kodelyth-ecc 1.5.4 → 1.5.6

package/commands/refactor-sprint.md

@@ -0,0 +1,77 @@
+---
+description: Parallel refactor sprint — fires refactor-cleaner + code-simplifier + type-design-analyzer + tdd-guide simultaneously. Full cleanup in one pass.
+---
+
+# /refactor-sprint — Parallel Refactor Sprint
+
+Four agents clean, simplify, type-harden, and test-cover your code simultaneously. What would take a full day of careful manual work is scoped and planned in 15 minutes.
+
+## What Gets Launched in Parallel
+
+| Agent | Focus |
+|---|---|
+| `refactor-cleaner` | Dead code, unused imports, duplicate logic, copy-paste debt, tech debt |
+| `code-simplifier` | Complex functions, deep nesting, clever one-liners, readability improvements |
+| `type-design-analyzer` | `any` types, weak discriminated unions, missing type guards, type safety gaps |
+| `tdd-guide` | Test coverage gaps, missing unit tests, untested edge cases, coverage below 80% |
+
+## Usage
+
+```
+/refactor-sprint                     # full repo
+/refactor-sprint src/auth/           # focus on a module
+/refactor-sprint --types-only        # skip cleanup, focus on type safety
+/refactor-sprint --tests-only        # skip cleanup, focus on test coverage
+```
+
+## Report Format
+
+```
+## REFACTOR SPRINT REPORT
+
+### Dead Code & Debt (refactor-cleaner)
+REMOVE:    [files, functions, imports to delete]
+EXTRACT:   [duplicated logic to consolidate]
+DEBT:      [tech debt items ranked by impact]
+
+### Simplification (code-simplifier)
+COMPLEX:   [functions that need splitting]
+NESTING:   [deep nesting to flatten with early returns]
+READABILITY: [naming and clarity improvements]
+
+### Type Safety (type-design-analyzer)
+ANY_USAGE: [locations using any/unknown unsafely]
+WEAK_TYPES:[discriminated unions to strengthen]
+GUARDS:    [missing type guards]
+
+### Test Coverage (tdd-guide)
+UNCOVERED: [critical paths with no tests]
+GAPS:      [edge cases missing]
+PLAN:      [test writing priority order]
+
+---
+TOTAL DEBT: X items | QUICK WINS: Y items
+RECOMMENDED ORDER: [prioritized action list]
+```
+
+## When to Use
+
+- Before a major feature addition (clean house first)
+- After a fast-moving sprint that accumulated debt
+- Monthly code health pass
+- Before onboarding a new team member
+- When coverage has dropped below 80%
+
+## Execute Now
+
+Invoking this command is confirmation to proceed. Execute immediately:
+
+1. Determine scope from `$ARGUMENTS`. Default: entire current project.
+2. Spawn all agents simultaneously with `run_in_background: true`:
+   - `refactor-cleaner` — dead code and duplicate logic audit
+   - `code-simplifier` — complexity and readability analysis
+   - `type-design-analyzer` — type safety audit
+   - `tdd-guide` — test coverage gap analysis
+3. Wait for all to complete.
+4. Aggregate into the Refactor Sprint Report above with a prioritized action list.
+5. End with: "Which area do you want to tackle first?"

package/commands/security-audit.md

@@ -0,0 +1,66 @@
+---
+description: Parallel security audit — fires security-reviewer + dependency-doctor + api-guardian simultaneously. Full threat surface in one command.
+---
+
+# /security-audit — Parallel Security Audit
+
+Three security-focused agents fire simultaneously. What would take an hour one-by-one finishes in 15 minutes.
+
+## What Gets Launched in Parallel
+
+| Agent | Focus |
+|---|---|
+| `security-reviewer` | OWASP Top 10, secrets in code, injection, XSS, CSRF, auth gaps, crypto misuse |
+| `dependency-doctor` | CVEs in deps, outdated packages, transitive vulnerabilities, license issues |
+| `api-guardian` | Exposed endpoints, missing auth, broken contracts, data leakage in responses |
+
+## Usage
+
+```
+/security-audit                  # full repo
+/security-audit src/auth/        # focus on auth module
+/security-audit --pre-deploy     # adds environment + secrets check
+```
+
+## Report Format
+
+```
+## SECURITY AUDIT REPORT
+
+### Vulnerabilities (security-reviewer)
+CRITICAL: [list]
+HIGH:     [list]
+MEDIUM:   [list]
+
+### Dependencies (dependency-doctor)
+CVE:      [list with severity]
+OUTDATED: [list]
+
+### API Surface (api-guardian)
+EXPOSED:  [list]
+WARN:     [list]
+
+---
+TOTAL: X critical, Y high, Z medium
+ACTION: [ship / patch first / block]
+```
+
+## When to Use
+
+- Before any production deploy
+- After adding new auth or payment flows
+- When a dep audit flags CVEs
+- Quarterly security health check
+
+## Execute Now
+
+Invoking this command is confirmation to proceed. Execute immediately:
+
+1. Determine scope from `$ARGUMENTS`. Default: entire current project.
+2. Spawn all agents simultaneously with `run_in_background: true`:
+   - `security-reviewer` — full OWASP scan of codebase
+   - `dependency-doctor` — CVE audit of all package manifests
+   - `api-guardian` — API surface exposure check
+3. Wait for all to complete.
+4. Aggregate into the Security Audit Report format above.
+5. End with: "Which vulnerability do you want to fix first?"

package/commands/update.md

@@ -0,0 +1,92 @@
+---
+description: Upgrade Kodelyth ECC to the latest version, preserving your current install target and language profile
+---
+
+# /update
+
+Upgrades your ECC install to the latest version from npm. Reads your existing install state to replay the same target and language options automatically — no flags to remember.
+
+## Usage
+
+```
+/update
+```
+
+## What It Does
+
+1. Reads `kodelyth-ecc-install-state.json` from your install directory to recover the original `target` and `languages`
+2. Runs `npx kodelyth-ecc@latest` with those same flags
+3. Overwrites agents, skills, rules, and commands with the latest versions
+4. Leaves your memory store (`~/.kodelyth/memory/`) and `tasks/lessons.md` untouched — your learned context is never overwritten
+
+## Implementation
+
+The agent should run the appropriate command based on your platform.
+
+### Automatic (reads install state)
+
+```bash
+node -e "
+const fs = require('fs');
+const os = require('os');
+const path = require('path');
+
+const candidates = [
+  path.join(os.homedir(), '.claude', 'kodelyth-ecc-install-state.json'),
+  path.join(os.homedir(), '.codeium', 'windsurf', 'kodelyth-ecc-install-state.json'),
+  path.join(os.homedir(), '.codex', 'kodelyth-ecc-install-state.json'),
+  path.join(process.cwd(), '.windsurf', 'kodelyth-ecc-install-state.json'),
+  path.join(process.cwd(), '.cursor', 'kodelyth-ecc-install-state.json'),
+  path.join(process.cwd(), '.agent', 'kodelyth-ecc-install-state.json'),
+  path.join(process.cwd(), '.opencode', 'kodelyth-ecc-install-state.json'),
+];
+
+let state = null;
+let stateFile = null;
+for (const f of candidates) {
+  if (fs.existsSync(f)) { state = JSON.parse(fs.readFileSync(f, 'utf8')); stateFile = f; break; }
+}
+
+if (!state) {
+  console.error('No install state found. Run the installer manually:');
+  console.error('  npx kodelyth-ecc --target <target>');
+  process.exit(1);
+}
+
+const langs = (state.languages || []).join(' ');
+const cmd = ['npx', 'kodelyth-ecc@latest', '--target', state.target, langs].filter(Boolean).join(' ');
+console.log('Found install state:', stateFile);
+console.log('Previous version:', state.version);
+console.log('Running:', cmd);
+require('child_process').execSync(cmd, { stdio: 'inherit' });
+"
+```
+
+### Manual (if you know your target)
+
+```bash
+npx kodelyth-ecc@latest                              # Claude Code
+npx kodelyth-ecc@latest --target windsurf-home       # Windsurf global
+npx kodelyth-ecc@latest --target windsurf-project    # Windsurf project
+npx kodelyth-ecc@latest --target codex-home          # Codex CLI
+npx kodelyth-ecc@latest --target cursor-project      # Cursor
+```
+
+## What Is NOT Overwritten
+
+| Path | Protected |
+|------|-----------|
+| `~/.kodelyth/memory/` | Your BM25 memory store |
+| `tasks/lessons.md` | Project correction rules |
+| `tasks/todo.md` | Open todos |
+
+## After Updating
+
+Run `/doctor` to confirm the new version is healthy.
+
+## Related
+
+- `/doctor` — verify install health
+- `use kodelyth-advisor` — guidance after a major version update
+
+> Powered by Kodelyth — stay current, stay sharp.

package/install.ps1

@@ -21,7 +21,7 @@ $ErrorActionPreference = "Stop"
 # ── Banner ────────────────────────────────────────────────────────────────────
 Write-Host ""
 Write-Host "  Kodelyth ECC — Production-grade AI coding agent toolkit" -ForegroundColor Cyan
-Write-Host "  59 agents · 188 skills · 80 commands · 18+ hooks · intent routing · local memory" -ForegroundColor Gray
+Write-Host "  62 agents · 188 skills · 90 commands · 20+ hooks · intent routing · local memory" -ForegroundColor Gray
 Write-Host ""
 
 $ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
@@ -107,6 +107,11 @@ if ($Confirm -and $Confirm -notmatch '^[Yy]$') {
 }
 Write-Host ""
 
+# ── Dynamic Counts ───────────────────────────────────────────────────────────
+$AgentCount   = (Get-ChildItem -Path "$ScriptDir\agents"   -Filter "*.md" -File).Count
+$SkillCount   = (Get-ChildItem -Path "$ScriptDir\skills"   -Recurse -Filter "SKILL.md" -File).Count
+$CmdCount     = (Get-ChildItem -Path "$ScriptDir\commands" -Filter "*.md" -File).Count
+
 # ── Helpers ───────────────────────────────────────────────────────────────────
 function Install-Dir {
     param([string]$Src, [string]$Dest, [string]$Label)
@@ -162,12 +167,12 @@ switch ($Target) {
         Write-Host "  [OK] CLAUDE.md + SOUL.md" -ForegroundColor Green
     }
     { $_ -in "windsurf-project","windsurf-home" } {
-        Install-Dir  "$ScriptDir\agents"   $AgentsDest "Agents   (58)"
-        Install-Dir  "$ScriptDir\skills"   $SkillsDest "Skills   (187)"
+        Install-Dir  "$ScriptDir\agents"   $AgentsDest "Agents   ($AgentCount)"
+        Install-Dir  "$ScriptDir\skills"   $SkillsDest "Skills   ($SkillCount)"
         Install-Flat "$ScriptDir\rules"    $RulesDest  "Rules"
 
         # Generate .windsurfrules from all common rules
-        $WindsurfRulesFile = if ($Target -eq "windsurf-project") { "$(Get-Location)\.windsurfrules" } else { "$HomeDir\.windsurfrules" }
+        $WindsurfRulesFile = if ($Target -eq "windsurf-project") { "$(Get-Location)\.windsurfrules" } else { "$Dest\.windsurfrules" }
         $CommonRulesDir = "$ScriptDir\rules\common"
         if (Test-Path $CommonRulesDir) {
             $Combined = Get-ChildItem -Path $CommonRulesDir -Filter "*.md" | Sort-Object Name | ForEach-Object { Get-Content $_.FullName }
@@ -176,18 +181,18 @@ switch ($Target) {
         }
     }
     "antigravity" {
-        Install-Dir  "$ScriptDir\agents"   $AgentsDest   "Agents -> skills (58)"
-        Install-Dir  "$ScriptDir\commands" $CommandsDest "Commands -> workflows (79)"
+        Install-Dir  "$ScriptDir\agents"   $AgentsDest   "Agents -> skills ($AgentCount)"
+        Install-Dir  "$ScriptDir\commands" $CommandsDest "Commands -> workflows ($CmdCount)"
         Install-Flat "$ScriptDir\rules"    $RulesDest    "Rules"
     }
     "cursor-project" {
         Install-Flat "$ScriptDir\rules"    $RulesDest  "Rules"
-        Install-Dir  "$ScriptDir\skills"   $SkillsDest "Skills (187)"
+        Install-Dir  "$ScriptDir\skills"   $SkillsDest "Skills ($SkillCount)"
     }
     "codex-home" {
-        Install-Dir  "$ScriptDir\agents"   $AgentsDest   "Agents   (58)"
-        Install-Dir  "$ScriptDir\skills"   $SkillsDest   "Skills   (187)"
-        Install-Dir  "$ScriptDir\commands" $CommandsDest "Commands (79)"
+        Install-Dir  "$ScriptDir\agents"   $AgentsDest   "Agents   ($AgentCount)"
+        Install-Dir  "$ScriptDir\skills"   $SkillsDest   "Skills   ($SkillCount)"
+        Install-Dir  "$ScriptDir\commands" $CommandsDest "Commands ($CmdCount)"
         Install-Flat "$ScriptDir\rules"    $RulesDest    "Rules"
     }
     "opencode" {
@@ -231,7 +236,7 @@ switch ($Target) {
     }
     "codex-home" {
         Write-Host "  1. Restart Codex CLI (codex)"
-        Write-Host "  2. All 59 agents and 188 skills are now available"
+        Write-Host "  2. All $AgentCount agents and $SkillCount skills are now available"
         Write-Host "  3. Try:  use kodelyth-advisor"
     }
     "antigravity" {

package/install.sh

@@ -47,7 +47,7 @@ echo -e "${RED}${BOLD}  ║   DANGER LEVEL: GOD TIER    ·    NOT FOR JUNIOR DEV
 echo -e "${RED}${BOLD}  ╚══════════════════════════════════════════════════════════════╝${RESET}"
 echo ""
 echo -e "${BOLD}  Kodelyth ECC — The most dangerous AI coding toolkit on the planet${RESET}"
-echo -e "${CYAN}  61 specialist agents  ·  188 skills  ·  80 commands  ·  20+ hooks  ·  intent routing  ·  compound memory${RESET}"
+echo -e "${CYAN}  62 specialist agents  ·  188 skills  ·  88 commands  ·  20+ hooks  ·  intent routing  ·  compound memory${RESET}"
 echo -e "${CYAN}  Any language  ·  Any framework  ·  Any scale  ·  300B-level quality${RESET}"
 echo ""
 echo -e "  github.com/sifxprime/kodelyth-ecc"
@@ -87,7 +87,7 @@ while [[ $# -gt 0 ]]; do
       TARGET="${1#--target=}"
       shift
       ;;
-    typescript|python|golang|go|rust|java|kotlin|php|swift|cpp|csharp|dart)
+    typescript|python|golang|go|rust|java|kotlin|php|swift|cpp|csharp|dart|ruby|elixir)
       lang="$1"
       [[ "$lang" == "go" ]] && lang="golang"
       LANGUAGE_MODULES+=("$lang")
@@ -143,7 +143,7 @@ while [[ $# -gt 0 ]]; do
       echo "  --profile backend     Go + Python + Java"
       echo ""
       echo "Languages (manual, installs language-specific rules):"
-      echo "  typescript  python  golang  rust  java  kotlin  php  swift  cpp  dart"
+      echo "  typescript  python  golang  rust  java  kotlin  php  swift  cpp  dart  ruby  elixir"
       echo ""
       echo "Examples:"
       echo "  ./install.sh"
@@ -338,15 +338,20 @@ generate_windsurfrules() {
   echo -e "  ${GREEN}✓${RESET} .windsurfrules ${BLUE}(→ $dest_file)${RESET}"
 }
 
+# ── Dynamic Counts ────────────────────────────────────────────────────────────
+AGENT_COUNT=$(find "$SCRIPT_DIR/agents" -maxdepth 1 -name "*.md" | wc -l | tr -d ' ')
+SKILL_COUNT=$(find "$SCRIPT_DIR/skills" -mindepth 2 -maxdepth 2 -name "SKILL.md" | wc -l | tr -d ' ')
+CMD_COUNT=$(find "$SCRIPT_DIR/commands" -maxdepth 1 -name "*.md" | wc -l | tr -d ' ')
+
 # ── Install ───────────────────────────────────────────────────────────────────
 echo -e "${BOLD}Installing components...${RESET}"
 echo ""
 
 case "$TARGET" in
   claude-home)
-    install_dir  "$SCRIPT_DIR/agents"   "$AGENTS_DEST"   "Agents   (58)"
-    install_dir  "$SCRIPT_DIR/skills"   "$SKILLS_DEST"   "Skills   (187)"
-    install_dir  "$SCRIPT_DIR/commands" "$COMMANDS_DEST" "Commands (79)"
+    install_dir  "$SCRIPT_DIR/agents"   "$AGENTS_DEST"   "Agents   ($AGENT_COUNT)"
+    install_dir  "$SCRIPT_DIR/skills"   "$SKILLS_DEST"   "Skills   ($SKILL_COUNT)"
+    install_dir  "$SCRIPT_DIR/commands" "$COMMANDS_DEST" "Commands ($CMD_COUNT)"
     install_hooks                       "$HOOKS_DEST"
     # Rules: install common + selected languages
     mkdir -p "$RULES_DEST"
@@ -369,9 +374,9 @@ case "$TARGET" in
 
   antigravity)
     # Agents → .agent/skills/
-    install_dir  "$SCRIPT_DIR/agents"   "$AGENTS_DEST"   "Agents → skills  (53)"
+    install_dir  "$SCRIPT_DIR/agents"   "$AGENTS_DEST"   "Agents → skills  ($AGENT_COUNT)"
     # Commands → .agent/workflows/
-    install_dir  "$SCRIPT_DIR/commands" "$COMMANDS_DEST" "Commands → workflows (79)"
+    install_dir  "$SCRIPT_DIR/commands" "$COMMANDS_DEST" "Commands → workflows ($CMD_COUNT)"
     # Rules → .agent/rules/ (flattened)
     install_flat "$SCRIPT_DIR/rules"    "$RULES_DEST"    "Rules (flattened)"
     # Kodelyth skills → .agent/rules/ (flattened — Antigravity has no skills system)
@@ -387,19 +392,19 @@ case "$TARGET" in
 
   cursor-project)
     install_flat "$SCRIPT_DIR/rules"    "$RULES_DEST"    "Rules (flattened)"
-    install_dir  "$SCRIPT_DIR/skills"   "$SKILLS_DEST"   "Skills (187)"
+    install_dir  "$SCRIPT_DIR/skills"   "$SKILLS_DEST"   "Skills ($SKILL_COUNT)"
     ;;
 
   codex-home)
-    install_dir  "$SCRIPT_DIR/agents"   "$AGENTS_DEST"   "Agents   (58)"
-    install_dir  "$SCRIPT_DIR/skills"   "$SKILLS_DEST"   "Skills   (187)"
-    install_dir  "$SCRIPT_DIR/commands" "$COMMANDS_DEST" "Commands (79)"
+    install_dir  "$SCRIPT_DIR/agents"   "$AGENTS_DEST"   "Agents   ($AGENT_COUNT)"
+    install_dir  "$SCRIPT_DIR/skills"   "$SKILLS_DEST"   "Skills   ($SKILL_COUNT)"
+    install_dir  "$SCRIPT_DIR/commands" "$COMMANDS_DEST" "Commands ($CMD_COUNT)"
     install_flat "$SCRIPT_DIR/rules"    "$RULES_DEST"    "Rules (flattened)"
     ;;
 
   windsurf-project|windsurf-home)
-    install_dir  "$SCRIPT_DIR/agents"  "$AGENTS_DEST"  "Agents   (58)"
-    install_dir  "$SCRIPT_DIR/skills"  "$SKILLS_DEST"  "Skills   (187)"
+    install_dir  "$SCRIPT_DIR/agents"  "$AGENTS_DEST"  "Agents   ($AGENT_COUNT)"
+    install_dir  "$SCRIPT_DIR/skills"  "$SKILLS_DEST"  "Skills   ($SKILL_COUNT)"
     install_flat "$SCRIPT_DIR/rules"   "$RULES_DEST"   "Rules (flattened)"
     generate_windsurfrules "$SCRIPT_DIR/rules" "$WINDSURFRULES_DEST"
     ;;
@@ -472,10 +477,11 @@ case "$TARGET" in
     echo "    use kodelyth-advisor"
     ;;
   windsurf-project|windsurf-home)
+    RULE_COUNT=$(find "$SCRIPT_DIR/rules/common" -maxdepth 1 -name "*.md" ! -name "agent-intent-routing.md" | wc -l | tr -d ' ')
     echo -e "${BOLD}  Windsurf — what to do now:${RESET}"
     echo ""
     echo "  Open your project in Windsurf (Cascade)."
-    echo "  .windsurfrules is active — 15 coding rules + intent routing loaded automatically."
+    echo "  .windsurfrules is active — $RULE_COUNT coding rules + intent routing loaded automatically."
     echo "  Agents available in .windsurf/agents/"
     echo ""
     echo "    use kodelyth-advisor       ← not sure where to start"

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "kodelyth-ecc",
-  "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.",
+  "version": "1.5.6",
+  "description": "Production-grade AI coding toolkit — 62 agents, 188 skills, 90 commands, parallel multi-agent commands, semantic intent routing, self-learning memory. Works with Claude Code, Windsurf, Cursor, Codex, Antigravity, and OpenCode.",
   "author": "Kodelyth <github.com/sifxprime>",
   "license": "MIT",
   "repository": {

package/rules/common/agents.md

@@ -1,50 +1,146 @@
 # Agent Orchestration
 
-## Available Agents
-
-Located in `~/.claude/agents/`:
-
-| Agent | Purpose | When to Use |
-|-------|---------|-------------|
-| planner | Implementation planning | Complex features, refactoring |
-| architect | System design | Architectural decisions |
-| tdd-guide | Test-driven development | New features, bug fixes |
-| code-reviewer | Code review | After writing code |
-| security-reviewer | Security analysis | Before commits |
-| build-error-resolver | Fix build errors | When build fails |
-| e2e-runner | E2E testing | Critical user flows |
-| refactor-cleaner | Dead code cleanup | Code maintenance |
-| doc-updater | Documentation | Updating docs |
-| rust-reviewer | Rust code review | Rust projects |
-
-## Immediate Agent Usage
-
-No user prompt needed:
-1. Complex feature requests - Use **planner** agent
-2. Code just written/modified - Use **code-reviewer** agent
-3. Bug fix or new feature - Use **tdd-guide** agent
-4. Architectural decision - Use **architect** agent
-
-## Parallel Task Execution
-
-ALWAYS use parallel Task execution for independent operations:
-
-```markdown
-# GOOD: Parallel execution
-Launch 3 agents in parallel:
-1. Agent 1: Security analysis of auth module
-2. Agent 2: Performance review of cache system
-3. Agent 3: Type checking of utilities
-
-# BAD: Sequential when unnecessary
-First agent 1, then agent 2, then agent 3
+62 specialist agents are available. Intent routing is always-on — describe your problem in plain words and the right agent is invoked automatically. You can also invoke explicitly: `use <agent-name>`.
+
+## Kodelyth Exclusives
+
+| Agent | When to Use |
+|-------|-------------|
+| `kodelyth-advisor` | Not sure where to start — master guide |
+| `pair-programmer` | Before writing code — think through approach first |
+| `debug-detective` | Any bug — evidence-first root cause, never guess-and-check |
+| `silent-failure-hunter` | Bugs that don't throw errors |
+| `incident-commander` | Production incident — P0/P1 triage, contain, postmortem |
+| `load-tester` | Load/stress testing — k6, Locust, Artillery, capacity planning |
+| `kodelyth-memory` | Manage local BM25 memory — recall, capture, review |
+| `image-architect` | AI image generation — Gemini/DALL-E/fal.ai/SVG |
+
+## Planning & Architecture
+
+| Agent | When to Use |
+|-------|-------------|
+| `planner` | Plan a feature before writing a line of code |
+| `architect` | System-level design, dependency graphs |
+| `code-architect` | Code-level architecture decisions |
+| `chief-of-staff` | Strategic decisions, comms, stakeholder updates |
+| `migration-guide` | Framework/language version upgrades, phase by phase |
+
+## Code Review
+
+| Agent | When to Use |
+|-------|-------------|
+| `code-reviewer` | General review after writing code |
+| `typescript-reviewer` | TypeScript / React / Next.js |
+| `python-reviewer` | Python |
+| `go-reviewer` | Go |
+| `rust-reviewer` | Rust |
+| `java-reviewer` | Java / Spring Boot |
+| `kotlin-reviewer` | Kotlin / Android / KMP |
+| `cpp-reviewer` | C++ |
+| `csharp-reviewer` | C# / .NET |
+| `flutter-reviewer` | Flutter / Dart |
+| `database-reviewer` | SQL schema, query patterns, indexes |
+| `healthcare-reviewer` | PHI/HIPAA-aware review for healthcare apps |
+
+## Build Fixers
+
+| Agent | When to Use |
+|-------|-------------|
+| `build-error-resolver` | General build failure |
+| `go-build-resolver` | Go build errors |
+| `rust-build-resolver` | Rust/Cargo build errors |
+| `java-build-resolver` | Java/Maven/Gradle build errors |
+| `kotlin-build-resolver` | Kotlin/Gradle build errors |
+| `cpp-build-resolver` | C++/CMake/Make build errors |
+| `dart-build-resolver` | Dart/Flutter build errors |
+| `pytorch-build-resolver` | PyTorch/CUDA build errors |
+| `dependency-doctor` | npm/pip/cargo/maven dep hell, CVEs, lockfile drift |
+| `env-debugger` | "Works on my machine" — env, config, secrets layers |
+
+## Debugging & Testing
+
+| Agent | When to Use |
+|-------|-------------|
+| `tdd-guide` | Write tests first — TDD methodology |
+| `e2e-runner` | End-to-end test automation |
+| `pr-test-analyzer` | CI output — root cause failing tests |
+| `flake-hunter` | Flaky test stabilization — never blind retries |
+
+## Security & API
+
+| Agent | When to Use |
+|-------|-------------|
+| `security-reviewer` | OWASP top 10, secrets, auth, injection vectors |
+| `api-guardian` | Detect breaking API changes before they ship |
+
+## Performance & Quality
+
+| Agent | When to Use |
+|-------|-------------|
+| `performance-optimizer` | Profiling-first — measure before optimizing |
+| `refactor-cleaner` | Remove code smells, dead code, tech debt |
+| `code-simplifier` | Improve readability without changing behavior |
+| `type-design-analyzer` | TypeScript type system design |
+
+## Documentation & Analysis
+
+| Agent | When to Use |
+|-------|-------------|
+| `doc-updater` | Update or write documentation |
+| `docs-lookup` | Find docs for a library or API |
+| `comment-analyzer` | Audit code comments for accuracy |
+| `code-explorer` | Explore an unfamiliar codebase |
+| `conversation-analyzer` | Analyze conversation or chat patterns |
+
+## Release & Ops
+
+| Agent | When to Use |
+|-------|-------------|
+| `release-captain` | Cut a clean release — semver, tagging, rollback plan |
+| `git-rescue` | Broken git state, lost commits, bad rebase — no history loss |
+
+## Open Source
+
+| Agent | When to Use |
+|-------|-------------|
+| `opensource-forker` | Fork and clean a project for open-source release |
+| `opensource-sanitizer` | Strip secrets, PII, proprietary references |
+| `opensource-packager` | README, license, contribution docs |
+
+## Specialized
+
+| Agent | When to Use |
+|-------|-------------|
+| `ux-reviewer` | UX behavior + WCAG 2.1 AA accessibility |
+| `seo-specialist` | Technical SEO, structured data, rankings |
+
+## GAN Harness (Multi-Agent)
+
+| Agent | When to Use |
+|-------|-------------|
+| `gan-planner` | Plan a GAN-style generator/evaluator workflow |
+| `gan-generator` | Generate output in a GAN harness loop |
+| `gan-evaluator` | Evaluate output and provide adversarial feedback |
+| `harness-optimizer` | Optimize agent harness action spaces |
+| `loop-operator` | Operate autonomous agent loops |
+
+## Parallel Execution
+
+ALWAYS launch independent agents in parallel:
+
+```
+# GOOD: parallel
+use code-reviewer + security-reviewer + ux-reviewer simultaneously
+
+# BAD: sequential when not needed
+code-reviewer → then security-reviewer → then ux-reviewer
 ```
 
-## Multi-Perspective Analysis
+## Standard Handoff Chains
 
-For complex problems, use split role sub-agents:
-- Factual reviewer
-- Senior engineer
-- Security expert
-- Consistency reviewer
-- Redundancy checker
+| Workflow | Chain |
+|----------|-------|
+| New feature | `pair-programmer` → `tdd-guide` → `code-reviewer` → `security-reviewer` |
+| Bug fix | `debug-detective` → `tdd-guide` → `refactor-cleaner` |
+| Production incident | `incident-commander` → `debug-detective` → `tdd-guide` |
+| Open-source | `opensource-forker` → `opensource-sanitizer` → `opensource-packager` → `release-captain` |

package/rules/elixir/coding-style.md

@@ -0,0 +1,46 @@
+---
+paths:
+  - "**/*.ex"
+  - "**/*.exs"
+---
+# Elixir Coding Style
+
+> This file extends [common/coding-style.md](../common/coding-style.md) with Elixir specific content.
+
+## Standards
+
+- Follow the official **Elixir Style Guide**
+- Use **mix format** — non-negotiable, always auto-format
+- All public functions must have `@spec` type annotations and `@doc` documentation
+
+## Immutability
+
+Data is immutable by default in Elixir. Embrace it:
+
+```elixir
+# Use the pipe operator for data transformations
+result =
+  input
+  |> validate()
+  |> transform()
+  |> persist()
+```
+
+## Function Heads Over Conditionals
+
+```elixir
+# Prefer pattern-matched function heads over cond/case at the top level
+def process(%{status: :active} = user), do: activate(user)
+def process(%{status: :banned} = user), do: reject(user)
+def process(_user), do: {:error, :unknown_status}
+```
+
+## Formatting
+
+- **mix format** — run on every save
+- **Credo** for code quality and style checks
+- Line length: 98 characters (mix format default)
+
+## Reference
+
+See skill: `elixir-patterns` for comprehensive GenServer, Phoenix, and OTP patterns.