kodelyth-ecc 2.23.1 → 2.23.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/CHANGELOG.md +40 -0
  2. package/README.md +42 -20
  3. package/VERSION +1 -1
  4. package/package.json +1 -1
package/CHANGELOG.md CHANGED
@@ -2,6 +2,46 @@
2
2
 
3
3
  All notable changes to Kodelyth ECC are documented here.
4
4
 
5
+ ## v2.23.2 — the README leads with the product, not the badges (October 2026)
6
+
7
+ No change to the toolkit. The README **is** the npm landing page, and npm only
8
+ re-renders it on publish, so this exists to make the rewrite actually reach
9
+ anyone.
10
+
11
+ ### What changed
12
+
13
+ It opened with a logo, a 900px hero and **21 shields — 35 lines before a single
14
+ word of what this is**. Someone arriving from npm search had to scroll past a
15
+ wall of badges to learn whether they cared.
16
+
17
+ The strongest thing in the file was buried too: the routing transcript, where
18
+
19
+ ```
20
+ You: "I've been staring at this NullPointerException for two hours,
21
+ I'm losing my mind."
22
+
23
+ AI: → Routing to debug-detective
24
+ ```
25
+
26
+ explains the product faster than any paragraph could, and sat at line 55.
27
+
28
+ The first screen is now: logo, one-line claim, that transcript, `npx
29
+ kodelyth-ecc`, and the platform list. Badges and hero follow below a rule.
30
+
31
+ **Nothing was cut.** All 1,100+ lines and every badge are intact — just no
32
+ longer first.
33
+
34
+ ### Corrected while reading
35
+
36
+ The comparison tables still claimed 194 skills, 97 slash commands and "22+"
37
+ quality hooks in three places. Actual: 196, 103, 44. Those tables make direct
38
+ claims against other kits, so wrong numbers there cost more than anywhere else.
39
+
40
+ Verified: 82 code fences balanced, 19 `div`s balanced, zero stale figures left,
41
+ and a line-by-line diff against the previous file confirming no content lost.
42
+
43
+ **647 tests passing.**
44
+
5
45
  ## v2.23.1 — the shop window said the wrong numbers (October 2026)
6
46
 
7
47
  No change to the toolkit. This exists because npm metadata only refreshes when
package/README.md CHANGED
@@ -5,7 +5,38 @@
5
5
  <img src="brand/ecc-lockup-light.svg" alt="Kodelyth ECC — Elite Code Crew" width="440"/>
6
6
  </picture>
7
7
 
8
- <br><br>
8
+
9
+ </div>
10
+
11
+ ### Describe your problem in plain words. The right specialist shows up.
12
+
13
+ No agent names to memorise. No prompt engineering. Nothing leaves your machine.
14
+
15
+ ```
16
+ You: "I've been staring at this NullPointerException for two hours,
17
+ I'm losing my mind."
18
+
19
+ AI: → Routing to debug-detective (your error + frustration matches the bug-tracking signal)
20
+
21
+ That kind of bug is exhausting — let's trace it properly so we
22
+ fix the root cause, not the symptom.
23
+
24
+ First, can you share the full stack trace and...
25
+ ```
26
+
27
+ You never typed `use debug-detective`. You did not have to — ECC read the intent,
28
+ picked the specialist out of 70, and told you which one it chose and why.
29
+
30
+ ```bash
31
+ npx kodelyth-ecc
32
+ ```
33
+
34
+ Works on **macOS, Linux and Windows** with Claude Code, Windsurf, Cursor, Codex CLI,
35
+ Google Antigravity, OpenCode, Cline, Roo Code, Aider, Kimi and Gemini CLI.
36
+
37
+ ---
38
+
39
+ <div align="center">
9
40
 
10
41
  <img src="social/readme-hero.svg" alt="Kodelyth ECC — AI Agent Toolkit" width="900"/>
11
42
 
@@ -31,6 +62,7 @@
31
62
  ![Codebase Graph](https://img.shields.io/badge/Codebase%20Graph-158%20languages-green)
32
63
  ![Interactive CLI](https://img.shields.io/badge/CLI-interactive%20menu-blue)
33
64
 
65
+
34
66
  </div>
35
67
 
36
68
  **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
48
80
 
49
81
  ---
50
82
 
51
- ## Why ECC ≠ Another Agent Collection
52
-
53
- 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.
54
-
55
- ```
56
- You: "I've been staring at this NullPointerException for two hours,
57
- I'm losing my mind."
58
-
59
- AI: → Routing to debug-detective (your error + frustration matches the bug-tracking signal)
83
+ 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.
60
84
 
61
- That kind of bug is exhausting — let's trace it properly so we
62
- fix the root cause, not the symptom.
85
+ ---
63
86
 
64
- First, can you share the full stack trace and...
65
- ```
87
+ ## Why ECC ≠ Another Agent Collection
66
88
 
67
- 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.
89
+ 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.
68
90
 
69
91
  ### The Layer Stack
70
92
 
@@ -76,7 +98,7 @@ You never typed `use debug-detective`. You didn't have to. The toolkit read the
76
98
  | **103 commands** | Slash workflows (`/tdd`, `/arena`, `/devil-mode`, `/team-review`) | Limited or none |
77
99
  | **8 parallel commands** | Fire 3-8 agents simultaneously, aggregate results | Rare |
78
100
  | **Compound memory** | BM25 local recall + auto-inject + project lessons | Cloud-only or absent |
79
- | **22+ hooks** | Quality gates, secret scan, project-DNA detection | Often missing |
101
+ | **44 hook entries** | Quality gates, secret scan, project-DNA detection | Often missing |
80
102
  | **11 IDE platforms** | Claude Code, Windsurf, Cursor, Codex, Antigravity, OpenCode, Cline, Roo Code, Aider, Kimi, Gemini CLI (13 install targets) | 1-2 platforms typical |
81
103
  | **Zero telemetry** | Everything stays on your disk; verifiable | Many kits phone home |
82
104
 
@@ -85,15 +107,15 @@ You never typed `use debug-detective`. You didn't have to. The toolkit read the
85
107
  | Feature | **Kodelyth ECC** | `agency-agents` | `awesome-claude-agents` | Generic prompt libs |
86
108
  |---|---|---|---|---|
87
109
  | Specialist agents | **70** | ~30 | ~20 | Varies |
88
- | Skills as separate layer | ✅ 194 | ❌ | ❌ | ❌ |
89
- | Slash commands | ✅ 97 | Some | Some | ❌ |
110
+ | Skills as separate layer | ✅ 196 | ❌ | ❌ | ❌ |
111
+ | Slash commands | ✅ 103 | Some | Some | ❌ |
90
112
  | **Parallel multi-agent commands** | ✅ 8 (incl. `/devil-mode`) | ❌ | ❌ | ❌ |
91
113
  | **Intent routing (plain language → agent)** | ✅ 10-tier rule | ❌ | ❌ | ❌ |
92
114
  | **Local BM25 self-learning memory** | ✅ | ❌ | ❌ | ❌ |
93
115
  | **Compound learning from corrections** | ✅ `tasks/lessons.md` | ❌ | ❌ | ❌ |
94
116
  | **Adversarial / red-team agents** | ✅ 8 (devil-mode) | ❌ | ❌ | ❌ |
95
117
  | **Adversarial build/attack loop** | ✅ `/arena` — scored, verified, converges | ❌ | ❌ | ❌ |
96
- | Quality hooks | ✅ 22+ | Some | ❌ | ❌ |
118
+ | Quality hooks | ✅ 44 | Some | ❌ | ❌ |
97
119
  | IDE platforms | **11** (Claude Code, Windsurf, Cursor, Codex, Antigravity, OpenCode, Cline, Roo Code, Aider, Kimi, Gemini CLI) | 1-2 | 1 | Varies |
98
120
  | Telemetry | ❌ none | Varies | ❌ | Varies |
99
121
  | Test coverage | ✅ 647 tests | ❌ | ❌ | ❌ |
@@ -262,7 +284,7 @@ npx kodelyth-ecc --bundle red-team # Security engineer — devil-mode + a
262
284
  npx kodelyth-ecc --bundle enterprise # Compliance / audit team — SBOM, license, supply chain
263
285
  ```
264
286
 
265
- 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.
287
+ 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.
266
288
 
267
289
  Combine with any target:
268
290
 
package/VERSION CHANGED
@@ -1 +1 @@
1
- 2.23.1
1
+ 2.23.2
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "kodelyth-ecc",
3
- "version": "2.23.1",
3
+ "version": "2.23.2",
4
4
  "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.",
5
5
  "author": "Kodelyth <github.com/sifxprime>",
6
6
  "license": "MIT",