mindforge-cc 2.0.0 → 2.1.0

package/CHANGELOG.md

@@ -1,5 +1,23 @@
 # Changelog
 
+## [2.1.0] — The Specialized Expansion — 2026-03-24
+
+🧩 **MindForge v2.1.0 — The Specialized Expansion**
+
+This release significantly expands the MindForge persona ecosystem, integrating 18+ high-performance specialized agents from the GSD framework. This expansion doubles the framework's baseline capabilities in research, architecture, execution, and quality assurance.
+
+### Added
+- **18+ New Specialized Personas**: Integration of advanced agents including `nyquist-auditor`, `user-profiler`, `advisor-researcher`, `ui-auditor`, and more.
+- **Extended Mapping & Strategy**: Enhanced `roadmapper-extend` and `codebase-mapper-extend` for deep project lifecycle management.
+- **Comprehensive Permissions Audit**: Full tool-access transparency for all 32 personas in `docs/PERSONAS.md`.
+- **Architectural State Update**: `Master-Context.md` now reflects the 32-persona structural foundation.
+
+### Changed
+- **Documentation Overhaul**: Complete update of `PERSONAS.md` and `Master-Context.md` to reflect the expanded ecosystem.
+- **Branding Alignment**: All integrated GSD personas rebranded and fully sanitized for MindForge native use.
+
+---
+
 ## [2.0.0] — The Autonomous Enterprise — 2026-03-24
 
 🚀 **MindForge v2.0.0 — The Autonomous Enterprise — Major Release**
@@ -13,6 +31,14 @@ This major release transforms MindForge from a Claude-centric framework into a u
 - **Unified Migration Engine (v2.0.0)**: Additive schema upgrades for `AUDIT.jsonl` (runtime/agent_id) and `token-usage.jsonl` (model_group).
 - **Hardened Self-Building Skills**: Automated skill capture from documentation and phase outputs.
 - **7-Dimension Quality Scorer**: Enhanced static analysis for skill authoring.
+- **GSD Integration**: 10 new advanced commands for design-first planning, zero-friction capture, and smart routing.
+- **`/mindforge:do`**: Smart natural language dispatcher that routes intent to the correct command.
+- **`/mindforge:ui-phase` & `/mindforge:ui-review`**: Tier-1 visual design contract and visual audit engine.
+- **`/mindforge:note`**: Instant idea capture with todo promotion.
+- **`/mindforge:validate-phase`**: Requirement coverage and test gap identification.
+- **`/mindforge:session-report`**: Professional stakeholder summary with token profiling.
+- **Backlog & Seed Management**: `/mindforge:add-backlog`, `/mindforge:review-backlog`, and `/mindforge:plant-seed`.
+- **Parallel Workstreams**: `/mindforge:workstreams` for concurrent milestone execution.
 - **65-Point Production Checklist**: Exhaustive verification suite for enterprise readiness.
 
 ### Changed

package/MINDFORGE.md

@@ -81,6 +81,8 @@ BROWSER_HEADLESS=true
 DEV_SERVER_URL=http://localhost:3000
 AUTO_RUN_QA_AFTER_UI_WAVES=true
 BROWSER_IDLE_TIMEOUT_MINUTES=30
+AUTO_RUN_UI_REVIEW_AFTER_UI_WAVES=true
+UI_PHASE_ACCESSIBILITY_STANDARD=WCAG_AA
 
 ## Project-specific agent instructions
 ADDITIONAL_AGENT_INSTRUCTIONS="""

package/README.md

@@ -125,6 +125,7 @@ If issues are found, run:
 ## Quick start (existing codebase)
 ```bash
 /mindforge:map-codebase
+/mindforge:do I want to plan the next phase
 /mindforge:plan-phase 1
 ```
 
@@ -136,6 +137,15 @@ If issues are found, run:
     → Requirements interview
     → Creates PROJECT.md, REQUIREMENTS.md, STATE.md
 
+/ mindforge:do <text>
+    → Smart natural language dispatcher (v2)
+
+/ mindforge:note <text>
+    → Zero-friction idea capture and todo promotion (v2)
+
+/ mindforge:ui-phase 1
+    → Create UI design contract (UI-SPEC.md) (v2)
+
 / mindforge:plan-phase 1
     → Discuss scope and decisions
     → Research domain (parallel)
@@ -146,6 +156,32 @@ If issues are found, run:
     → One commit per task
     → Automated verification
 
+/ mindforge:ui-review 1
+    → Retroactive 6-pillar visual audit (v2)
+
+/ mindforge:validate-phase 1
+    → Requirement coverage and test gap audit (v2)
+
+/ mindforge:session-report
+    → Automated post-session stakeholder summary (v2)
+
+/ mindforge:add-backlog <desc>
+    → Park ideas in 999.x "parking lot" (v2)
+
+/ mindforge:review-backlog
+    → Review and promote backlog items (v2)
+
+/ mindforge:plant-seed <idea>
+    → Capture speculative ideas with triggers (v2)
+
+/ mindforge:workstreams
+    → Parallel feature tracks with isolated state (v2)
+
+/ mindforge:execute-phase 1
+    → Wave-based parallel execution
+    → One commit per task
+    → Automated verification
+
 / mindforge:verify-phase 1
     → Human acceptance testing
     → Debug agent on failures
@@ -259,7 +295,8 @@ See `.mindforge/production/token-optimiser.md`.
 - **Visual QA Engine**: `/mindforge:qa` and automated regression tests.
 - **Persistent Browser Runtime**: `/mindforge:browse` and Playwright integration.
 - **Autonomous Execution Engine**: `/mindforge:auto` and `/mindforge:steer`.
-- 48+ commands across 10 workflow categories.
+- **GSD Integration**: 10 new advanced commands for design, capture, and routing.
+- 58+ commands across 12 workflow categories.
 - 12 core skill packs with a three-tier registry.
 - 8 specialised agent personas.
 - Wave-based execution with dependency graph and compaction.

package/bin/installer-core.js

@@ -223,7 +223,7 @@ function verifyInstall(baseDir, cmdsDir, runtime, scope) {
   const cfg = RUNTIMES[runtime];
   const pfx = runtime === 'antigravity' ? 'mindforge:' : '';
   const required = [
-    scope === 'local' ? path.join(process.cwd(), cfg.entryFile) : path.join(baseDir, cfg.entryFile),
+    scope === 'local' ? path.join(process.cwd(), (cfg.entryFile || 'CLAUDE.md').replace(/\.rd$/, '.md')) : path.join(baseDir, (cfg.entryFile || 'CLAUDE.md').replace(/\.rd$/, '.md')),
     path.join(cmdsDir, `${pfx}help.md`),
     path.join(cmdsDir, `${pfx}init-project.md`),
     path.join(cmdsDir, `${pfx}health.md`),
@@ -267,10 +267,9 @@ async function install(runtime, scope, options = {}) {
     return;
   }
 
-  const claudeSrc = src('.claude', 'CLAUDE.md');
-  if (fsu.exists(claudeSrc)) {
+  if (fsu.exists(src('.claude', 'CLAUDE.md'))) {
     // ✨ PERSISTENT MEMORY: Load relevant context for this session
-    let content = fsu.read(claudeSrc);
+    let content = fsu.read(src('.claude', 'CLAUDE.md'));
     if (scope === 'local') {
       try {
         const stack = SessionMemoryLoader.readTechStack();

package/docs/Context/Master-Context.md

@@ -34,15 +34,8 @@ anti-pattern detector, quality metrics, team profiling).
 Built the entire structural foundation:
 
 - **`.claude/CLAUDE.md`** — The agent entry point. Session start protocol, plan-first rule, quality gates, security auto-trigger, state artifact table. Mirrored identically to `.agent/CLAUDE.md` (Antigravity runtime).
-- **8 agent persona files** in `.mindforge/personas/`:
-  - `analyst.md` — Requirements decomposition and gap identification
-  - `architect.md` — System design, ADRs, technology decisions
-  - `developer.md` — Implementation with 5 common AI anti-pattern guards
-  - `qa-engineer.md` — Test strategy and verification
-  - `security-reviewer.md` — OWASP-aligned security review
-  - `tech-writer.md` — Documentation and changelog authoring
-  - `debug-specialist.md` — 10-step root cause analysis protocol
-  - `release-manager.md` — Deployment coordination
+- **32 agent persona files** in `.mindforge/personas/`:
+  - `advisor-researcher.md`, `analyst.md`, `architect.md`, `assumptions-analyzer-extend.md`, `assumptions-analyzer.md`, `codebase-mapper-extend.md`, `codebase-mapper.md`, `coverage-specialist.md`, `debug-specialist.md`, `debugger.md`, `decision-architect.md`, `developer.md`, `executor.md`, `integration-checker.md`, `nyquist-auditor.md`, `phase-researcher.md`, `plan-checker.md`, `planner.md`, `project-researcher.md`, `qa-engineer.md`, `release-manager.md`, `research-agent.md`, `research-synthesizer.md`, `roadmapper-extend.md`, `roadmapper.md`, `security-reviewer.md`, `tech-writer.md`, `ui-auditor.md`, `ui-checker.md`, `ui-researcher.md`, `user-profiler.md`, `verifier.md`
 - **5 initial core skill packs** in `.mindforge/skills/`:
   - `security-review/SKILL.md` — 29 trigger keywords, OWASP A01-A10
   - `code-quality/SKILL.md` — Complexity, naming, error handling
@@ -331,7 +324,7 @@ mindforge-cc/                         ← npm package root
 │       └── [36 .md command files]
 │
 ├── .mindforge/
-│   ├── personas/                     ← 8 persona definitions + overrides/
+│   ├── personas/                     ← 32 persona definitions + overrides/
 │   ├── skills/                       ← 10 core skill packs (SKILL.md each)
 │   ├── engine/
 │   │   ├── wave-executor.md          ← Kahn's topological sort, parallel waves
@@ -490,9 +483,9 @@ mindforge-cc/                         ← npm package root
 9. `incident-response` — P0-P3, runbooks, postmortems
 10. `database-patterns` — Compound cursor, UUIDv7, indexes
 
-### 8 Agent Personas
+### 32 Agent Personas
 
-analyst, architect, developer, qa-engineer, security-reviewer, tech-writer, debug-specialist, release-manager
+advisor-researcher, analyst, architect, assumptions-analyzer-extend, assumptions-analyzer, codebase-mapper-extend, codebase-mapper, coverage-specialist, debug-specialist, debugger, decision-architect, developer, executor, integration-checker, nyquist-auditor, phase-researcher, plan-checker, planner, project-researcher, qa-engineer, release-manager, research-agent, research-synthesizer, roadmapper-extend, roadmapper, security-reviewer, tech-writer, ui-auditor, ui-checker, ui-researcher, user-profiler, verifier
 
 ### 20 Architecture Decision Records
 
@@ -698,4 +691,4 @@ All prompt files are in `/mnt/user-data/outputs/`:
 
 ---
 
-*State file generated at completion. MindForge v1.0.0 — 36 commands · 10 skills · 8 personas · 20 ADRs · 15 test suites.*
+*State file generated at completion. MindForge v1.0.0 — 36 commands · 10 skills · 32 personas · 20 ADRs · 15 test suites.*