mindforge-cc 2.0.0-alpha.9 → 2.1.0

package/docs/architecture/decision-records-index.md

@@ -24,3 +24,6 @@ All 20 ADRs in chronological order.
 | ADR-018 | Installer detects and handles self-install | Accepted | Installer running inside its own repo = no-op for framework files |
 | ADR-019 | Self-update preserves original install scope | Accepted | Update local→local, global→global |
 | ADR-020 | v1.0.0 stable interface contract | Accepted | Defines what "stable" means for plugins and SDK consumers |
+| ADR-039 | Multi-runtime platform support | Accepted | Native support for Cursor, Gemini, Copilot, etc. |
+| ADR-040 | Additive schema migration strategy | Accepted | Non-destructive, backup-first backfill logic |
+| ADR-041 | Stable runtime interface contract | Accepted | Exported RUNTIMES and adapters for extensibility |

package/docs/commands-reference.md

@@ -9,4 +9,7 @@
 | `/mindforge:verify-phase [N]`   | Human acceptance testing + automated checks  |
 | `/mindforge:ship [N]`           | Generate changelog, run quality gates, create PR |
 | `/mindforge:dashboard`           | Manage the real-time web observability dashboard |
+| `/mindforge:learn [SRC]`         | Automatically capture skills from Docs, Sessions, or npm |
+| `/mindforge:marketplace [SEARCH]`| Search, install, and publish community skills        |
+| `/mindforge:new-runtime`     | Scaffold custom runtime configurations for any AI agent |
 

package/docs/mindforge-md-reference.md

@@ -28,6 +28,10 @@ Unavailable value -> fallback to `inherit` with warning.
 - `VERIFY_PASS_RATE_WARNING_THRESHOLD`
 - `COMPACTION_THRESHOLD_PCT`
 - `MAX_TASKS_PER_PHASE`
+- `AUTONOMOUS_MODE_ENABLED`
+- `NODE_REPAIR_ENABLED`
+- `STUCK_DETECTION_TIMEOUT_MS`
+- `STEERING_CHECK_INTERVAL_MS`
 
 ### Quality and governance
 - `MIN_TEST_COVERAGE_PCT`

package/docs/reference/commands.md

@@ -1,89 +1,99 @@
 # MindForge v2.0.0 — Complete Commands Reference
 
-## All 40+ commands
+## All 50+ commands
 
 ### Lifecycle commands (core workflow)
 
 | Command | Usage | Description | Added |
 |---|---|---|---|
-| `/mindforge:init-project` | `init-project` | Guided project setup — creates all `.planning/` files |
-| `/mindforge:discuss-phase` | `discuss-phase [N] [--batch|--auto]` | Pre-planning interview to capture implementation decisions |
-| `/mindforge:plan-phase` | `plan-phase [N]` | Research, decompose, and create atomic task plans |
+| `/mindforge:init-project` | `init-project` | Guided project setup — creates all `.planning/` files | |
+| `/mindforge:discuss-phase` | `discuss-phase [N] [--batch|--auto]` | Pre-planning interview to capture implementation decisions | |
+| `/mindforge:ui-phase` | `ui-phase [N]` | Generate UI design contract (UI-SPEC.md) | v2.0.0 |
+| `/mindforge:plan-phase` | `plan-phase [N]` | Research, decompose, and create atomic task plans | |
 | `/mindforge:execute-phase` | `execute-phase [N]` | Wave-based parallel execution of all phase plans | Day 1+2 |
-| `/mindforge:verify-phase` | `verify-phase [N]` | Automated + human acceptance testing pipeline |
-| `/mindforge:ship` | `ship [N]` | Create PR, write release notes, push to remote |
-| `/mindforge:auto` | `auto [--phase N] [--milestone M]` | Walk-away autonomous execution with stuck detection |
-| `/mindforge:steer` | `steer "instruction"` | Inject guidance into a running autonomous session |
-| `/mindforge:next` | `next` | Auto-detect and execute the correct next workflow step |
-| `/mindforge:cross-review` | `cross-review` | Adversarial multi-model code review and synthesis |
-| `/mindforge:research` | `research "query"` | Deep research using Gemini 1.5 Pro 1M context |
-| `/mindforge:remember` | `remember [--add X|--search Y|--promote ID|--stats]` | Persistent knowledge graph management |
+| `/mindforge:ui-review` | `ui-review [N]` | Retroactive 6-pillar visual audit | v2.0.0 |
+| `/mindforge:verify-phase` | `verify-phase [N]` | Automated + human acceptance testing pipeline | |
+| `/mindforge:validate-phase` | `validate-phase [N]` | Requirement coverage and test gap audit | v2.0.0 |
+| `/mindforge:ship` | `ship [N]` | Create PR, write release notes, push to remote | |
+| `/mindforge:auto` | `auto [--phase N] [--milestone M]` | Walk-away autonomous execution with stuck detection | |
+| `/mindforge:steer` | `steer "instruction"` | Inject guidance into a running autonomous session | |
+| `/mindforge:next` | `next` | Auto-detect and execute the correct next workflow step | |
+| `/mindforge:cross-review` | `cross-review` | Adversarial multi-model code review and synthesis | |
+| `/mindforge:research` | `research "query"` | Deep research using Gemini 1.5 Pro 1M context | |
+| `/mindforge:remember` | `remember [--add X|--search Y|--promote ID|--stats]` | Persistent knowledge graph management | |
+| `/mindforge:workstreams` | `workstreams [list|create|switch|status|complete]` | Manage parallel feature tracks with isolated state | v2.0.0 |
 
 ### Project setup & discovery
 
 | Command | Usage | Description | Added |
 |---|---|---|---|
-| `/mindforge:map-codebase` | `map-codebase` | Brownfield onboarding: infer stack and seed docs |
-| `/mindforge:quick` | `quick` | Run a small, single-task plan without a full phase |
-| `/mindforge:status` | `status` | Show current phase, plan status, and next action |
-| `/mindforge:health` | `health [--repair]` | Validate installation and repair drift |
-| `/mindforge:review` | `review [N]` | Run a structured review pass for a phase |
-| `/mindforge:debug` | `debug [plan-id]` | Debug a failed plan with root-cause workflow |
+| `/mindforge:map-codebase` | `map-codebase` | Brownfield onboarding: infer stack and seed docs | |
+| `/mindforge:do` | `do <text>` | Smart dispatcher for natural language intent | v2.0.0 |
+| `/mindforge:note` | `note <text> [list|promote N]` | Zero-friction idea capture and todo promotion | v2.0.0 |
+| `/mindforge:quick` | `quick` | Run a small, single-task plan without a full phase | |
+| `/mindforge:status` | `status` | Show current phase, plan status, and next action | |
+| `/mindforge:health` | `health [--repair]` | Validate installation and repair drift | |
+| `/mindforge:review` | `review [N]` | Run a structured review pass for a phase | |
+| `/mindforge:debug` | `debug [plan-id]` | Debug a failed plan with root-cause workflow | |
+| `/mindforge:add-backlog` | `add-backlog <desc>` | Park ideas in 999.x "parking lot" | v2.0.0 |
+| `/mindforge:review-backlog` | `review-backlog` | Review and promote backlog items to active phases | v2.0.0 |
+| `/mindforge:plant-seed` | `plant-seed <idea>` | Capture speculative ideas with triggers | v2.0.0 |
 
 ### Governance & compliance
 
 | Command | Usage | Description | Added |
 |---|---|---|---|
-| `/mindforge:approve` | `approve [--tier 2|3]` | Process approvals and emergency overrides |
-| `/mindforge:audit` | `audit [--phase N] [--event X] [--since DATE]` | Query `AUDIT.jsonl` history |
-| `/mindforge:security-scan` | `security-scan [--deep] [--secrets] [--deps]` | Security scan with OWASP classification |
-| `/mindforge:milestone` | `milestone [name]` | Create or update milestone definitions |
-| `/mindforge:complete-milestone` | `complete-milestone [name]` | Archive milestone and generate release report |
-| `/mindforge:retrospective` | `retrospective [N]` | Phase retrospective and improvement actions |
+| `/mindforge:approve` | `approve [--tier 2|3]` | Process approvals and emergency overrides | |
+| `/mindforge:audit` | `audit [--phase N] [--event X] [--since DATE]` | Query `AUDIT.jsonl` history | |
+| `/mindforge:security-scan` | `security-scan [--deep] [--secrets] [--deps]` | Security scan with OWASP classification | |
+| `/mindforge:milestone` | `milestone [name]` | Create or update milestone definitions | |
+| `/mindforge:complete-milestone` | `complete-milestone [name]` | Archive milestone and generate release report | |
+| `/mindforge:retrospective` | `retrospective [N]` | Phase retrospective and improvement actions | |
 
 ### Skills & plugins
 
 | Command | Usage | Description | Added |
 |---|---|---|---|
-| `/mindforge:skills` | `skills [list|validate|refresh]` | Manage core/org/project skills |
-| `/mindforge:install-skill` | `install-skill <name> [--version]` | Install skill from registry |
-| `/mindforge:publish-skill` | `publish-skill <path>` | Publish a skill to the registry |
-| `/mindforge:plugins` | `plugins [list|install|uninstall|validate]` | Manage plugin lifecycle |
+| `/mindforge:skills` | `skills [list|validate|refresh]` | Manage core/org/project skills | |
+| `/mindforge:install-skill` | `install-skill <name> [--version]` | Install skill from registry | |
+| `/mindforge:publish-skill` | `publish-skill <path>` | Publish a skill to the registry | |
+| `/mindforge:plugins` | `plugins [list|install|uninstall|validate]` | Manage plugin lifecycle | |
 
 ### Intelligence & metrics
 
 | Command | Usage | Description | Added |
 |---|---|---|---|
-| `/mindforge:metrics` | `metrics [--phase N]` | Compute quality and throughput metrics |
-| `/mindforge:profile-team` | `profile-team` | Generate team skill and ownership profile |
-| `/mindforge:benchmark` | `benchmark [--skill X]` | Measure skill effectiveness |
-| `/mindforge:tokens` | `tokens [--profile] [--summary]` | Token usage profiling and optimisation |
+| `/mindforge:metrics` | `metrics [--phase N]` | Compute quality and throughput metrics | |
+| `/mindforge:profile-team` | `profile-team` | Generate team skill and ownership profile | |
+| `/mindforge:benchmark` | `benchmark [--skill X]` | Measure skill effectiveness | |
+| `/mindforge:tokens` | `tokens [--profile] [--summary]` | Token usage profiling and optimisation | |
 
 ### Integrations & distribution
 
 | Command | Usage | Description | Added |
 |---|---|---|---|
-| `/mindforge:init-org` | `init-org` | Org-wide MindForge setup |
-| `/mindforge:sync-jira` | `sync-jira [--project KEY]` | Sync phases and plans to Jira |
-| `/mindforge:sync-confluence` | `sync-confluence [--page ...]` | Publish docs to Confluence |
-| `/mindforge:pr-review` | `pr-review [--range A..B]` | AI PR review with context |
-| `/mindforge:workspace` | `workspace [detect|plan|test]` | Monorepo workspace management |
-| `/mindforge:browse` | `browse [--navigate URL] [--command]` | Control persistent browser daemon and sessions |
-| `/mindforge:qa` | `qa [--diff] [--all]` | Run systematic visual QA and regression tests |
+| `/mindforge:init-org` | `init-org` | Org-wide MindForge setup | |
+| `/mindforge:sync-jira` | `sync-jira [--project KEY]` | Sync phases and plans to Jira | |
+| `/mindforge:sync-confluence` | `sync-confluence [--page ...]` | Publish docs to Confluence | |
+| `/mindforge:pr-review` | `pr-review [--range A..B]` | AI PR review with context | |
+| `/mindforge:workspace` | `workspace [detect|plan|test]` | Monorepo workspace management | |
+| `/mindforge:browse` | `browse [--navigate URL] [--command]` | Control persistent browser daemon and sessions | |
+| `/mindforge:qa` | `qa [--diff] [--all]` | Run systematic visual QA and regression tests | |
 
 ### Release & maintenance
 
 | Command | Usage | Description | Added |
 |---|---|---|---|
-| `/mindforge:update` | `update [--apply] [--force] [--check]` | Check for and apply framework updates |
-| `/mindforge:migrate` | `migrate [--from vX] [--to vY] [--dry-run]` | Run schema migrations |
-| `/mindforge:release` | `release [--tag vX]` | Framework release pipeline (core team) |
+| `/mindforge:update` | `update [--apply] [--force] [--check]` | Check for and apply framework updates | |
+| `/mindforge:migrate` | `migrate [--from vX] [--to vY] [--dry-run]` | Run schema migrations | |
+| `/mindforge:session-report` | `session-report` | Generate post-session summary and resource profiling | v2.0.0 |
+| `/mindforge:release` | `release [--tag vX]` | Framework release pipeline (core team) | |
 
 ### Utility
 
 | Command | Usage | Description | Added |
 |---|---|---|---|
-| `/mindforge:help` | `help` | Show all available commands and current project status |
+| `/mindforge:help` | `help` | Show all available commands and current project status | |
 
 ## Command interface contract (v1.0.0 stable)
 

package/docs/skills-authoring-guide.md

@@ -15,6 +15,28 @@ Write a new skill when:
 - Your team has standards that aren't captured in CONVENTIONS.md
 - An existing core skill doesn't match your organisation's approach
 
+## Automated Skill Generation (New in v2)
+MindForge can now generate skills automatically. Instead of writing `SKILL.md` from scratch, use the intelligent learning engine:
+
+### 1. Learn from Documentation
+```bash
+/mindforge:learn https://react.dev/learn "react-best-practices"
+```
+The agent will research the URL, extract high-value engineering patterns, and generate a high-quality `SKILL.md` with examples and triggers.
+
+### 2. Learn from Project History
+```bash
+/mindforge:learn ./src/modules/auth "auth-patterns"
+```
+This analyzes your codebase and session history to capture project-specific expertise.
+
+### 3. Community Marketplace
+```bash
+/mindforge:marketplace search "performance"
+/mindforge:marketplace install mindforge-skill-latency-optimizer
+```
+Discover and install verified skills from the MindForge community.
+
 ## Skill file structure
 
 ```
@@ -103,6 +125,13 @@ After creating SKILL.md:
 # Commit the manifest update
 ```
 
+### Quality Scoring
+All skills (automated or manual) are passed through the **7-Dimension Scorer**. To manually score a skill:
+```bash
+/mindforge:skills validate .mindforge/skills/[your-skill]
+```
+A minimum score of **60** is required for registration.
+
 ## Tier guidance
 
 | Tier | Use when | Location |

package/docs/skills-publishing-guide.md

@@ -10,11 +10,12 @@ Skills are distributed as npm packages with the `mindforge-skill-` prefix.
 - `CHANGELOG.md`
 
 ## Publish checklist
-1. Run `npx mindforge-cc validate-skill ./SKILL.md --quality`
+1. Run `/mindforge:skills validate ./SKILL.md --quality`
 2. Verify `package.json` metadata is complete
 3. Ensure `CHANGELOG.md` includes the current version
 4. Run `npm pack --dry-run` to inspect files
-5. Publish with `npm publish --access public`
+5. Publish with `/mindforge:marketplace publish` (handles pre-flight scoring)
+   - Or manually via `npm publish --access public`
 
 ## Private registries
 Set `MINDFORGE_SKILL_REGISTRY` in `.mindforge/org/integrations/INTEGRATIONS-CONFIG.md`

package/docs/testing-current-version.md

@@ -1,4 +1,4 @@
-# MindForge v2.0.0-alpha.9: In-Depth Testing Guide (Antigravity)
+# MindForge v2.0.0-alpha.10: In-Depth Testing Guide (Antigravity)
 
 This document provides a step-by-step rigorous testing flow to validate the entire MindForge framework from a blank project state. It is designed to be shared and logged for architectural review.
 
@@ -9,7 +9,7 @@ This document provides a step-by-step rigorous testing flow to validate the enti
      ```bash
      /Users/sairamugge/.vite-plus/js_runtime/node/24.14.0/bin/mindforge-cc --antigravity --local
      ```
-   - *Confirmation*: Run the command with `--version`. It must show `v2.0.0-alpha.9`.
+   - *Confirmation*: Run the command with `--version`. It must show `v2.0.0-alpha.10`.
 3. Verify the local binary exists: `ls agents/bin/install.js` (or `.agent/bin/install.js` if legacy)
 
 ## 🏗 Phase 1: Registry & Integrity
@@ -126,5 +126,5 @@ All Antigravity sessions are logged. To share your results for review, zip and s
 - `CHANGELOG.md` (Outcome summary)
 ## 💡 Troubleshooting
 - **Command not found**: Ensure you are using `./mindforge:command` or `/mindforge:command` within the agent.
-- **Wrong Version**: Run `/mindforge:health` and check for "v2.0.0-alpha.9". If it shows "v1.0.5", your installation failed or you are using the global `npx` version.
+- **Wrong Version**: Run `/mindforge:health` and check for "v2.0.0-alpha.10". If it shows "v1.0.5", your installation failed or you are using the global `npx` version.
 - **Registry Error**: Check `~/.mindforge/registry.json` exists; it is now automatically created by the v2 installer.

package/docs/upgrade.md

@@ -1,6 +1,6 @@
-# MindForge Upgrade Guide (v1.0.0)
+# MindForge Upgrade Guide (v2.0.0)
 
-This guide covers upgrades from v0.6.0 to v1.0.0.
+This guide covers upgrades from v0.6.0 to v2.0.0.
 
 ## 1. Check version
 ```bash
@@ -19,10 +19,18 @@ npx mindforge-cc@latest --claude --local --force
 ```
 
 ## 3. Migrate schema files
+
+### v0.6.0 to v1.0.0
 ```
 /mindforge:migrate --from v0.6.0 --to v1.0.0
 ```
 
+### v1.0.0 to v2.0.0
+```
+/mindforge:migrate --from v1.0.0 --to v2.0.0
+```
+MindForge v2 uses an **additive-only** migration strategy. Existing data is never deleted; only new fields (like `runtime`, `agent_id`, and `model_group`) are backfilled into your `AUDIT.jsonl` and `token-usage.jsonl` files.
+
 ## 4. Verify
 ```
 /mindforge:health
@@ -30,10 +38,16 @@ npx mindforge-cc@latest --claude --local --force
 ```
 
 ## 5. Known breaking changes
+
+### v1.0.0
 - `VERIFY_PASS_RATE_WARNING_THRESHOLD` now uses 0.0–1.0 (was 0–100)
 - `AUDIT.jsonl` now requires `session_id` (auto-backfilled)
 - `HANDOFF.json` now requires `plugin_api_version`
 
+### v2.0.0
+- **Multi-Runtime Entry Points**: If installing for Cursor or Copilot, ensure you use the correct `--local` flag to generate `.cursorrules` or `copilot-instructions.md`.
+- **Preambles**: Non-slash runtimes now have a mandatory preamble in their entry files.
+
 ## 6. Rollback
 If anything goes wrong, restore the migration backup:
 ```

package/docs/user-guide.md

@@ -1,4 +1,4 @@
-# MindForge User Guide (v2.0.0-alpha.9)
+# MindForge User Guide (v2.0.0)
 
 This guide gets you from install to productive, with the minimum needed to run
 MindForge in a real project. It assumes Node.js 18+.
@@ -32,9 +32,34 @@ npx mindforge-cc@latest --antigravity --global
 npx mindforge-cc@latest --antigravity --local
 ```
 
-### Both runtimes
+### Cursor
 ```bash
-npx mindforge-cc@latest --all --global
+npx mindforge-cc@latest --cursor --local
+```
+
+### Gemini CLI
+```bash
+npx mindforge-cc@latest --gemini --global
+```
+
+### GitHub Copilot
+```bash
+npx mindforge-cc@latest --copilot --local
+```
+
+### OpenCode
+```bash
+npx mindforge-cc@latest --opencode --global
+```
+
+### Specific Runtime (Universal)
+```bash
+npx mindforge-cc@latest --runtime <name>
+```
+
+### Multiple runtimes
+```bash
+npx mindforge-cc@latest --runtime claude,cursor --local
 ```
 
 ## 2. Verify installation
@@ -187,7 +212,10 @@ This will start the Express-based SSE bridge and open `http://localhost:7339` in
 
 ### Run schema migrations manually
 ```
-/mindforge:migrate --from v0.6.0 --to v1.0.0
+### Run schema migrations manually
+```
+/mindforge:migrate --from v1.0.0 --to v2.0.0
+```
 ```
 
 ## 11. Plugins
@@ -202,13 +230,34 @@ This will start the Express-based SSE bridge and open `http://localhost:7339` in
 /mindforge:plugins install mindforge-plugin-<name>
 ```
 
-## 12. Skills
+## 12. Custom Runtimes (v2)
+MindForge v2 allows you to scaffold support for any AI agent runtime by generating the necessary instruction files and directory structures.
+
+### Scaffold a New Runtime
+```bash
+/mindforge:new-runtime
 ```
-/mindforge:skills list
-/mindforge:skills validate
+This command will interview you about the runtime's name, entry file (e.g., `INSTRUCTIONS.md`), and whether it supports slash commands. It then scaffolds the standard MindForge preamble and directory structure for that agent.
+
+## 12. Self-Building Skills (v2)
+MindForge can now learn new skills automatically from documentation, project history, or the community marketplace.
+
+### Learn from Source
+To create a new skill from a URL, local file, or npm package:
+```bash
+/mindforge:learn https://docs.prisma.io "prisma-best-practices"
+```
+This triggers a 7-step generation pipeline that researches, extracts patterns, and scores the resulting skill.
+
+### Skills Marketplace
+Discover and install community-authored skills:
+```bash
+/mindforge:marketplace search "tailwind"
+/mindforge:marketplace install mindforge-skill-react-patterns
 ```
 
-To publish or install a skill, see `docs/skills-publishing-guide.md`.
+### Auto-Capture
+MindForge automatically detects recurring patterns in your phase outputs. After a successful `/mindforge:execute-phase`, the agent may suggest capturing a new skill if it identifies high-value engineering patterns.
 
 ## 13. Token usage profiling
 ```

package/docs/usp-features.md

@@ -1,7 +1,7 @@
-# MindForge v2.0.0 — Unique Selling Points, Features, and Best Practices (v2.0.0-alpha.9)
+# MindForge v2.0.0 — Unique Selling Points, Features, and Best Practices (v2.0.0)
 
 This document summarizes what makes MindForge v2.0.0 distinct, what features
-are included in the latest alpha release, and how to use them effectively.
+are included in the official release, and how to use them effectively.
 
 ---
 
@@ -46,9 +46,12 @@ are included in the latest alpha release, and how to use them effectively.
 12. **Real-time Observability Dashboard (v2)**
     - High-fidelity web interface for live audit streams, metrics visualization, and browser-based governance with zero performance overhead.
 
+13. **Self-Building Skills Platform (v2)**
+    - Automatically capture and score engineering patterns from docs, npm, or session history into high-quality `SKILL.md` files with non-bypassable quality gates.
+
 ---
 
-## Feature Set (v1.0.0)
+## Feature Set (v2.0.0)
 
 ### 1. Installation & Distribution
 **What it does:** Production‑grade installer with update, uninstall, and CI support.
@@ -214,6 +217,18 @@ Access at `http://localhost:7339` (Localhost-only for security).
 
 ---
 
+### 17. Self‑Building Skills Platform (v2)
+**What it does:** Automatically captures engineering knowledge into high-quality `SKILL.md` files. Features a 7-dimension quality scorer and npm-based marketplace integration.
+
+**How to use:**
+```bash
+/mindforge:learn https://docs.example.com "my-skill"
+/mindforge:marketplace search "auth"
+/mindforge:marketplace install mindforge-skill-example
+```
+
+---
+
 ### 15. SDK (TypeScript)
 **What it does:** Programmatic access to health, audit log, event stream, and commands.
 
@@ -226,7 +241,7 @@ const report = await client.health();
 
 ---
 
-## Best Practices for v1.0.0
+## Best Practices for v2.0.0
 
 1. **Always run health after install**
    - `/mindforge:health --repair` fixes drift immediately.
@@ -271,6 +286,6 @@ const report = await client.health();
 ---
 
 ## Summary
-MindForge v1.0.0 combines governance, observability, and execution rigor into a
-single workflow engine that works across Claude Code and Antigravity. Its core
+MindForge v2.0.0 combines governance, observability, and autonomous execution rigor into a
+single workflow engine that works across 6 major AI runtimes. Its core
 value is consistent, repeatable quality in long‑running AI development sessions.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mindforge-cc",
-  "version": "2.0.0-alpha.9",
+  "version": "2.1.0",
   "description": "MindForge - Enterprise Agentic Framework for Claude Code and Antigravity",
   "bin": {
     "mindforge-cc": "bin/install.js"