kodelyth-ecc 1.5.1 → 1.5.3

package/commands/project-launch.md

@@ -0,0 +1,74 @@
+---
+description: Parallel founding-team blast for new projects. Fires architect + security + UX + TDD + pair-programmer simultaneously. One command, 5 specialist reports at once.
+---
+
+# /project-launch — Parallel Founding Team
+
+Launch all founding-team agents in parallel on your new project. What would take 40+ minutes sequentially finishes in under 10 minutes as one parallel burst.
+
+## Usage
+
+```
+/project-launch <description>
+/project-launch "SaaS dashboard with Stripe billing, user auth, real-time data"
+/project-launch --full    # adds performance-optimizer and api-guardian to the team
+```
+
+## What Gets Launched in Parallel
+
+Five specialist agents fire simultaneously, each with the same project description:
+
+| Agent | Deliverable |
+|---|---|
+| `architect` | System design — components, data flow, boundaries, trade-offs |
+| `pair-programmer` | Approach validation — risks, wrong turns, questions to answer before coding |
+| `security-reviewer` | Threat model — auth, data exposure, OWASP risks for THIS project type |
+| `tdd-guide` | Test strategy — what to test first, test pyramid, critical paths |
+| `ux-reviewer` | UX blueprint — user flows, accessibility requirements, interaction risks |
+
+With `--full`, also adds:
+- `performance-optimizer` — scaling bottlenecks, caching strategy, query patterns
+- `api-guardian` — API contract design, versioning strategy, breaking change risks
+
+## How It Works
+
+1. Read the project description from `$ARGUMENTS`
+2. If no description provided, ask for one in one sentence
+3. Spawn all 5 (or 7) agents simultaneously with `run_in_background: true`
+4. Each agent receives: the project description + its specialist brief
+5. Wait for all to complete
+6. Aggregate results into a structured **Project Launch Report**:
+
+```
+## PROJECT LAUNCH REPORT
+### Architecture (architect)
+[findings]
+
+### Approach Risks (pair-programmer)
+[findings]
+
+### Threat Model (security-reviewer)
+[findings]
+
+### Test Strategy (tdd-guide)
+[findings]
+
+### UX Blueprint (ux-reviewer)
+[findings]
+```
+
+7. After report: ask "Which area do you want to go deeper on first?"
+
+## Token Efficiency
+
+Each agent gets a **narrow, focused context** — just the project description + its specialist instructions. No agent carries the full conversation history. The system prompt (rules + agents) is cached across all parallel agents. Result: 5× the analysis at roughly 2× the token cost of a single sequential session.
+
+## When to Use
+
+- Starting any non-trivial project (3+ components, real users, production intent)
+- Before writing a single line of code
+- When you want to catch architecture mistakes before they're baked in
+
+## Arguments
+
+$ARGUMENTS

package/commands/team-review.md

@@ -0,0 +1,90 @@
+---
+description: Parallel full-team audit for existing projects. Fires code-reviewer + security-reviewer + performance-optimizer + api-guardian simultaneously. One command, complete audit at once.
+---
+
+# /team-review — Parallel Full-Team Audit
+
+Run a full audit of your existing codebase with 4 specialist agents firing simultaneously. What would take an hour sequentially takes 15 minutes in parallel.
+
+## Usage
+
+```
+/team-review                    # full audit — all 4 agents on entire codebase
+/team-review src/auth/          # focus all agents on a specific directory
+/team-review --changed          # audit only files changed since last commit
+/team-review --pre-release      # adds release-captain for release readiness check
+```
+
+## What Gets Launched in Parallel
+
+| Agent | Focus |
+|---|---|
+| `code-reviewer` | Quality, patterns, dead code, naming, complexity, maintainability |
+| `security-reviewer` | OWASP Top 10, secrets, injection, auth gaps, CVEs in deps |
+| `performance-optimizer` | N+1 queries, unbounded loops, missing indexes, memory leaks, bundle size |
+| `api-guardian` | Breaking changes, missing validation, versioning gaps, contract drift |
+
+With `--pre-release`, also adds:
+- `release-captain` — release readiness: changelog, semver, rollback plan, smoke test coverage
+
+## How It Works
+
+1. Identify the target scope (whole repo, directory, or changed files)
+2. Spawn all 4 agents simultaneously with `run_in_background: true`
+3. Each agent scans its assigned concern independently
+4. Wait for all to complete
+5. Aggregate into a structured **Team Review Report**:
+
+```
+## TEAM REVIEW REPORT
+
+### Code Quality (code-reviewer)
+CRITICAL: [list]
+HIGH:     [list]
+MEDIUM:   [list]
+
+### Security (security-reviewer)
+CRITICAL: [list]
+HIGH:     [list]
+
+### Performance (performance-optimizer)
+HIGH:     [list]
+MEDIUM:   [list]
+
+### API Contracts (api-guardian)
+BREAKING: [list]
+WARN:     [list]
+
+---
+TOTAL: X critical, Y high, Z medium
+RECOMMENDATION: [ship / fix critical first / block]
+```
+
+6. After report: "Which finding do you want to fix first?"
+
+## Severity Levels
+
+| Level | Meaning | Action |
+|---|---|---|
+| CRITICAL | Security vulnerability, data loss, production breakage | Block — fix before merge |
+| HIGH | Bug, broken contract, significant perf regression | Fix before shipping |
+| MEDIUM | Maintainability debt, minor perf, code smell | Fix when convenient |
+| LOW | Style, suggestion | Optional |
+
+## When to Use
+
+- Before any major PR merge
+- Pre-release audit
+- Onboarding to an unfamiliar codebase (run `/team-review` to get the full picture fast)
+- After a large refactor
+- Monthly health check on long-running projects
+
+## Time and Token Efficiency
+
+Sequential audit (4 agents one by one): ~40–60 minutes, full context per agent.
+`/team-review` parallel: ~10–15 minutes, narrow focused context per agent.
+System prompt cached across all agents → each pays 10% on that prefix.
+
+## Arguments
+
+$ARGUMENTS

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "kodelyth-ecc",
-  "version": "1.5.1",
+  "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.",
   "author": "Kodelyth <github.com/sifxprime>",
   "license": "MIT",
@@ -24,7 +24,11 @@
     "auto-recall",
     "incident-response",
     "load-testing",
-    "kodelyth"
+    "kodelyth",
+    "image-generation",
+    "parallel-agents",
+    "multi-agent",
+    "project-launch"
   ],
   "bin": {
     "kodelyth-ecc": "bin/kodelyth-ecc.js"