://img.shields.io/badge/Agents-70-brightgreen)
 ![Devil Mode](https://img.shields.io/badge/Devil%20Mode-new-red)
-![Skills](https://img.shields.io/badge/Skills-194-brightgreen)
+![Skills](https://img.shields.io/badge/Skills-196-brightgreen)
 ![Memory](https://img.shields.io/badge/Local%20Memory-on-blueviolet)
 ![Auto Recall](https://img.shields.io/badge/Auto%20Chat%20Recall-on-blueviolet)
 ![Parallel Agents](https://img.shields.io/badge/Parallel%20Agents-new-red)
@@ -31,6 +62,7 @@
 ![Codebase Graph](https://img.shields.io/badge/Codebase%20Graph-158%20languages-green)
 ![Interactive CLI](https://img.shields.io/badge/CLI-interactive%20menu-blue)
 
+
 </div>
 
 **Kodelyth ECC** is a production-grade AI coding toolkit — **70 specialist agents (incl. an 8-agent devil-mode adversarial crew), 196 skills, 103 commands**, a god-tier **semantic intent-routing system**, local self-learning memory, MCP server, swarm orchestrator, and an observability dashboard — all local, zero telemetry.
@@ -48,23 +80,13 @@ Works with **Claude Code**, **Windsurf**, **Cursor**, **Codex CLI**, **Google An
 
 ---
 
-## Why ECC ≠ Another Agent Collection
-
-Most "AI agent kits" are folders of markdown files you have to remember the names of. **ECC is infrastructure** — a layered system where intent routing, compound memory, parallel orchestration, and quality hooks all reinforce each other.
-
-```
-You:   "I've been staring at this NullPointerException for two hours,
-        I'm losing my mind."
-
-AI:    → Routing to debug-detective (your error + frustration matches the bug-tracking signal)
+You never typed `use debug-detective`. You didn't have to. The toolkit read the intent, picked the specialist, and announced the routing. Next time you can invoke it directly — but you don't have to remember names to get senior-grade help.
 
-       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...
-```
+## Why ECC ≠ Another Agent Collection
 
-You never typed `use debug-detective`. You didn't have to. The toolkit read the intent, picked the specialist, and announced the routing. Next time you can invoke it directly — but you don't have to remember names to get senior-grade help.
+Most "AI agent kits" are folders of markdown files you have to remember the names of. **ECC is infrastructure** — a layered system where intent routing, compound memory, parallel orchestration, and quality hooks all reinforce each other.
 
 ### The Layer Stack
 
@@ -76,7 +98,7 @@ You never typed `use debug-detective`. You didn't have to. The toolkit read the
 | **103 commands** | Slash workflows (`/tdd`, `/arena`, `/devil-mode`, `/team-review`) | Limited or none |
 | **8 parallel commands** | Fire 3-8 agents simultaneously, aggregate results | Rare |
 | **Compound memory** | BM25 local recall + auto-inject + project lessons | Cloud-only or absent |
-| **22+ hooks** | Quality gates, secret scan, project-DNA detection | Often missing |
+| **44 hook entries** | Quality gates, secret scan, project-DNA detection | Often missing |
 | **11 IDE platforms** | Claude Code, Windsurf, Cursor, Codex, Antigravity, OpenCode, Cline, Roo Code, Aider, Kimi, Gemini CLI (13 install targets) | 1-2 platforms typical |
 | **Zero telemetry** | Everything stays on your disk; verifiable | Many kits phone home |
 
@@ -85,15 +107,15 @@ You never typed `use debug-detective`. You didn't have to. The toolkit read the
 | Feature | **Kodelyth ECC** | `agency-agents` | `awesome-claude-agents` | Generic prompt libs |
 |---|---|---|---|---|
 | Specialist agents | **70** | ~30 | ~20 | Varies |
-| Skills as separate layer | ✅ 194 | ❌ | ❌ | ❌ |
-| Slash commands | ✅ 97 | Some | Some | ❌ |
+| Skills as separate layer | ✅ 196 | ❌ | ❌ | ❌ |
+| Slash commands | ✅ 103 | Some | Some | ❌ |
 | **Parallel multi-agent commands** | ✅ 8 (incl. `/devil-mode`) | ❌ | ❌ | ❌ |
 | **Intent routing (plain language → agent)** | ✅ 10-tier rule | ❌ | ❌ | ❌ |
 | **Local BM25 self-learning memory** | ✅ | ❌ | ❌ | ❌ |
 | **Compound learning from corrections** | ✅ `tasks/lessons.md` | ❌ | ❌ | ❌ |
 | **Adversarial / red-team agents** | ✅ 8 (devil-mode) | ❌ | ❌ | ❌ |
 | **Adversarial build/attack loop** | ✅ `/arena` — scored, verified, converges | ❌ | ❌ | ❌ |
-| Quality hooks | ✅ 22+ | Some | ❌ | ❌ |
+| Quality hooks | ✅ 44 | Some | ❌ | ❌ |
 | IDE platforms | **11** (Claude Code, Windsurf, Cursor, Codex, Antigravity, OpenCode, Cline, Roo Code, Aider, Kimi, Gemini CLI) | 1-2 | 1 | Varies |
 | Telemetry | ❌ none | Varies | ❌ | Varies |
 | Test coverage | ✅ 647 tests | ❌ | ❌ | ❌ |
@@ -262,7 +284,7 @@ npx kodelyth-ecc --bundle red-team        # Security engineer — devil-mode + a
 npx kodelyth-ecc --bundle enterprise      # Compliance / audit team — SBOM, license, supply chain
 ```
 
-Each bundle installs the full ECC toolkit (all 70 agents, 196 skills, 103 commands, 22+ hooks), adds a `BUNDLE.md` cheat sheet, and biases the AI toward audience-fit workflows on every session.
+Each bundle installs the full ECC toolkit (all 70 agents, 196 skills, 103 commands, 44 hook entries), adds a `BUNDLE.md` cheat sheet, and biases the AI toward audience-fit workflows on every session.
 
 Combine with any target:
 

package/VERSION

@@ -1 +1 @@
-2.23.0
+2.23.2

package/bin/kodelyth-ecc.js

@@ -724,7 +724,13 @@ if (args[0] === 'doctor') {
   w('─'.repeat(60));
   const s = report.summary;
   w(`${s.pass} pass · ${s.warn} warn · ${s.fail} fail  (of ${s.total} checks)`);
-  if (s.fail === 0 && s.warn === 0) w('\x1b[32mEverything is wired and working.\x1b[0m');
+  if (s.fail === 0 && s.warn === 0) {
+    w('\x1b[32mEverything is wired and working.\x1b[0m');
+    // An all-green doctor is the other honest moment to ask. Shares the install
+    // marker, so nobody is asked twice on the same machine, and it stays silent
+    // when anything is warning or failing — that is not the time.
+    maybeAskForAStar(0);
+  }
   else if (s.fail === 0) w('\x1b[33mWorking, with optional features not yet enabled (warnings above).\x1b[0m');
   else w('\x1b[31mSome subsystems are broken — see fixes above.\x1b[0m');
   w('');
@@ -1817,6 +1823,33 @@ if (args.includes('--version') || args.includes('-v')) {
 // Every block below already guards itself and reports a reason when it cannot
 // proceed, which is what makes sharing it safe: on Windows the parts that work
 // now run, and the parts that cannot say so instead of vanishing.
+/**
+ * One quiet line at the end of a successful install.
+ *
+ * This is the highest-intent moment there is — someone has just watched the
+ * whole thing land and work — and it was going unused. It is deliberately shown
+ * ONCE per machine, not on every target install: somebody wiring up four IDEs
+ * should not be asked four times. The marker lives beside the other ECC state.
+ *
+ * Never shown on a failed install, and never blocks or prompts.
+ */
+function maybeAskForAStar(status) {
+  if (status !== 0) return;
+  try {
+    const dir = path.join(os.homedir(), '.kodelythecc');
+    const marker = path.join(dir, 'star-asked');
+    if (fs.existsSync(marker)) return;
+    fs.mkdirSync(dir, { recursive: true });
+    fs.writeFileSync(marker, new Date().toISOString() + '\n');
+
+    process.stdout.write('\n');
+    process.stdout.write('  If ECC saved you time today, a star helps others find it:\n');
+    process.stdout.write('  https://github.com/sifxprime/kodelyth-ecc\n\n');
+  } catch {
+    // A star request is never worth failing an install over.
+  }
+}
+
 function runPostInstall(status, args) {
   // Post-install: auto-register ECC's own MCP server in Claude Code + Desktop.
   if (status === 0 && !args.includes('--no-mcp-register')) {
@@ -1983,6 +2016,7 @@ if (isWin) {
     process.exit(1);
   }
   runPostInstall(result.status, args);
+  maybeAskForAStar(result.status);
   process.exit(result.status ?? 1);
 } else {
   try { require(path.join(ROOT, 'scripts', 'migrate-legacy.js')).main(); } catch {}
@@ -1995,5 +2029,6 @@ if (isWin) {
   const result = spawnSync('bash', [sh, ...args], { stdio: 'inherit', shell: false });
 
   runPostInstall(result.status, args);
+  maybeAskForAStar(result.status);
   process.exit(result.status ?? 1);
 }

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "kodelyth-ecc",
-  "version": "2.23.0",
-  "description": "Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) that bridges to Claude Desktop, LangGraph, AutoGen, CrewAI, and OpenAI Agents SDK. Works with Claude Code, Windsurf, Cursor, Codex, Antigravity, OpenCode, Cline, RooCode, Aider, Kimi, and Gemini CLI.",
+  "version": "2.23.2",
+  "description": "Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 196 skills, 103 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) that bridges to Claude Desktop, LangGraph, AutoGen, CrewAI, and OpenAI Agents SDK. Works on macOS, Linux and Windows with Claude Code, Windsurf, Cursor, Codex, Antigravity, OpenCode, Cline, RooCode, Aider, Kimi, and Gemini CLI.",
   "author": "Kodelyth <github.com/sifxprime>",
   "license": "MIT",
   "repository": {
@@ -54,7 +54,16 @@
     "local-memory",
     "hooks",
     "slash-commands",
-    "productivity"
+    "productivity",
+    "claude",
+    "agent",
+    "agents",
+    "ai",
+    "subagents",
+    "prompt-engineering",
+    "ai-assistant",
+    "code-review",
+    "windows"
   ],
   "bin": {
     "kodelyth-ecc": "bin/kodelyth-ecc.js",