mindforge-cc 11.4.0 → 11.5.0

package/.claude/commands/mindforge/product-spec.md

@@ -15,6 +15,41 @@ Arguments: $ARGUMENTS (feature name or description, optional --framework for pri
 Knowledge: PROJECT.md, existing BRDs, market research, competitive analysis, user feedback.
 </context>
 
+<gated_question_flow>
+> Adapted from the PRP-PRD interactive flow (PRPs-agentic-eng by Wirasm). This
+> question-flow runs BEFORE and AROUND the `<process>` below — it augments, it
+> does not replace, the personas / RICE / MoSCoW depth. Each gate is an explicit
+> STOP: present the questions, then WAIT FOR USER RESPONSE before proceeding.
+
+Flow: `INITIATE -> FOUNDATION -> GROUNDING -> DEEP DIVE -> GROUNDING (technical) -> DECISIONS -> GENERATE`
+
+1. **INITIATE** — If `$ARGUMENTS` is empty, ask "What do you want to build?" If
+   provided, restate your understanding and ask the user to confirm/adjust.
+   **GATE: wait for the user.**
+2. **FOUNDATION** — Ask (all at once): Who has the problem? What is the observable
+   pain? Why can't they solve it today (and why do alternatives fail)? Why now?
+   How will we know it's solved? **GATE: wait for the user.**
+3. **GROUNDING (market + codebase)** — Research market/competitor context; if a
+   codebase exists, explore relevant patterns. Summarize findings, ask "Does this
+   refine your thinking?" **GATE: brief pause for the user** (may be "continue").
+4. **DEEP DIVE** — Ask: one-sentence vision, primary user, Job-to-Be-Done, explicit
+   non-users, constraints. **GATE: wait for the user.**
+5. **GROUNDING (technical feasibility)** — Trace how similar features are built,
+   map integration points, rate feasibility HIGH/MEDIUM/LOW with reasons. Summarize,
+   ask for unknown technical constraints. **GATE: brief pause for the user.**
+6. **DECISIONS** — Ask: MVP definition, must-have vs nice-to-have, key hypothesis
+   ("We believe [capability] will [solve problem] for [users]; we'll know we're
+   right when [measurable outcome]"), explicit out-of-scope, open questions.
+   **GATE: wait for the user before generating.**
+7. **GENERATE** — Only after the DECISIONS gate, run the `<process>` below and
+   write the output (see `<output_mapping>`).
+
+**Anti-invention rule (MANDATORY)**: Never fill a section with plausible-sounding
+fluff. If information is missing, write **`TBD - needs research`** (and name the
+method to resolve it) rather than inventing an answer. Acknowledge uncertainty
+honestly; list open questions instead of hiding them.
+</gated_question_flow>
+
 <process>
 1. **Define personas**: Create 2-4 user personas relevant to the feature:
    - Name, role, and demographic summary
@@ -65,6 +100,7 @@ Knowledge: PROJECT.md, existing BRDs, market research, competitive analysis, use
    - Technical Constraints and Dependencies
    - Success Metrics (leading and lagging indicators)
    - Release Plan (milestones with dates)
+   - **Implementation Phases** (dependency table — see `<output_mapping>`)
    - Open Questions and Risks
 
 8. **Define success metrics**: For the feature overall:
@@ -88,3 +124,43 @@ Knowledge: PROJECT.md, existing BRDs, market research, competitive analysis, use
     - Timeline with confidence intervals
     - Request specific decisions from specific stakeholders
 </process>
+
+<output_mapping>
+> Adapted from the PRP-PRD Implementation-Phases pattern. The PRD's phase table
+> is the hand-off that lets `/mindforge:plan-phase` and `/mindforge:plan-write`
+> auto-select the next pending phase.
+
+**Primary output path**: write the generated PRD to `.planning/REQUIREMENTS.md`
+(create the `.planning/` directory if it does not exist). This is the file
+`/mindforge:execute-phase` and `/mindforge:plan-phase` read from.
+
+**Implementation-Phases dependency table** — include this section in
+`.planning/REQUIREMENTS.md`. The `Status` / `Parallel` / `Depends` columns let
+downstream commands auto-select the next eligible pending phase (a phase is
+eligible when its `Status` is `pending` and every phase in `Depends` is `complete`):
+
+```markdown
+## Implementation Phases
+
+<!--
+  STATUS:   pending | in-progress | complete
+  PARALLEL: phases that can run concurrently (e.g., "with 4" or "-")
+  DEPENDS:  phases that must be complete first (e.g., "1, 2" or "-")
+-->
+
+| # | Phase | Description | Status | Parallel | Depends |
+|---|-------|-------------|--------|----------|---------|
+| 1 | {Phase name} | {What this phase delivers} | pending | - | - |
+| 2 | {Phase name} | {What this phase delivers} | pending | - | 1 |
+| 3 | {Phase name} | {What this phase delivers} | pending | with 4 | 2 |
+| 4 | {Phase name} | {What this phase delivers} | pending | with 3 | 2 |
+| 5 | {Phase name} | {What this phase delivers} | pending | - | 3, 4 |
+```
+
+**Anti-invention rule still applies**: any phase whose scope is not yet known
+gets `TBD - needs research` in its Description rather than an invented deliverable.
+
+**Next step to report**: tell the user to run `/mindforge:plan-phase` (or
+`/mindforge:plan-write .planning/REQUIREMENTS.md`), which will read this table and
+plan the next pending, dependency-satisfied phase.
+</output_mapping>

package/.mindforge/config.json

@@ -1,11 +1,11 @@
 {
-  "version": "11.4.0",
+  "version": "11.5.0",
   "environment": "development",
   "governance": {
     "drift_threshold": 0.75,
     "critical_drift_threshold": 0.5,
     "res_threshold": 0.8,
-    "active_did": "did:mindforge:39723c91-8532-400f-855f-720ec0a5387c"
+    "active_did": "did:mindforge:f5ee24cf-f359-475e-bd76-c83e3d6fce02"
   },
   "revops": {
     "market_registry": {

package/.mindforge/engine/instincts/instinct-schema.md

@@ -20,11 +20,12 @@ Each instinct is a single JSON line in `instinct-store.jsonl`:
   "times_succeeded": 6,
   "times_failed": 2,
   "project": "mindforge",
+  "project_id": "a1b2c3d4e5f6",
   "tags": ["database", "documentation", "patterns"],
   "status": "active",
   "promoted_to_skill": null,
   "last_applied_at": "2026-05-25T14:20:00Z",
-  "source_sessions": ["session-abc123", "session-def456"]
+  "source": "auto-capture"
 }
 ```
 
@@ -41,12 +42,13 @@ Each instinct is a single JSON line in `instinct-store.jsonl`:
 | times_applied | int | yes | Total times this instinct was applied |
 | times_succeeded | int | yes | Times application led to positive outcome |
 | times_failed | int | yes | Times application led to negative outcome or correction |
-| project | string | yes | Project scope (instincts never leak between projects) |
+| project | string | yes | Human-readable project name (or `global`) |
+| project_id | string | yes | Stable 12-char git-remote hash; the read-time scope key (instincts never leak between projects). `global` outside a git repo |
 | tags | string[] | yes | Classification tags for retrieval |
 | status | enum | yes | One of: active, promoted, deprecated, pruned |
-| promoted_to_skill | string|null | yes | Skill name if promoted, null otherwise |
-| last_applied_at | ISO-8601 | yes | When instinct was last used |
-| source_sessions | string[] | yes | Session IDs where this instinct was observed/reinforced |
+| promoted_to_skill | string\|null | yes | Skill name if promoted, null otherwise |
+| last_applied_at | ISO-8601\|null | yes | When instinct was last used (null until first applied) |
+| source | string | yes | Origin: `auto-capture` (PostToolUse hook), `manual` (/mindforge:learn-instinct), `imported`, or `observer` |
 
 ## Confidence Scoring
 
@@ -56,16 +58,22 @@ confidence = (times_succeeded / times_applied) * weight_factor
 where weight_factor = min(1.0, times_applied / 10)
 ```
 
-- New instincts start at 0.5 confidence (neutral)
-- Each success: recalculate with updated counts
-- Each failure: recalculate with updated counts
+Starting confidence depends on `source` (a new instinct has `times_applied: 0`,
+so the ratio formula does not yet apply — it seeds an initial value):
+- `auto-capture` (PostToolUse hook): **0.3** — low trust, inferred from a single success
+- `manual` (/mindforge:learn-instinct): **0.7** — user-stated, higher trust
+- `imported` / `observer`: as stamped by the importer/observer (default 0.3)
+- 0.5 is the neutral midpoint the ratio formula trends toward once applications accrue
+
+Then, once `times_applied > 0`:
+- Each success/failure recalculates `confidence` with updated counts
 - Weight factor prevents high confidence from single observations
 - Minimum 5 applications before promotion is considered
 
 ## Status Transitions
 
 ```
-[new observation] → active (confidence: 0.5)
+[auto-capture] → active (confidence: 0.3)   [manual] → active (0.7)
                        ↓
             confidence >= 0.85 AND times_applied >= 5
                        ↓

package/.mindforge/imported-agents.jsonl

@@ -63,6 +63,8 @@
 {"name":"game-developer","path":"subagents/categories/07-specialized-domains/game-developer.md","category":"07-specialized-domains","model":"sonnet","description":"Use this agent when implementing game systems, optimizing graphics rendering, building multiplayer networking, or developing gameplay mechanics for games targeting specific platforms."}
 {"name":"gdpr-ccpa-compliance","path":"subagents/categories/04-quality-security/gdpr-ccpa-compliance.md","category":"04-quality-security","model":"sonnet","description":"Use when the user needs to understand GDPR or CCPA compliance, review data practices, or assess privacy requirements. Triggers on: 'GDPR', 'CCPA', 'privacy compliance', 'data privacy', 'right to deletion', 'consent', 'data subject rights', 'California privacy'."}
 {"name":"git-workflow-manager","path":"subagents/categories/06-developer-experience/git-workflow-manager.md","category":"06-developer-experience","model":"haiku","description":"Use this agent when you need to design, establish, or optimize Git workflows, branching strategies, and merge management for a project or team."}
+{"name":"go-build-resolver","path":"subagents/categories/04-quality-security/go-build-resolver.md","category":"04-quality-security","model":"sonnet","description":"Go build, vet, and compilation error resolution specialist. Fixes build errors, go vet issues, and linter warnings with minimal changes. Use when Go builds fail."}
+{"name":"go-reviewer","path":"subagents/categories/04-quality-security/go-reviewer.md","category":"04-quality-security","model":"sonnet","description":"Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects."}
 {"name":"golang-pro","path":"subagents/categories/02-language-specialists/golang-pro.md","category":"02-language-specialists","model":"sonnet","description":"Use when building Go applications requiring concurrent programming, high-performance systems, microservices, or cloud-native architectures where idiomatic patterns, error handling excellence, and efficiency are critical."}
 {"name":"graphql-architect","path":"subagents/categories/01-core-development/graphql-architect.md","category":"01-core-development","model":"opus","description":"Use this agent when designing or evolving GraphQL schemas across microservices, implementing federation architectures, or optimizing query performance in distributed graphs."}
 {"name":"growth-loops","path":"subagents/categories/08-business-product/growth-loops.md","category":"08-business-product","model":"sonnet","description":"Use when the user wants to design a growth loop, understand PLG mechanics, or build sustainable acquisition. Triggers on: 'growth loop', 'flywheel', 'viral loop', 'PLG growth', 'product-led growth', 'growth mechanics', 'how do we grow', 'word of mouth'."}
@@ -112,16 +114,21 @@
 {"name":"project-manager","path":"subagents/categories/08-business-product/project-manager.md","category":"08-business-product","model":"haiku","description":"Use this agent when you need to establish project plans, track execution progress, manage risks, control budget/schedule, and coordinate stakeholders across complex initiatives."}
 {"name":"prompt-engineer-cc","path":"subagents/categories/05-data-ai/prompt-engineer-cc.md","category":"05-data-ai","model":"sonnet","description":"Use this agent when you need to design, optimize, test, or evaluate prompts for large language models in production systems."}
 {"name":"python-pro","path":"subagents/categories/02-language-specialists/python-pro.md","category":"02-language-specialists","model":"sonnet","description":"Use this agent when you need to build type-safe, production-ready Python code for web APIs, system utilities, or complex applications requiring modern async patterns and extensive type coverage."}
+{"name":"python-reviewer","path":"subagents/categories/04-quality-security/python-reviewer.md","category":"04-quality-security","model":"sonnet","description":"Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects."}
 {"name":"qa-expert","path":"subagents/categories/04-quality-security/qa-expert.md","category":"04-quality-security","model":"sonnet","description":"Use this agent when you need comprehensive quality assurance strategy, test planning across the entire development cycle, or quality metrics analysis to improve overall software quality."}
 {"name":"quant-analyst","path":"subagents/categories/07-specialized-domains/quant-analyst.md","category":"07-specialized-domains","model":"opus","description":"Use this agent when you need to develop quantitative trading strategies, build financial models with rigorous mathematical foundations, or conduct advanced risk analytics for derivatives and portfolios. Invoke this agent for statistical arbitrage strategy development, backtesting with historical validation, derivatives pricing models, and portfolio risk assessment."}
 {"name":"rails-expert","path":"subagents/categories/02-language-specialists/rails-expert.md","category":"02-language-specialists","model":"sonnet","description":"Use when building or modernizing Rails applications requiring API development, Hotwire reactivity, real-time features, background job processing, deployment automation, or Rails-idiomatic patterns for maximum productivity. Version-aware: adapts to Rails 7.x and 8.x projects."}
+{"name":"react-build-resolver","path":"subagents/categories/04-quality-security/react-build-resolver.md","category":"04-quality-security","model":"sonnet","description":"Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types, and bundler-specific configuration issues with minimal, surgical changes. MUST BE USED when a React build fails."}
+{"name":"react-reviewer","path":"subagents/categories/04-quality-security/react-reviewer.md","category":"04-quality-security","model":"sonnet","description":"Expert React/JSX code reviewer specializing in hook correctness, render performance, server/client component boundaries, accessibility, and React-specific security. Use for any change touching .tsx/.jsx files or React component logic. MUST BE USED for React projects."}
 {"name":"react-specialist-cc","path":"subagents/categories/02-language-specialists/react-specialist-cc.md","category":"02-language-specialists","model":"sonnet","description":"Use when optimizing existing React applications for performance, implementing advanced React 18+ features, or solving complex state management and architectural challenges within React codebases."}
 {"name":"readme-generator","path":"subagents/categories/06-developer-experience/readme-generator.md","category":"06-developer-experience","model":"sonnet","description":"Use this agent when you need a maintainer-ready README built from exact repository reality, with deep codebase scanning, zero hallucination, and optional git commit/push only when explicitly requested."}
 {"name":"refactoring-specialist","path":"subagents/categories/06-developer-experience/refactoring-specialist.md","category":"06-developer-experience","model":"sonnet","description":"Use when you need to transform poorly structured, complex, or duplicated code into clean, maintainable systems while preserving all existing behavior."}
 {"name":"reinforcement-learning-engineer","path":"subagents/categories/05-data-ai/reinforcement-learning-engineer.md","category":"05-data-ai","model":"sonnet","description":"Use when designing RL environments, training agents with reward optimization, implementing policy gradient methods, or deploying decision-making systems for robotics, gaming, and autonomous operations."}
 {"name":"research-analyst","path":"subagents/categories/10-research-analysis/research-analyst.md","category":"10-research-analysis","model":"sonnet","description":"Use this agent when you need comprehensive research across multiple sources with synthesis of findings into actionable insights, trend identification, and detailed reporting."}
 {"name":"risk-manager","path":"subagents/categories/07-specialized-domains/risk-manager.md","category":"07-specialized-domains","model":"opus","description":"Use this agent when you need to identify, quantify, and mitigate enterprise-level risks across financial, operational, regulatory, and strategic domains. Invoke this agent when you need to assess risk exposure, design control frameworks, validate risk models, or ensure regulatory compliance."}
+{"name":"rust-build-resolver","path":"subagents/categories/04-quality-security/rust-build-resolver.md","category":"04-quality-security","model":"sonnet","description":"Rust build, compilation, and dependency error resolution specialist. Fixes cargo build errors, borrow checker issues, and Cargo.toml problems with minimal changes. Use when Rust builds fail."}
 {"name":"rust-engineer","path":"subagents/categories/02-language-specialists/rust-engineer.md","category":"02-language-specialists","model":"sonnet","description":"Use when building Rust systems where memory safety, ownership patterns, zero-cost abstractions, and performance optimization are critical for systems programming, embedded development, async applications, or high-performance services."}
+{"name":"rust-reviewer","path":"subagents/categories/04-quality-security/rust-reviewer.md","category":"04-quality-security","model":"sonnet","description":"Expert Rust code reviewer specializing in ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Use for all Rust code changes. MUST BE USED for Rust projects."}
 {"name":"sales-engineer","path":"subagents/categories/08-business-product/sales-engineer.md","category":"08-business-product","model":"sonnet","description":"Use this agent when you need to conduct technical pre-sales activities including solution architecture, proof-of-concept development, and technical demonstrations for complex sales deals."}
 {"name":"scientific-literature-researcher","path":"subagents/categories/10-research-analysis/scientific-literature-researcher.md","category":"10-research-analysis","model":"sonnet","description":"Use when you need to search scientific literature and retrieve structured experimental data from published studies. Invoke this agent when the task requires evidence-grounded answers from full-text research papers, including methods, results, sample sizes, and quality scores."}
 {"name":"scrum-master","path":"subagents/categories/08-business-product/scrum-master.md","category":"08-business-product","model":"haiku","description":"Use when teams need facilitation, process optimization, velocity improvement, or agile ceremony management—especially for sprint planning, retrospectives, impediment removal, and scaling agile practices across multiple teams."}
@@ -129,6 +136,7 @@
 {"name":"security-auditor","path":"subagents/categories/04-quality-security/security-auditor.md","category":"04-quality-security","model":"opus","description":"Use this agent when conducting comprehensive security audits, compliance assessments, or risk evaluations across systems, infrastructure, and processes. Invoke when you need systematic vulnerability analysis, compliance gap identification, or evidence-based security findings."}
 {"name":"security-engineer","path":"subagents/categories/03-infrastructure/security-engineer.md","category":"03-infrastructure","model":"opus","description":"Use this agent when implementing comprehensive security solutions across infrastructure, building automated security controls into CI/CD pipelines, or establishing compliance and vulnerability management programs. Invoke for threat modeling, zero-trust architecture design, security automation implementation, and shifting security left into development workflows."}
 {"name":"seo-specialist-cc","path":"subagents/categories/07-specialized-domains/seo-specialist-cc.md","category":"07-specialized-domains","model":"haiku","description":"Use this agent when you need comprehensive SEO optimization encompassing technical audits, keyword strategy, content optimization, and search rankings improvement."}
+{"name":"silent-failure-hunter","path":"subagents/categories/04-quality-security/silent-failure-hunter.md","category":"04-quality-security","model":"sonnet","description":"Use this agent to review code for silent failures, swallowed errors, dangerous fallbacks, and missing error propagation. Read-only diff scanner that complements code-reviewer and security-auditor in review/verify gates."}
 {"name":"slack-expert","path":"subagents/categories/06-developer-experience/slack-expert.md","category":"06-developer-experience","model":"sonnet","description":"Use this agent when developing Slack applications, implementing Slack API integrations, or reviewing Slack bot code for security and best practices."}
 {"name":"spring-boot-engineer","path":"subagents/categories/02-language-specialists/spring-boot-engineer.md","category":"02-language-specialists","model":"sonnet","description":"Use this agent when building enterprise Spring Boot 3+ applications requiring microservices architecture, cloud-native deployment, or reactive programming patterns."}
 {"name":"sql-pro","path":"subagents/categories/02-language-specialists/sql-pro.md","category":"02-language-specialists","model":"sonnet","description":"Use this agent when you need to optimize complex SQL queries, design efficient database schemas, or solve performance issues across PostgreSQL, MySQL, SQL Server, and Oracle requiring advanced query optimization, index strategies, or data warehouse patterns."}
@@ -142,7 +150,9 @@
 {"name":"test-automator","path":"subagents/categories/04-quality-security/test-automator.md","category":"04-quality-security","model":"sonnet","description":"Use this agent when you need to build, implement, or enhance automated test frameworks, create test scripts, or integrate testing into CI/CD pipelines."}
 {"name":"tooling-engineer","path":"subagents/categories/06-developer-experience/tooling-engineer.md","category":"06-developer-experience","model":"sonnet","description":"Use this agent when you need to build or enhance developer tools including CLIs, code generators, build tools, and IDE extensions."}
 {"name":"trend-analyst","path":"subagents/categories/10-research-analysis/trend-analyst.md","category":"10-research-analysis","model":"sonnet","description":"Use when analyzing emerging patterns, predicting industry shifts, or developing future scenarios to inform strategic planning and competitive positioning."}
+{"name":"type-design-analyzer","path":"subagents/categories/04-quality-security/type-design-analyzer.md","category":"04-quality-security","model":"sonnet","description":"Use this agent to grade type design on whether it makes illegal states unrepresentable — scoring encapsulation, invariant expression, invariant usefulness, and enforcement. Read-only; pairs with the typescript and rust reviewers."}
 {"name":"typescript-pro","path":"subagents/categories/02-language-specialists/typescript-pro.md","category":"02-language-specialists","model":"sonnet","description":"Use when implementing TypeScript code requiring advanced type system patterns, complex generics, type-level programming, or end-to-end type safety across full-stack applications."}
+{"name":"typescript-reviewer","path":"subagents/categories/04-quality-security/typescript-reviewer.md","category":"04-quality-security","model":"sonnet","description":"Expert TypeScript/JavaScript code reviewer specializing in type safety, async correctness, Node/web security, and idiomatic patterns. Use for all TypeScript and JavaScript code changes. MUST BE USED for TypeScript/JavaScript projects."}
 {"name":"ui-designer","path":"subagents/categories/01-core-development/ui-designer.md","category":"01-core-development","model":"sonnet","description":"Use this agent when designing visual interfaces, creating design systems, building component libraries, or refining user-facing aesthetics requiring expert visual design, interaction patterns, and accessibility considerations."}
 {"name":"ui-ux-tester","path":"subagents/categories/04-quality-security/ui-ux-tester.md","category":"04-quality-security","model":"sonnet","description":"Use this agent when you need exhaustive UI and UX functionality testing driven by documented user flows, with browser or desktop interaction tooling and structured defect reporting."}
 {"name":"ux-researcher","path":"subagents/categories/08-business-product/ux-researcher.md","category":"08-business-product","model":"sonnet","description":"Use this agent when you need to conduct user research, analyze user behavior, or generate actionable insights to validate design decisions and uncover user needs. Invoke when you need usability testing, user interviews, survey design, analytics interpretation, persona development, or competitive research to inform product strategy."}

package/.mindforge/manifests/install-components.json

@@ -0,0 +1,36 @@
+{
+  "version": 1,
+  "_comment": "Optional install components for the MindForge manifest engine (INERT). A component is a named module grouping the resolver can ADD (--with) or REMOVE (--without) on top of a profile. 'family' classifies the component for listing/filtering. Module ids must exist in install-modules.json. Replaces ad-hoc flags once a driver wires this.",
+  "components": [
+    {
+      "id": "subagents",
+      "family": "capability",
+      "description": "The imported subagent corpus (subagents/categories). Heavy; excluded from minimal/standard, included in full.",
+      "modules": ["subagents"]
+    },
+    {
+      "id": "integrations",
+      "family": "capability",
+      "description": "Third-party integration adapters (.mindforge/integrations). Beta.",
+      "modules": ["integrations"]
+    },
+    {
+      "id": "docs",
+      "family": "capability",
+      "description": "Reference and template documentation (docs/References + docs/Templates).",
+      "modules": ["docs-references", "docs-templates"]
+    },
+    {
+      "id": "hooks",
+      "family": "capability",
+      "description": "Runtime hook scripts (.agent/hooks): TrustGate, guards, lib helpers. Drop with --without hooks for a hook-free install.",
+      "modules": ["hooks-runtime"]
+    },
+    {
+      "id": "engine",
+      "family": "capability",
+      "description": "The full engine stack: engine core, governance, intelligence, models, and engine-format skills.",
+      "modules": ["engine-core", "governance", "intelligence", "models", "engine-skills"]
+    }
+  ]
+}

package/.mindforge/manifests/install-modules.json

@@ -0,0 +1,193 @@
+{
+  "version": 1,
+  "_comment": "MindForge install module vocabulary (INERT). Each module names a real, package.json-files[]-covered asset path the installer already copies. The adapter-factory that would CONSUME a resolved plan is deferred; this manifest + resolver ship inert (the live install() path is unchanged). 'targets' uses installer-core RUNTIMES ids. Validated by .mindforge/schemas/install-modules.schema.json.",
+  "modules": [
+    {
+      "id": "entry-claude",
+      "kind": "configs",
+      "description": "Claude runtime entry document (.claude/CLAUDE.md).",
+      "paths": [".claude/CLAUDE.md"],
+      "targets": ["claude", "cursor", "opencode", "copilot"],
+      "dependencies": [],
+      "defaultInstall": true,
+      "cost": "light",
+      "stability": "stable"
+    },
+    {
+      "id": "entry-agent",
+      "kind": "configs",
+      "description": "Agent runtime entry document (.agent/CLAUDE.md) for Antigravity/Gemini-style harnesses.",
+      "paths": [".agent/CLAUDE.md"],
+      "targets": ["antigravity", "gemini"],
+      "dependencies": [],
+      "defaultInstall": true,
+      "cost": "light",
+      "stability": "stable"
+    },
+    {
+      "id": "parameter-registry",
+      "kind": "configs",
+      "description": "MINDFORGE.md parameter registry (the session-start source of truth).",
+      "paths": ["MINDFORGE.md"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": [],
+      "defaultInstall": true,
+      "cost": "light",
+      "stability": "stable"
+    },
+    {
+      "id": "commands-claude",
+      "kind": "commands",
+      "description": "Claude slash-command corpus under .claude/commands/mindforge.",
+      "paths": [".claude/commands/mindforge"],
+      "targets": ["claude", "cursor", "opencode", "copilot"],
+      "dependencies": ["entry-claude"],
+      "defaultInstall": true,
+      "cost": "medium",
+      "stability": "stable"
+    },
+    {
+      "id": "commands-agent",
+      "kind": "commands",
+      "description": "Agent-runtime command sets (.agent/mindforge + .agent/forge namespaces).",
+      "paths": [".agent/mindforge", ".agent/forge"],
+      "targets": ["antigravity", "gemini"],
+      "dependencies": ["entry-agent"],
+      "defaultInstall": true,
+      "cost": "medium",
+      "stability": "stable"
+    },
+    {
+      "id": "skills",
+      "kind": "skills",
+      "description": "Skill corpus under .agent/skills (SKILL.md definitions).",
+      "paths": [".agent/skills"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": [],
+      "defaultInstall": true,
+      "cost": "medium",
+      "stability": "stable"
+    },
+    {
+      "id": "hooks-runtime",
+      "kind": "hooks",
+      "description": "Runtime hook scripts under .agent/hooks (TrustGate, guards, lib helpers).",
+      "paths": [".agent/hooks"],
+      "targets": ["claude", "antigravity", "cursor", "gemini", "copilot"],
+      "dependencies": [],
+      "defaultInstall": true,
+      "cost": "medium",
+      "stability": "stable"
+    },
+    {
+      "id": "personas",
+      "kind": "agents",
+      "description": "Persona prompt library under .mindforge/personas.",
+      "paths": [".mindforge/personas"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": [],
+      "defaultInstall": true,
+      "cost": "light",
+      "stability": "stable"
+    },
+    {
+      "id": "subagents",
+      "kind": "agents",
+      "description": "Imported subagent corpus under subagents/categories.",
+      "paths": ["subagents/categories"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": [],
+      "defaultInstall": true,
+      "cost": "heavy",
+      "stability": "stable"
+    },
+    {
+      "id": "engine-core",
+      "kind": "engine",
+      "description": "MindForge engine binary logic and schemas under .mindforge/engine.",
+      "paths": [".mindforge/engine"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": [],
+      "defaultInstall": true,
+      "cost": "heavy",
+      "stability": "stable"
+    },
+    {
+      "id": "governance",
+      "kind": "engine",
+      "description": "Tier-3 governance assets under .mindforge/governance.",
+      "paths": [".mindforge/governance"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": ["engine-core"],
+      "defaultInstall": true,
+      "cost": "medium",
+      "stability": "stable"
+    },
+    {
+      "id": "intelligence",
+      "kind": "engine",
+      "description": "Neural/intelligence assets under .mindforge/intelligence.",
+      "paths": [".mindforge/intelligence"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": ["engine-core"],
+      "defaultInstall": true,
+      "cost": "medium",
+      "stability": "stable"
+    },
+    {
+      "id": "integrations",
+      "kind": "engine",
+      "description": "Third-party integration adapters under .mindforge/integrations.",
+      "paths": [".mindforge/integrations"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": ["engine-core"],
+      "defaultInstall": false,
+      "cost": "medium",
+      "stability": "beta"
+    },
+    {
+      "id": "models",
+      "kind": "engine",
+      "description": "Model provider definitions under .mindforge/models.",
+      "paths": [".mindforge/models"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": ["engine-core"],
+      "defaultInstall": true,
+      "cost": "light",
+      "stability": "stable"
+    },
+    {
+      "id": "engine-skills",
+      "kind": "skills",
+      "description": "Engine-format skills under .mindforge/skills (full schema).",
+      "paths": [".mindforge/skills"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": ["engine-core"],
+      "defaultInstall": true,
+      "cost": "medium",
+      "stability": "stable"
+    },
+    {
+      "id": "docs-references",
+      "kind": "configs",
+      "description": "Reference documentation under docs/References.",
+      "paths": ["docs/References"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": [],
+      "defaultInstall": false,
+      "cost": "light",
+      "stability": "stable"
+    },
+    {
+      "id": "docs-templates",
+      "kind": "configs",
+      "description": "Planning/document templates under docs/Templates.",
+      "paths": ["docs/Templates"],
+      "targets": ["claude", "antigravity", "cursor", "opencode", "gemini", "copilot"],
+      "dependencies": [],
+      "defaultInstall": false,
+      "cost": "light",
+      "stability": "stable"
+    }
+  ]
+}

package/.mindforge/manifests/install-profiles.json

@@ -0,0 +1,57 @@
+{
+  "version": 1,
+  "_comment": "Named install profiles for the MindForge manifest engine (INERT). Each profile is a curated module bundle resolved by bin/installer/install-manifests.js. Module ids must exist in install-modules.json; dependencies are pulled in automatically by the resolver. Replaces the two-boolean --minimal/--with-utils selectivity once a driver wires this.",
+  "profiles": {
+    "minimal": {
+      "description": "Smallest viable install: entry docs, parameter registry, command corpus, and skills. No heavy engine subtrees or subagent corpus.",
+      "modules": [
+        "entry-claude",
+        "entry-agent",
+        "parameter-registry",
+        "commands-claude",
+        "commands-agent",
+        "skills"
+      ]
+    },
+    "standard": {
+      "description": "Default install: minimal plus runtime hooks, personas, engine core, governance, intelligence, models, and engine-format skills. Excludes the heavy subagent corpus and optional docs.",
+      "modules": [
+        "entry-claude",
+        "entry-agent",
+        "parameter-registry",
+        "commands-claude",
+        "commands-agent",
+        "skills",
+        "hooks-runtime",
+        "personas",
+        "engine-core",
+        "governance",
+        "intelligence",
+        "models",
+        "engine-skills"
+      ]
+    },
+    "full": {
+      "description": "Everything: standard plus the subagent corpus, integrations, and reference/template docs.",
+      "modules": [
+        "entry-claude",
+        "entry-agent",
+        "parameter-registry",
+        "commands-claude",
+        "commands-agent",
+        "skills",
+        "hooks-runtime",
+        "personas",
+        "subagents",
+        "engine-core",
+        "governance",
+        "intelligence",
+        "integrations",
+        "models",
+        "engine-skills",
+        "docs-references",
+        "docs-templates"
+      ]
+    }
+  }
+}

package/.mindforge/memory/sync-manifest.json

@@ -1,6 +1,6 @@
 {
   "pattern-library.jsonl": {
-    "lastSync": "2026-06-05T20:10:07.452Z",
+    "lastSync": "2026-06-11T08:14:04.496Z",
     "localCount": 1
   }
 }