@softspark/ai-toolkit 1.3.9 → 1.3.10

package/CHANGELOG.md

@@ -7,6 +7,13 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ---
 
+## v1.3.10 — Patch (2026-04-07)
+
+### Fixed
+- **Version cache**: `install` and `update` now clear `~/.ai-toolkit/version-check.json` so `status` shows correct "Latest" immediately after upgrade.
+
+---
+
 ## v1.3.9 — Single Source of Truth for Counts (2026-04-07)
 
 ### Changed

package/app/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ai-toolkit",
   "description": "Professional-grade Claude Code toolkit with persona presets, skill security auditor, expanded lifecycle hooks, experimental opt-in plugin packs, benchmark harvesting, and multi-tool support.",
-  "version": "1.3.8",
+  "version": "1.3.10",
   "author": {
     "name": "SoftSpark",
     "url": "https://github.com/softspark"

package/app/agents/orchestrator.md

@@ -145,7 +145,7 @@ smart_query("[task description in English]")  # or hybrid_search_kb()
 | `data-analyst` | Data | Analysis, visualization, SQL |
 | `documenter` | Documentation | Architecture notes, runbooks, guides |
 | `tech-lead` | Architecture | Code review, standards, tech disputes |
-| `product-owner` | Product | Requirements, priorities, acceptance criteria |
+| `product-manager` | Product | Requirements, priorities, acceptance criteria |
 | `security-architect` | Security Design | Threat modeling, secure architecture |
 | `night-watchman` | Autonomous Ops | Auto-updates, refactoring, cleanup |
 | `chaos-monkey` | Resilience | Fault injection, reliability testing |
@@ -154,6 +154,24 @@ smart_query("[task description in English]")  # or hybrid_search_kb()
 | `chief-of-staff` | Management | Executive summary, noise filtering |
 | `meta-architect` | Evolution | Self-optimization, agent updates |
 | `system-governor` | Safety | Constitution enforcement, VETO power |
+| `ai-engineer` | AI/ML | LLM integration, RAG, vector DBs |
+| `ml-engineer` | ML | Model training, MLOps |
+| `nlp-engineer` | NLP | NER, text classification, NLP pipelines |
+| `llm-ops-engineer` | LLM Ops | LLM caching, fallback, cost optimization |
+| `prompt-engineer` | Prompts | Prompt design, chain-of-thought |
+| `data-scientist` | Data Science | Statistics, EDA, A/B testing |
+| `search-specialist` | Search | Search optimization, relevance tuning |
+| `code-reviewer` | Code Quality | Code review, quality, security |
+| `code-archaeologist` | Legacy Code | Legacy code investigation, dead code |
+| `command-expert` | CLI | Shell scripting, CLI tools |
+| `qa-automation-engineer` | QA | E2E testing, Playwright, Cypress |
+| `mcp-testing-engineer` | MCP Testing | MCP protocol testing |
+| `infrastructure-architect` | Architecture | Architecture decisions, trade-offs |
+| `infrastructure-validator` | Deployment | Deployment verification, health checks |
+| `incident-responder` | Incidents | Production incidents, P1-P4 |
+| `seo-specialist` | SEO | SEO, meta tags, structured data |
+| `fact-checker` | Verification | Claim verification, accuracy |
+| `technical-researcher` | Research | Technical investigation, synthesis |
 
 ## 🔴 Agent Boundary Enforcement
 
@@ -213,7 +231,7 @@ Invoke entire SQUADS in PARALLEL to maximize impact.
 
 ### 1. The "Feature Squad" (New Capability)
 **Target**: Implementing a new user-facing feature.
-- `product-owner`: Value & Acceptance Criteria
+- `product-manager`: Value & Acceptance Criteria
 - `tech-lead`: Architecture & Standards
 - `frontend-specialist`: UI/UX
 - `backend-specialist`: Logic & Data
@@ -255,7 +273,7 @@ Invoke entire SQUADS in PARALLEL to maximize impact.
 □ MCP/Protocol  → mcp-specialist
 □ Discovery     → explorer-agent
 □ Architecture  → tech-lead
-□ Product       → product-owner
+□ Product       → product-manager
 □ Security Design → security-architect
 □ Maintenance   → night-watchman
 □ Resilience    → chaos-monkey

package/kb/reference/agents-catalog.md

@@ -3,7 +3,7 @@ title: "AI Toolkit - Agents Catalog"
 category: reference
 service: ai-toolkit
 tags: [agents, catalog, roles, ai-development]
-version: "1.3.8"
+version: "1.3.10"
 created: "2026-03-23"
 last_updated: "2026-03-25"
 description: "Complete catalog of specialized agents with roles, models, and use cases."

package/kb/reference/architecture-overview.md

@@ -3,7 +3,7 @@ title: "AI Toolkit - Architecture Overview"
 category: reference
 service: ai-toolkit
 tags: [architecture, overview, design, structure]
-version: "1.0.0"
+version: "1.3.10"
 created: "2026-03-23"
 last_updated: "2026-04-07"
 description: "Architecture of ai-toolkit: directory layout, global install model, skill tiers, and integration with projects."

package/kb/reference/skills-catalog.md

@@ -3,7 +3,7 @@ title: "AI Toolkit - Skills Catalog"
 category: reference
 service: ai-toolkit
 tags: [skills, domain-knowledge, catalog, task-skills, hybrid-skills]
-version: "1.3.8"
+version: "1.3.10"
 created: "2026-03-23"
 last_updated: "2026-04-07"
 description: "Complete skills catalog with task, hybrid, and knowledge skills. Includes effort levels, skill-scoped hooks, executable scripts, security auditor, and persona presets."

package/llms-full.txt

@@ -22,7 +22,6 @@
 - [CI Integration](kb/reference/ci-integration.md)
 - [Claude Ecosystem Benchmark Snapshot](kb/reference/claude-ecosystem-benchmark-snapshot.md)
 - [Claude Ecosystem Expansion Foundations](kb/reference/claude-ecosystem-expansion-foundations.md)
-- [Commands Catalog (DEPRECATED)](kb/reference/commands-catalog.md)
 - [Plan: Competitive Features — ai-toolkit](kb/reference/competitive-features-implementation.md)
 - [Distribution Model](kb/reference/distribution-model.md)
 - [Extension API Reference](kb/reference/extension-api.md)
@@ -582,7 +581,7 @@ title: "AI Toolkit - Agents Catalog"
 category: reference
 service: ai-toolkit
 tags: [agents, catalog, roles, ai-development]
-version: "1.3.8"
+version: "1.3.10"
 created: "2026-03-23"
 last_updated: "2026-03-25"
 description: "Complete catalog of specialized agents with roles, models, and use cases."
@@ -934,7 +933,7 @@ title: "AI Toolkit - Architecture Overview"
 category: reference
 service: ai-toolkit
 tags: [architecture, overview, design, structure]
-version: "1.0.0"
+version: "1.3.10"
 created: "2026-03-23"
 last_updated: "2026-04-07"
 description: "Architecture of ai-toolkit: directory layout, global install model, skill tiers, and integration with projects."
@@ -1540,32 +1539,6 @@ The reference benchmark set is intentionally curated:
 
 ---
 
-## kb/reference/commands-catalog.md
-
----
-title: "AI Toolkit - Commands Catalog (DEPRECATED)"
-category: reference
-service: ai-toolkit
-tags: [commands, deprecated]
-version: "1.0.0"
-created: "2026-03-23"
-last_updated: "2026-03-28"
-description: "DEPRECATED: All slash commands are implemented as skills. See skills-catalog.md for the current catalog."
----
-
-# Commands Catalog (DEPRECATED)
-
-All slash commands have been migrated to skills.
-
-See **[Skills Catalog](skills-catalog.md)** for the complete list of skills, including:
-- **28 Task Skills** — formerly standalone commands and creator workflows (e.g., `/commit`, `/test`, `/deploy`, `/hook-creator`, `/plugin-creator`)
-- **30 Hybrid Skills** — slash commands that also provide agent knowledge (e.g., `/review`, `/debug`, `/plan`, `/tdd`, `/write-a-prd`, `/council`, `/introspect`)
-- **32 Knowledge Skills** — domain patterns auto-loaded by agents (e.g., `brand-voice`, `clean-code`, `testing-patterns`)
-
-Slash command syntax (`/command`) continues to work. The underlying implementation moved from `app/commands/` to `app/skills/`.
-
----
-
 ## kb/reference/competitive-features-implementation.md
 
 ---
@@ -4114,7 +4087,7 @@ title: "AI Toolkit - Skills Catalog"
 category: reference
 service: ai-toolkit
 tags: [skills, domain-knowledge, catalog, task-skills, hybrid-skills]
-version: "1.3.8"
+version: "1.3.10"
 created: "2026-03-23"
 last_updated: "2026-04-07"
 description: "Complete skills catalog with task, hybrid, and knowledge skills. Includes effort levels, skill-scoped hooks, executable scripts, security auditor, and persona presets."

package/llms.txt

@@ -22,7 +22,6 @@
 - [CI Integration](kb/reference/ci-integration.md)
 - [Claude Ecosystem Benchmark Snapshot](kb/reference/claude-ecosystem-benchmark-snapshot.md)
 - [Claude Ecosystem Expansion Foundations](kb/reference/claude-ecosystem-expansion-foundations.md)
-- [Commands Catalog (DEPRECATED)](kb/reference/commands-catalog.md)
 - [Plan: Competitive Features — ai-toolkit](kb/reference/competitive-features-implementation.md)
 - [Distribution Model](kb/reference/distribution-model.md)
 - [Extension API Reference](kb/reference/extension-api.md)

package/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.3.8",
+  "version": "1.3.10",
   "components": {
     "agents": {
       "description": "44 specialized agents (orchestrator, backend, frontend, security, devops, etc.)",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@softspark/ai-toolkit",
-  "version": "1.3.9",
+  "version": "1.3.10",
   "description": "Professional-grade AI coding toolkit: 90 skills, 44 agents, multi-platform support (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment), machine-enforced safety constitution, persona presets, skill security auditor, expanded lifecycle hooks, 11 plugin packs, and benchmark tooling.",
   "keywords": [
     "claude",

package/scripts/install_steps/install_state.py

@@ -88,6 +88,11 @@ def record_install(
 
     save_state(state)
 
+    # Clear version check cache (version may have changed)
+    cache_file = _state_path().parent / "version-check.json"
+    if cache_file.is_file():
+        cache_file.unlink()
+
 
 def print_status() -> None:
     """Print a human-readable summary of the install state."""

package/kb/reference/commands-catalog.md

@@ -1,21 +0,0 @@
----
-title: "AI Toolkit - Commands Catalog (DEPRECATED)"
-category: reference
-service: ai-toolkit
-tags: [commands, deprecated]
-version: "1.0.0"
-created: "2026-03-23"
-last_updated: "2026-03-28"
-description: "DEPRECATED: All slash commands are implemented as skills. See skills-catalog.md for the current catalog."
----
-
-# Commands Catalog (DEPRECATED)
-
-All slash commands have been migrated to skills.
-
-See **[Skills Catalog](skills-catalog.md)** for the complete list of skills, including:
-- **28 Task Skills** — formerly standalone commands and creator workflows (e.g., `/commit`, `/test`, `/deploy`, `/hook-creator`, `/plugin-creator`)
-- **30 Hybrid Skills** — slash commands that also provide agent knowledge (e.g., `/review`, `/debug`, `/plan`, `/tdd`, `/write-a-prd`, `/council`, `/introspect`)
-- **32 Knowledge Skills** — domain patterns auto-loaded by agents (e.g., `brand-voice`, `clean-code`, `testing-patterns`)
-
-Slash command syntax (`/command`) continues to work. The underlying implementation moved from `app/commands/` to `app/skills/`.