kodelyth-ecc 1.5.3 → 1.5.4

package/CLAUDE.md

@@ -6,11 +6,11 @@ Guidance for Claude Code when working with this repository.
 
 **Kodelyth ECC** — a production-grade AI coding toolkit:
 
-- **61 specialist agents** — debug-detective, incident-commander, load-tester, kodelyth-memory, security-reviewer, etc.
+- **62 specialist agents** — debug-detective, incident-commander, load-tester, image-architect, kodelyth-memory, security-reviewer, etc.
 - **188 skills** — domain knowledge, patterns, testing, security, intent routing, local memory
-- **80 commands** — slash workflows (`/tdd`, `/plan`, `/code-review`, `/memory`, ...)
-- **18+ hooks** — automated quality gates, session memory, memory inject + capture
-- **16 rules** — always-on coding standards + intent routing + memory protocol
+- **80 commands** — slash workflows (`/tdd`, `/plan`, `/code-review`, `/memory`, `/project-launch`, `/team-review`, ...)
+- **20+ hooks** — automated quality gates, session memory, memory inject + capture, correction encoding
+- **17 rules** — always-on coding standards + semantic intent routing + memory protocol
 
 Works with Claude Code, Windsurf, Cursor, Codex CLI, Antigravity, and OpenCode.
 

package/VERSION

@@ -1 +1 @@
-1.5.3
+1.5.4

package/commands/project-launch.md

@@ -72,3 +72,20 @@ Each agent gets a **narrow, focused context** — just the project description +
 ## Arguments
 
 $ARGUMENTS
+
+---
+
+## Execute Now
+
+Invoking this command is confirmation to proceed. Do not show this documentation to the user — execute immediately:
+
+1. Read `$ARGUMENTS` for the project description. If empty, ask: "What are you building? Describe it in 2–3 sentences."
+2. Once you have a project description, spawn all agents simultaneously using `run_in_background: true`:
+   - `architect` — system design, tech selection, component breakdown
+   - `pair-programmer` — implementation approach, patterns, gotchas
+   - `security-reviewer` — threats, auth design, data exposure risks
+   - `tdd-guide` — test strategy, coverage plan, critical paths to test
+   - `ux-reviewer` — UX flows, accessibility, interaction design
+3. Wait for all agents to complete.
+4. Aggregate into the Project Launch Report format above.
+5. End with: "Which area do you want to go deeper on first?"

package/commands/team-review.md

@@ -88,3 +88,20 @@ System prompt cached across all agents → each pays 10% on that prefix.
 ## Arguments
 
 $ARGUMENTS
+
+---
+
+## Execute Now
+
+Invoking this command is confirmation to proceed. Do not show this documentation to the user — execute immediately:
+
+1. Identify the target scope from `$ARGUMENTS` (directory, `--changed`, `--pre-release`). Default: entire current project.
+2. Spawn all agents simultaneously using `run_in_background: true`:
+   - `code-reviewer` — quality, patterns, complexity, naming
+   - `security-reviewer` — OWASP Top 10, secrets, auth gaps
+   - `performance-optimizer` — N+1, memory, bundle size, slow queries
+   - `api-guardian` — breaking changes, contract drift, missing validation
+   - If `--pre-release` in args: also spawn `release-captain`
+3. Wait for all agents to complete.
+4. Aggregate results into the Team Review Report format above.
+5. End with: "Which finding do you want to fix first?"

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "kodelyth-ecc",
-  "version": "1.5.3",
-  "description": "Production-grade AI coding toolkit \u2014 61 agents, 188 skills, 80 commands, god-tier intent routing, local self-learning memory with auto chat detection, incident response, load testing. Works with Claude Code, Windsurf, Cursor, Codex, Antigravity, and OpenCode.",
+  "version": "1.5.4",
+  "description": "Production-grade AI coding toolkit — 61 agents, 188 skills, 80 commands, god-tier intent routing, local self-learning memory with auto chat detection, incident response, load testing. Works with Claude Code, Windsurf, Cursor, Codex, Antigravity, and OpenCode.",
   "author": "Kodelyth <github.com/sifxprime>",
   "license": "MIT",
   "repository": {